Text Replacement
Tests deterministic text transformations: renaming characters/locations, expanding contractions, tense rewriting, POV shifts, gender swaps, combined transformations, and word avoidance. Scored by checking each expected change independently.
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 97% | $0.0003 | 1.7s | |
| Gemini 3.1 Flash Lite (Preview) | 99% | $0.0010 | 1.8s | |
| Mistral Small 4 | 96% | $0.0004 | 3.3s | |
| Gemini 3.1 Flash Lite (Reasoning) | 99% | $0.0010 | 3.1s | |
| Gemini 3.1 Flash Lite | 99% | $0.0010 | 2.8s | |
| GPT-6 Luna | 98% | $0.0003 | 4.7s | |
| Mistral Small 3.2 24B | 97% | $0.0002 | 5.0s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 98% | $0.0015 | 1.5s | |
| Gemini 3.5 Flash Lite (Reasoning) | 98% | $0.0015 | 1.5s | |
| Gemini 2.5 Flash | 99% | $0.0015 | 2.2s | |
| DeepSeek V4 Flash | 97% | $0.0002 | 8.1s | |
| GPT-6 Luna (Reasoning, Medium) | 99% | $0.0005 | 8.2s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 98% | $0.0002 | 10.6s | |
| Claude Haiku 5.5 (Adaptive) | 99% | $0.0009 | 6.0s | |
| Gemini 3 Flash (Preview) | 99% | $0.0019 | 3.4s | |
| GPT-6 Luna (Reasoning, High) | 98% | $0.0006 | 10.3s | |
| GPT-4.1 Mini | 98% | $0.0011 | 7.0s | |
| Claude Haiku 5.5 (Reasoning, Low) | 98% | $0.0007 | 5.1s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 97% | $0.0007 | 5.2s | |
| Mistral Large 3 | 98% | $0.0011 | 7.7s | |
Cost vs Performance
Compares total cost for this test against the test score. Quadrant lines are drawn at the median values. Only models with available cost data are shown.
14 low-scoring outliers hidden: DeepSeek V3 (2025-03-24) (92.9%), GPT-5.4 Nano (92.6%), DeepSeek V3.1 (89.5%), GPT-4.1 Nano (89.3%), Gemma 3 4B (89.3%), Ministral 3 8B (87.0%), Ministral 8B (86.7%), Mistral NeMO (86.6%), Arcee AI: Trinity Mini (85.7%), Nemotron 3 Nano (83.3%), Ministral 3 3B (81.2%), Ministral 3B (80.9%), Cohere Command R+ (Aug. 2024) (73.7%), Hermes 3 70B (69.5%).
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 4.6 | 100% | 99% | 99% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 98% | 98% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 98% | 98% | |
| Gemma 4 31B | 100% | 98% | 98% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 98% | 98% | |
| Claude Opus 4.5 | 100% | 98% | 98% | |
| Gemma 4 31B (Reasoning) | 100% | 98% | 98% | |
| Claude Sonnet 4 | 100% | 98% | 98% | |
| Grok 4.5 (Reasoning, High) | 100% | 98% | 98% | |
| Muse Wonder (Reasoning, Medium) | 100% | 98% | 98% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 100% | 98% | 98% | |
| Claude Opus 4.6 (Reasoning) | 100% | 98% | 98% | |
| Claude Sonnet 4.5 | 100% | 98% | 98% | |
| Claude Sonnet 5.5 (Reasoning) | 100% | 98% | 98% | |
| Claude Opus 4.8 (Reasoning, Low) | 100% | 98% | 98% | |
| Claude Opus 4.8 (Reasoning) | 100% | 98% | 98% | |
| Hy4 Preview (Reasoning, High) | 100% | 98% | 98% | |
| Grok 4.7 (Reasoning, High) | 100% | 98% | 98% | |
| Claude Sonnet 5 (Reasoning, Low) | 99% | 98% | 98% | |
| Claude Sonnet 4.6 (Reasoning) | 100% | 98% | 98% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Gemini 3.1 Flash Lite | 99% | $0.0010 | 2.8s | 96% | |
| Gemini 3.1 Flash Lite (Preview) | 99% | $0.0010 | 1.8s | 96% | |
| Gemini 3.1 Flash Lite (Reasoning) | 99% | $0.0010 | 3.1s | 96% | |
| Gemini 3 Flash (Preview) | 99% | $0.0019 | 3.4s | 97% | |
| Qwen 3.5 Plus (2026-02-15) | 99% | $0.0015 | 7.2s | 97% | |
| Claude Haiku 4.5 | 99% | $0.0036 | 3.2s | 97% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 99% | $0.0049 | 2.3s | 97% | |
| GPT-6 Luna (Reasoning, Medium) | 99% | $0.0005 | 8.2s | 95% | |
| GPT-6 Luna | 98% | $0.0003 | 4.7s | 94% | |
| Gemma 4 26B | 99% | $0.0003 | 17.1s | 97% | |
| Gemini 2.5 Flash | 99% | $0.0015 | 2.2s | 92% | |
| Mistral Large 4.0 | 99% | $0.0015 | 9.8s | 95% | |
| GPT-4.1 Mini | 98% | $0.0011 | 7.0s | 94% | |
| Claude Haiku 5.5 (Adaptive) | 99% | $0.0009 | 6.0s | 91% | |
| GPT-6 Luna (Reasoning, High) | 98% | $0.0006 | 10.3s | 94% | |
| Grok 4.20 | 98% | $0.0020 | 4.4s | 92% | |
| GPT-6 Sol | 99% | $0.0065 | 6.7s | 97% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 98% | $0.0015 | 1.5s | 90% | |
| GPT-5.6 Luna | 98% | $0.0038 | 3.0s | 94% | |
| Gemini 3.5 Flash Lite (Reasoning) | 98% | $0.0015 | 1.5s | 90% | |
| Specific Prompt | Generic Prompt | Specific Prompt | Generic Prompt | Specific Prompt | Generic Prompt | Specific Prompt | Generic Prompt | Specific Prompt | Generic Prompt | Specific Prompt | Generic Prompt | Specific Prompt | Generic Prompt | Specific Prompt | Generic Prompt | Specific Prompt | Generic Prompt | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Model | Total ▼ | Character rename: Elena->Mirabel, Gregor->Aldric | Character rename: Elena->Mirabel, Gregor->Aldric | Location rename: market square, outer ring, bridge, northern mines | Location rename: market square, outer ring, bridge, northern mines | Expand all contractions | Expand all contractions | Tense rewriting: past to present | Tense rewriting: past to present | POV shift: 3rd person to 1st person (Elena's perspective) | POV shift: 3rd person to 1st person (Elena's perspective) | Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged | Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged | Combined: 3rd person past → 1st person present | Combined: 3rd person past → 1st person present | Passive voice → active voice | Passive voice → active voice | Avoid said/asked/replied/answered | Avoid said/asked/replied/answered |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 99% | 100% | 100% | 100% | 100% | 100% | 99% | 99% | 97% | 100% | 100% |
| Claude Sonnet 4 | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 99% | 98% | 97% | 100% | 100% |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 99% | 100% | 100% | 100% | 100% | 100% | 99% | 99% | 97% | 100% | 100% |
| Gemma 4 31B | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 98% | 100% | 100% | 100% | 100% | 100% | 99% | 99% | 98% | 100% | 100% |
| Claude Opus 4.6 | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 99% | 100% | 99% | 100% | 100% | 100% | 99% | 98% | 98% | 100% | 100% |
| Grok 4.6 (Reasoning, High) | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 98% | 100% | 100% | 100% | 100% | 99% | 99% | 99% | 97% | 100% | 100% |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 99% | 100% | 100% | 100% | 100% | 99% | 99% | 99% | 97% | 100% | 100% |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 99% | 100% | 100% | 100% | 100% | 100% | 99% | 99% | 97% | 100% | 100% |
| Claude Sonnet 4.5 | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 99% | 99% | 99% | 96% | 100% | 100% |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 99% | 100% | 100% | 100% | 99% | 99% | 96% | 100% | 100% |
| Gemma 4 31B (Reasoning) | 100% | 100% | 100% | 100% | 100% | 100% | 99% | 100% | 99% | 100% | 100% | 100% | 100% | 100% | 99% | 99% | 97% | 100% | 100% |
| Hy4 Preview (Reasoning, High) | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 99% | 98% | 96% | 100% | 100% |
| Muse Wonder (Reasoning, Medium) | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 99% | 100% | 100% | 100% | 100% | 99% | 99% | 99% | 97% | 100% | 100% |
| Grok 4.7 (Reasoning, High) | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 99% | 99% | 98% | 96% | 100% | 100% |
| Z.AI GLM 5.2 (Reasoning, High) | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 99% | 100% | 100% | 100% | 96% | 100% | 99% | 99% | 98% | 100% | 100% |
1–15 of 202
Page 1 / 14
Generic Prompt
Character rename: Elena->Mirabel, Gregor->Aldric
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.6s | |
| Inception Mercury 2 | 100% | $0.0007 | 971ms | |
| Laguna S 2.1 | 100% | $0.0002 | 5.7s | |
| Ministral 8B | 100% | $0.0001 | 3.2s | |
| Ministral 3 8B | 100% | $0.0002 | 2.9s | |
| Mistral Small 4 | 100% | $0.0004 | 2.8s | |
| GPT-4.1 Nano | 100% | $0.0003 | 3.7s | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0005 | 2.8s | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0005 | 2.8s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0005 | 2.9s | |
| Ministral 3 14B | 100% | $0.0002 | 4.0s | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.6s | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | $0.0006 | 4.2s | |
| GPT-6 Luna | 100% | $0.0003 | 4.5s | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0009 | 4.3s | |
| Gemini 3.1 Flash Lite | 100% | $0.0009 | 1.9s | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0007 | 2.8s | |
| GPT-5.4 Nano | 100% | $0.0007 | 2.7s | |
| Gemma 3 4B | 100% | $0.0001 | 6.1s | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0003 | 4.7s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 5.5 (Reasoning) | 100% | 100% | 100% | |
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 100% | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Ember-1 (Reasoning, Max) | 100% | 100% | 100% | |
| Muse Wonder (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 100% | 100% | 100% | |
| GPT-5.6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Hy4 Preview (Reasoning, High) | 100% | 100% | 100% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 100% | 100% | 100% | |
| Qwen 3.8 Flash (Reasoning) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Muse Spark 1.3 (Reasoning, Medium) | 100% | 100% | 100% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.6s | 100% | |
| Inception Mercury 2 | 100% | $0.0007 | 971ms | 100% | |
| Ministral 3 8B | 100% | $0.0002 | 2.9s | 100% | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.6s | 100% | |
| Ministral 8B | 100% | $0.0001 | 3.2s | 100% | |
| Mistral Small 4 | 100% | $0.0004 | 2.8s | 100% | |
| Gemini 3.1 Flash Lite | 100% | $0.0009 | 1.9s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0005 | 2.8s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0005 | 2.8s | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0005 | 2.9s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0014 | 1.4s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0014 | 1.4s | 100% | |
| GPT-5.4 Nano | 100% | $0.0007 | 2.7s | 100% | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0007 | 2.8s | 100% | |
| GPT-4.1 Nano | 100% | $0.0003 | 3.7s | 100% | |
| Ministral 3 14B | 100% | $0.0002 | 4.0s | 100% | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0007 | 3.2s | 100% | |
| Gemini 2.5 Flash | 100% | $0.0014 | 2.1s | 100% | |
| GPT-6 Luna | 100% | $0.0003 | 4.5s | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | $0.0006 | 4.2s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Name replacement accuracy | ||
| 100.0% | No remaining old names | ||
| 100.0% | Non-name text preserved |
Location rename: market square, outer ring, bridge, northern mines
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.5s | |
| Laguna S 2.1 | 100% | $0.0001 | 6.5s | |
| GPT-4.1 Nano | 98% | $0.0003 | 3.5s | |
| Mistral Small 4 | 99% | $0.0004 | 2.9s | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.6s | |
| GPT-6 Luna | 100% | $0.0003 | 4.6s | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.7s | |
| Gemini 3.1 Flash Lite | 100% | $0.0009 | 10.3s | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0009 | 1.8s | |
| ByteDance Seed 1.6 Flash | 99% | $0.0003 | 5.3s | |
| DeepSeek V4 Flash | 100% | $0.0002 | 8.1s | |
| Inception Mercury 2 | 100% | $0.0010 | 1.4s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0001 | 12.4s | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0007 | 4.8s | |
| Llama 3.1 70B | 100% | $0.0005 | 17.8s | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0004 | 6.5s | |
| Gemma 3 12B | 100% | $0.0001 | 8.6s | |
| GPT-6 Luna (Reasoning, High) | 99% | $0.0004 | 9.2s | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0014 | 1.3s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0014 | 1.4s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 5.5 (Reasoning) | 100% | 100% | 100% | |
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 100% | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Ember-1 (Reasoning, Max) | 100% | 100% | 100% | |
| Muse Wonder (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 100% | 100% | 100% | |
| GPT-5.6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Hy4 Preview (Reasoning, High) | 100% | 100% | 100% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 100% | 100% | 100% | |
| Qwen 3.8 Flash (Reasoning) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Muse Spark 1.3 (Reasoning, Medium) | 100% | 100% | 100% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.5s | 100% | |
| Inception Mercury 2 | 100% | $0.0010 | 1.4s | 100% | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.7s | 100% | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0009 | 1.8s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0014 | 1.3s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0014 | 1.4s | 100% | |
| Gemini 2.5 Flash | 100% | $0.0014 | 2.1s | 100% | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.6s | 100% | |
| GPT-6 Luna | 100% | $0.0003 | 4.6s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0007 | 4.8s | 100% | |
| Laguna S 2.1 | 100% | $0.0001 | 6.5s | 100% | |
| GPT-5.4 Mini | 100% | $0.0027 | 2.2s | 100% | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0004 | 6.5s | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | $0.0008 | 6.0s | 100% | |
| Grok 4.3 | 100% | $0.0019 | 4.2s | 100% | |
| Grok 4.20 | 100% | $0.0020 | 4.1s | 100% | |
| GPT-4.1 Mini | 100% | $0.0010 | 5.8s | 100% | |
| DeepSeek V4 Flash | 100% | $0.0002 | 8.1s | 100% | |
| Gemma 3 12B | 100% | $0.0001 | 8.6s | 100% | |
| Gemini 2.5 Flash Lite (Reasoning) | 100% | $0.0009 | 7.3s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Name replacement accuracy | ||
| 100.0% | No remaining old names | — | |
| 100.0% | Non-name text preserved |
Expand all contractions
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0002 | 1.3s | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 3.7s | |
| DeepSeek V4 Flash | 100% | $0.0001 | 5.6s | |
| Gemini 3.1 Flash Lite | 100% | $0.0007 | 1.5s | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0007 | 1.5s | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0007 | 1.5s | |
| Mistral Small 4 | 99% | $0.0003 | 2.4s | |
| Laguna XS 2.1 | 100% | $0.0002 | 6.6s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 96% | $0.0001 | 6.7s | |
| GPT-4o Mini (temp=1) | 100% | $0.0003 | 7.0s | |
| Gemini 3.5 Flash Lite (Reasoning) | 90% | $0.0012 | 1.2s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 90% | $0.0012 | 1.2s | |
| Mistral NeMO | 98% | $0.0001 | 2.6s | |
| Gemini 2.5 Flash | 100% | $0.0012 | 1.8s | |
| GPT-4o Mini (temp=0) | 100% | $0.0003 | 8.4s | |
| ByteDance Seed 1.6 Flash | 100% | $0.0004 | 8.4s | |
| Qwen 3 235B A22B Instruct 2507 | 100% | $0.0003 | 11.9s | |
| Ministral 8B | 95% | $0.0001 | 2.4s | |
| Laguna S 2.1 | 99% | $0.0001 | 29.8s | |
| Qwen 2.5 72B | 100% | $0.0002 | 7.7s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 5.5 (Reasoning) | 100% | 100% | 100% | |
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 100% | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Muse Wonder (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 100% | 100% | 100% | |
| GPT-5.6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Hy4 Preview (Reasoning, High) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 100% | 100% | 100% | |
| Qwen 3.8 Flash (Reasoning) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Muse Spark 1.3 (Reasoning, Medium) | 100% | 100% | 100% | |
| Muse Spark 1.1 (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 4 Argon (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.1 | 100% | 100% | 100% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0002 | 1.3s | 100% | |
| Gemini 3.1 Flash Lite | 100% | $0.0007 | 1.5s | 100% | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0007 | 1.5s | 100% | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0007 | 1.5s | 100% | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 3.7s | 100% | |
| Gemini 2.5 Flash | 100% | $0.0012 | 1.8s | 100% | |
| DeepSeek V4 Flash | 100% | $0.0001 | 5.6s | 100% | |
| Mistral Small 4 | 99% | $0.0003 | 2.4s | 99% | |
| Gemini 3 Flash (Preview) | 100% | $0.0015 | 2.7s | 100% | |
| GPT-4o Mini (temp=1) | 100% | $0.0003 | 7.0s | 100% | |
| Mistral Large 3 | 100% | $0.0008 | 5.8s | 100% | |
| Laguna XS 2.1 | 100% | $0.0002 | 6.6s | 99% | |
| Qwen 3.5 Plus (2026-02-15) | 100% | $0.0012 | 5.5s | 100% | |
| GPT-4o Mini (temp=0) | 100% | $0.0003 | 8.4s | 100% | |
| Mistral NeMO | 98% | $0.0001 | 2.6s | 97% | |
| Gemini 2.5 Flash Lite (Reasoning) | 99% | $0.0008 | 4.6s | 99% | |
| ByteDance Seed 1.6 Flash | 100% | $0.0004 | 8.4s | 99% | |
| Claude Haiku 4.5 | 100% | $0.0027 | 2.2s | 100% | |
| Qwen 2.5 72B | 100% | $0.0002 | 7.7s | 98% | |
| Grok 4.20 | 99% | $0.0015 | 3.4s | 99% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Name replacement accuracy | ||
| 100.0% | Non-name text preserved | ||
| 100.0% | Possessive traps preserved |
Tense rewriting: past to present
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Qwen 3 235B A22B Instruct 2507 | 100% | $0.0003 | 10.6s | |
| Claude Haiku 5.5 (Reasoning, Low) | 99% | $0.0005 | 2.8s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 99% | $0.0005 | 2.9s | |
| Claude Haiku 5.5 (Adaptive) | 99% | $0.0005 | 2.9s | |
| Gemini 2.5 Flash Lite | 98% | $0.0003 | 1.5s | |
| Xiaomi MIMO v2.6 Flash | 97% | $0.0003 | 39.7s | |
| Mistral Small 3.2 24B | 99% | $0.0002 | 5.9s | |
| DeepSeek V4 Flash | 98% | $0.0002 | 6.8s | |
| Mistral Small 4 | 99% | $0.0004 | 2.8s | |
| Ministral 3 14B | 99% | $0.0002 | 3.8s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 99% | $0.0002 | 8.2s | |
| Mistral NeMO | 98% | $0.0002 | 3.0s | |
| Gemma 4 26B | 99% | $0.0002 | 12.9s | |
| Ministral 3 8B | 98% | $0.0002 | 3.7s | |
| Qwen 2.5 72B | 99% | $0.0003 | 10.4s | |
| Mistral Large 3 | 99% | $0.0010 | 7.4s | |
| DeepSeek V4 Pro | 100% | $0.0009 | 11.9s | |
| Qwen 3.5 Plus (2026-02-15) | 99% | $0.0015 | 6.6s | |
| Laguna XS 2.1 | 97% | $0.0002 | 8.6s | |
| Ministral 8B | 97% | $0.0001 | 3.6s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Hy4 Preview (Reasoning, High) | 100% | 100% | 100% | |
| Claude Sonnet 4.5 | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 99% | 99% | |
| Qwen 3 235B A22B Instruct 2507 | 100% | 99% | 99% | |
| Claude Sonnet 4 | 100% | 99% | 99% | |
| Gemini 4 Argon (Reasoning, Medium) | 99% | 100% | 99% | |
| Z.AI GLM 5.2 (Reasoning, High) | 99% | 100% | 99% | |
| Claude Opus 4.8 (Reasoning) | 99% | 100% | 99% | |
| Claude Opus 4.6 | 99% | 100% | 99% | |
| Gemma 4 31B (Reasoning) | 99% | 100% | 99% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 99% | 100% | 99% | |
| Gemma 4 26B | 99% | 100% | 99% | |
| Claude Haiku 5.5 (Reasoning, Low) | 99% | 100% | 99% | |
| Mistral Large 3 | 99% | 100% | 99% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 99% | 100% | 99% | |
| Mistral Large 2 | 99% | 100% | 99% | |
| Mistral Small 3.2 24B | 99% | 100% | 99% | |
| Grok 4.7 (Reasoning, High) | 100% | 99% | 99% | |
| Aion 3.5 Mini (Reasoning, High) | 100% | 99% | 99% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Claude Haiku 5.5 (Reasoning, Low) | 99% | $0.0005 | 2.8s | 99% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 99% | $0.0005 | 2.9s | 99% | |
| Mistral Small 3.2 24B | 99% | $0.0002 | 5.9s | 99% | |
| Qwen 3 235B A22B Instruct 2507 | 100% | $0.0003 | 10.6s | 99% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 99% | $0.0002 | 8.2s | 99% | |
| Claude Haiku 5.5 (Adaptive) | 99% | $0.0005 | 2.9s | 99% | |
| Mistral Large 3 | 99% | $0.0010 | 7.4s | 99% | |
| Ministral 3 14B | 99% | $0.0002 | 3.8s | 99% | |
| Gemma 4 26B | 99% | $0.0002 | 12.9s | 99% | |
| Qwen 3.5 Plus (2026-02-15) | 99% | $0.0015 | 6.6s | 99% | |
| DeepSeek V4 Pro | 100% | $0.0009 | 11.9s | 99% | |
| Ministral 3 8B | 98% | $0.0002 | 3.7s | 98% | |
| Z.AI GLM 5.2 (Reasoning, High) | 99% | $0.0027 | 9.6s | 99% | |
| Mistral Small 4 | 99% | $0.0004 | 2.8s | 97% | |
| Writer: Palmyra X5 | 100% | $0.0033 | 9.2s | 99% | |
| Mistral Large 2 | 99% | $0.0041 | 7.2s | 99% | |
| Mistral NeMO | 98% | $0.0002 | 3.0s | 97% | |
| Qwen 2.5 72B | 99% | $0.0003 | 10.4s | 96% | |
| Xiaomi MIMO v2.5 | 99% | $0.0021 | 9.3s | 97% | |
| Gemini 2.5 Flash Lite | 98% | $0.0003 | 1.5s | 96% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 90.0% | Dialogue content preserved | ||
| 97.8% | Name replacement accuracy | ||
| 100.0% | Non-name text preserved |
POV shift: 3rd person to 1st person (Elena's perspective)
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.7s | |
| GPT-4.1 Nano | 98% | $0.0003 | 3.5s | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.2s | |
| Laguna S 2.1 | 100% | $0.0001 | 26.3s | |
| GPT-6 Luna | 100% | $0.0003 | 4.4s | |
| Gemma 3 12B | 100% | $0.0001 | 7.7s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0001 | 7.1s | |
| DeepSeek V4 Flash | 100% | $0.0002 | 6.8s | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0004 | 2.7s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0004 | 2.8s | |
| Inception Mercury 2 | 100% | $0.0007 | 1.0s | |
| Mistral Small 4 | 87% | $0.0004 | 3.3s | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0003 | 4.9s | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0006 | 4.1s | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0004 | 6.2s | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0007 | 2.9s | |
| GPT-5.4 Nano | 100% | $0.0007 | 3.4s | |
| Qwen 2.5 72B | 100% | $0.0003 | 10.7s | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0008 | 3.2s | |
| GPT-4o Mini (temp=1) | 100% | $0.0004 | 9.2s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 100% | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Ember-1 (Reasoning, Max) | 100% | 100% | 100% | |
| Muse Wonder (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Hy4 Preview (Reasoning, High) | 100% | 100% | 100% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 100% | 100% | 100% | |
| Qwen 3.8 Flash (Reasoning) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Muse Spark 1.3 (Reasoning, Medium) | 100% | 100% | 100% | |
| GPT-6 Luna (Reasoning, High) | 100% | 100% | 100% | |
| GPT-5.4 (Reasoning) | 100% | 100% | 100% | |
| Muse Spark 1.1 (Reasoning, Medium) | 100% | 100% | 100% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.7s | 100% | |
| Inception Mercury 2 | 100% | $0.0007 | 1.0s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0004 | 2.7s | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0004 | 2.8s | 100% | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.7s | 100% | |
| Gemini 3.1 Flash Lite | 100% | $0.0009 | 1.7s | 100% | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.2s | 100% | |
| GPT-6 Luna | 100% | $0.0003 | 4.4s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0014 | 1.3s | 100% | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0008 | 3.2s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0014 | 1.7s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0006 | 4.1s | 100% | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0003 | 4.9s | 100% | |
| Gemini 2.5 Flash | 100% | $0.0014 | 2.1s | 100% | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0004 | 6.2s | 100% | |
| DeepSeek V4 Flash | 100% | $0.0002 | 6.8s | 100% | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0007 | 2.9s | 99% | |
| Xiaomi MIMO v2.6 Pro | 100% | $0.0007 | 5.9s | 100% | |
| GPT-5.4 Nano | 100% | $0.0007 | 3.4s | 99% | |
| Gemma 3 12B | 100% | $0.0001 | 7.7s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Name replacement accuracy | ||
| 100.0% | No remaining old names | ||
| 100.0% | Non-name text preserved |
Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| GPT-6 Luna | 100% | $0.0004 | 5.2s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0002 | 8.7s | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0004 | 5.8s | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0004 | 6.4s | |
| Gemma 4 26B | 100% | $0.0003 | 12.6s | |
| Gemini 3.1 Flash Lite | 100% | $0.0010 | 5.9s | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0010 | 1.9s | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0010 | 2.0s | |
| Z.AI GLM 4.5 Air | 99% | $0.0016 | 43.4s | |
| Qwen 2.5 72B | 89% | $0.0003 | 11.6s | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0010 | 6.5s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0009 | 6.6s | |
| GPT-5.4 Nano (Reasoning, Low) | 94% | $0.0008 | 3.3s | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0009 | 6.7s | |
| DeepSeek V4 Flash (Reasoning) | 100% | $0.0004 | 16.6s | |
| GPT-4.1 Mini | 100% | $0.0012 | 6.5s | |
| Mistral Medium 3.1 | 100% | $0.0014 | 6.9s | |
| Gemini 2.5 Flash | 100% | $0.0017 | 2.4s | |
| Gemma 4 31B | 100% | $0.0004 | 19.1s | |
| Xiaomi MIMO v2.6 Pro | 100% | $0.0009 | 10.8s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Ember-1 (Reasoning, Max) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 100% | 100% | 100% | |
| GPT-5.6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Qwen 3.6 Max Preview | 100% | 100% | 100% | |
| Claude Sonnet 4.6 (Reasoning) | 100% | 100% | 100% | |
| Kimi K3 (Reasoning, High) | 100% | 100% | 100% | |
| Claude Sonnet 5.5 (Reasoning) | 100% | 100% | 100% | |
| Grok 4.6 (Reasoning, High) | 100% | 100% | 100% | |
| GPT-6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Grok 4.7 (Reasoning, High) | 100% | 100% | 100% | |
| Kimi K2.6 | 100% | 100% | 100% | |
| GPT-5.5 (Reasoning, Low) | 100% | 100% | 100% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0010 | 1.9s | 100% | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0010 | 2.0s | 100% | |
| GPT-6 Luna | 100% | $0.0004 | 5.2s | 100% | |
| Gemini 2.5 Flash | 100% | $0.0017 | 2.4s | 100% | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0004 | 5.8s | 100% | |
| Gemini 3.1 Flash Lite | 100% | $0.0010 | 5.9s | 100% | |
| Gemini 3 Flash (Preview) | 100% | $0.0021 | 3.5s | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0009 | 6.6s | 100% | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0004 | 6.4s | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0002 | 8.7s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning) | 99% | $0.0017 | 1.5s | 99% | |
| GPT-4.1 Mini | 100% | $0.0012 | 6.5s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0017 | 1.8s | 99% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0010 | 6.5s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0009 | 6.7s | 100% | |
| Qwen 3.5 Plus (2026-02-15) | 100% | $0.0017 | 7.6s | 100% | |
| Mistral Medium 3.1 | 100% | $0.0014 | 6.9s | 100% | |
| GPT-5.6 Luna | 100% | $0.0041 | 2.7s | 100% | |
| Mistral Large 4.0 | 100% | $0.0015 | 9.0s | 100% | |
| Claude Haiku 4.5 | 100% | $0.0041 | 3.1s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Dialogue content preserved | ||
| 100.0% | Mara pronouns preserved (coreference test) | ||
| 99.6% | Name replacement accuracy | ||
| 100.0% | Non-name text preserved |
Combined: 3rd person past → 1st person present
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 99% | $0.0003 | 1.8s | |
| Claude Haiku 5.5 (Reasoning, Low) | 99% | $0.0005 | 2.7s | |
| Claude Haiku 5.5 (Adaptive) | 99% | $0.0005 | 3.4s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 99% | $0.0005 | 2.9s | |
| Xiaomi MIMO v2.6 Pro | 99% | $0.0007 | 8.5s | |
| DeepSeek V4 Flash | 98% | $0.0002 | 8.1s | |
| GPT-5.4 Nano | 99% | $0.0007 | 3.2s | |
| Gemini 3.1 Flash Lite | 98% | $0.0009 | 1.8s | |
| Gemini 3.1 Flash Lite (Reasoning) | 99% | $0.0009 | 1.8s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 99% | $0.0014 | 1.3s | |
| Gemini 3.5 Flash Lite (Reasoning) | 99% | $0.0014 | 1.5s | |
| Gemini 2.5 Flash | 94% | $0.0015 | 2.1s | |
| GPT-6 Luna | 96% | $0.0003 | 4.7s | |
| GPT-6 Luna (Reasoning, Medium) | 98% | $0.0004 | 7.1s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 98% | $0.0001 | 8.0s | |
| Gemma 3 12B | 94% | $0.0001 | 9.3s | |
| Gemma 4 31B | 99% | $0.0003 | 26.8s | |
| Gemma 4 26B | 99% | $0.0002 | 11.9s | |
| GPT-5.4 Nano (Reasoning) | 97% | $0.0007 | 3.1s | |
| GPT-4.1 Nano | 98% | $0.0003 | 3.6s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 100% | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5 Turbo | 100% | 99% | 99% | |
| GPT-5.5 | 100% | 99% | 99% | |
| Claude Opus 4.6 (Reasoning) | 99% | 100% | 99% | |
| Qwen 3.6 Max Preview | 99% | 100% | 99% | |
| Grok 4.6 (Reasoning, High) | 99% | 100% | 99% | |
| Claude Opus 4.7 (Reasoning) | 99% | 100% | 99% | |
| Claude Opus 4.8 (Reasoning) | 99% | 100% | 99% | |
| Claude Opus 4.6 | 99% | 100% | 99% | |
| GPT-5.4 Mini (Reasoning) | 99% | 100% | 99% | |
| Gemma 4 31B (Reasoning) | 99% | 100% | 99% | |
| Claude Sonnet 4 | 99% | 100% | 99% | |
| Gemma 4 31B | 99% | 100% | 99% | |
| Mistral Large 4.0 | 99% | 100% | 99% | |
| GPT-6 Sol (Reasoning, Medium) | 99% | 100% | 99% | |
| GPT-5.6 Terra (Reasoning, Medium) | 99% | 100% | 99% | |
| Grok 4.20 (Reasoning) | 99% | 100% | 99% | |
| Gemini 3.5 Flash Lite (Reasoning) | 99% | 100% | 99% | |
| Muse Wonder (Reasoning, Medium) | 99% | 100% | 99% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Claude Haiku 5.5 (Reasoning, Low) | 99% | $0.0005 | 2.7s | 99% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 99% | $0.0005 | 2.9s | 99% | |
| Gemini 2.5 Flash Lite | 99% | $0.0003 | 1.8s | 98% | |
| Gemini 3.5 Flash Lite (Reasoning) | 99% | $0.0014 | 1.5s | 99% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 99% | $0.0014 | 1.3s | 99% | |
| Claude Haiku 5.5 (Adaptive) | 99% | $0.0005 | 3.4s | 98% | |
| Gemini 3.1 Flash Lite (Reasoning) | 99% | $0.0009 | 1.8s | 98% | |
| GPT-5.4 Nano | 99% | $0.0007 | 3.2s | 98% | |
| Gemini 3.1 Flash Lite | 98% | $0.0009 | 1.8s | 98% | |
| Gemini 3.1 Flash Lite (Preview) | 98% | $0.0009 | 1.7s | 98% | |
| Xiaomi MIMO v2.6 Pro | 99% | $0.0007 | 8.5s | 99% | |
| Mistral Small 3.2 24B | 98% | $0.0002 | 4.4s | 97% | |
| Mistral Large 4.0 | 99% | $0.0014 | 9.1s | 99% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 98% | $0.0001 | 8.0s | 98% | |
| Qwen 3.5 Plus (2026-02-15) | 99% | $0.0014 | 6.7s | 99% | |
| GPT-4.1 Nano | 98% | $0.0003 | 3.6s | 96% | |
| Gemma 4 26B | 99% | $0.0002 | 11.9s | 98% | |
| Qwen 2.5 72B | 98% | $0.0003 | 9.5s | 98% | |
| Gemini 3 Flash (Preview) | 98% | $0.0018 | 3.1s | 97% | |
| Claude Haiku 4.5 | 99% | $0.0033 | 2.8s | 99% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Dialogue content preserved | ||
| 96.5% | Name replacement accuracy | ||
| 100.0% | Non-name text preserved |
Passive voice → active voice
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| GPT-6 Luna | 98% | $0.0004 | 5.9s | |
| Z.AI GLM 5.2 (Reasoning, High) | 98% | $0.0057 | 16.7s | |
| Gemma 4 31B | 98% | $0.0005 | 39.7s | |
| Qwen 3.5 Plus (2026-02-15) | 96% | $0.0021 | 10.9s | |
| DeepSeek V4 Flash | 89% | $0.0002 | 9.5s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 87% | $0.0002 | 11.7s | |
| Gemma 4 26B | 95% | $0.0003 | 23.2s | |
| Gemini 2.5 Flash | 95% | $0.0021 | 2.9s | |
| GPT-6 Luna (Reasoning, Medium) | 95% | $0.0008 | 16.2s | |
| GPT-6 Luna (Reasoning, High) | 95% | $0.0011 | 22.2s | |
| Gemini 3.1 Flash Lite | 94% | $0.0013 | 2.5s | |
| Gemini 3.1 Flash Lite (Preview) | 93% | $0.0013 | 2.4s | |
| Gemini 3 Flash (Preview) | 94% | $0.0026 | 4.3s | |
| Gemini 2.5 Flash Lite | 90% | $0.0004 | 2.5s | |
| DeepSeek V3.1 | 89% | $0.0008 | 37.0s | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 96% | $0.0069 | 3.1s | |
| Gemini 3.1 Flash Lite (Reasoning) | 93% | $0.0013 | 2.5s | |
| Laguna S 2.1 | 92% | $0.0002 | 5.5s | |
| Gemini 3.5 Flash Lite (Reasoning) | 91% | $0.0021 | 2.0s | |
| Xiaomi MIMO v2.6 Flash | 95% | $0.0007 | 1.0m | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 4.5 | 97% | 99% | 97% | |
| Claude Opus 4.8 (Reasoning) | 98% | 98% | 97% | |
| Grok 4.6 (Reasoning, High) | 97% | 99% | 97% | |
| Claude Opus 4.6 | 98% | 99% | 96% | |
| GPT-5 | 97% | 99% | 96% | |
| Z.AI GLM 5.2 (Reasoning, High) | 98% | 97% | 96% | |
| Gemma 4 31B | 98% | 98% | 96% | |
| GPT-6 Luna | 98% | 98% | 96% | |
| Claude Opus 4.8 (Reasoning, Low) | 98% | 98% | 96% | |
| GPT-6.1 Sol (Reasoning, Medium) | 97% | 99% | 96% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 97% | 99% | 96% | |
| Hy4 Preview (Reasoning, High) | 96% | 99% | 96% | |
| Aion 3.5 (Reasoning, High) | 98% | 98% | 96% | |
| Aion 3.0 | 97% | 98% | 96% | |
| Claude Sonnet 4 | 97% | 99% | 96% | |
| GPT-5.4 (Reasoning) | 97% | 99% | 96% | |
| Gemini 4 Argon (Reasoning, Medium) | 97% | 99% | 96% | |
| Thinking Machines Inkling (Reasoning) | 96% | 99% | 96% | |
| Muse Wonder (Reasoning, Medium) | 97% | 99% | 96% | |
| GPT-5.5 (Reasoning, Medium) | 97% | 99% | 96% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| GPT-6 Luna | 98% | $0.0004 | 5.9s | 96% | |
| Z.AI GLM 5.2 (Reasoning, High) | 98% | $0.0057 | 16.7s | 96% | |
| Gemma 4 31B | 98% | $0.0005 | 39.7s | 96% | |
| Qwen 3.5 Plus (2026-02-15) | 96% | $0.0021 | 10.9s | 94% | |
| Gemini 4 Argon (Reasoning, Medium) | 97% | $0.0092 | 5.9s | 96% | |
| GPT-6.1 Sol (Reasoning, Medium) | 97% | $0.0097 | 17.0s | 96% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 96% | $0.0080 | 3.5s | 94% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 96% | $0.0069 | 3.1s | 94% | |
| GPT-6 Luna (Reasoning, Medium) | 95% | $0.0008 | 16.2s | 93% | |
| Gemini 2.5 Flash | 95% | $0.0021 | 2.9s | 92% | |
| Gemma 4 26B | 95% | $0.0003 | 23.2s | 94% | |
| GPT-6 Sol | 96% | $0.0089 | 7.2s | 95% | |
| GPT-5.4 (Reasoning, Low) | 97% | $0.013 | 8.3s | 95% | |
| Gemini 3.1 Flash Lite | 94% | $0.0013 | 2.5s | 92% | |
| Claude Sonnet 4 | 97% | $0.015 | 9.5s | 96% | |
| Gemini 3 Flash (Preview) | 94% | $0.0026 | 4.3s | 92% | |
| Gemini 3.1 Flash Lite (Preview) | 93% | $0.0013 | 2.4s | 91% | |
| GPT-6 Luna (Reasoning, High) | 95% | $0.0011 | 22.2s | 92% | |
| GPT-5.6 Terra | 96% | $0.013 | 3.9s | 94% | |
| Gemini 3.1 Flash Lite (Reasoning) | 93% | $0.0013 | 2.5s | 90% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 97.1% | Dialogue content preserved | ||
| 100.0% | No hallucinated or fabricated content | ||
| 87.5% | Non-passive narration preserved | ||
| 86.3% | Passive → active voice transformations | ||
| 100.0% | Structural similarity to original |
Avoid said/asked/replied/answered
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.6s | |
| Mistral Small 4 | 100% | $0.0004 | 2.7s | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.8s | |
| GPT-6 Luna | 100% | $0.0003 | 4.2s | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0005 | 2.8s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0005 | 2.9s | |
| DeepSeek V4 Flash | 95% | $0.0002 | 8.4s | |
| Inception Mercury 2 | 100% | $0.0008 | 1.1s | |
| Gemma 3 12B | 100% | $0.0001 | 8.8s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0001 | 8.9s | |
| GPT-6 Luna (Reasoning, Medium) | 98% | $0.0004 | 6.4s | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0006 | 4.1s | |
| Gemma 4 26B | 100% | $0.0002 | 24.5s | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.7s | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0009 | 1.9s | |
| Gemini 3.1 Flash Lite | 100% | $0.0009 | 2.9s | |
| Gemini 2.5 Flash Lite (Reasoning) | 100% | $0.0006 | 4.9s | |
| GPT-4o Mini (temp=1) | 100% | $0.0004 | 8.5s | |
| GPT-4o Mini (temp=0) | 100% | $0.0004 | 9.0s | |
| Qwen 2.5 72B | 98% | $0.0003 | 9.8s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 5.5 (Reasoning) | 100% | 100% | 100% | |
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 100% | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Ember-1 (Reasoning, Max) | 100% | 100% | 100% | |
| Muse Wonder (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 100% | 100% | 100% | |
| GPT-5.6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Hy4 Preview (Reasoning, High) | 100% | 100% | 100% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 100% | 100% | 100% | |
| Qwen 3.8 Flash (Reasoning) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Muse Spark 1.3 (Reasoning, Medium) | 100% | 100% | 100% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.6s | 100% | |
| Inception Mercury 2 | 100% | $0.0008 | 1.1s | 100% | |
| Mistral Small 4 | 100% | $0.0004 | 2.7s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0005 | 2.8s | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0005 | 2.9s | 100% | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.7s | 100% | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0009 | 1.9s | 100% | |
| GPT-6 Luna | 100% | $0.0003 | 4.2s | 100% | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.8s | 100% | |
| Gemini 3.1 Flash Lite | 100% | $0.0009 | 2.9s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0006 | 4.1s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0014 | 1.5s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0014 | 1.8s | 100% | |
| Gemini 2.5 Flash Lite (Reasoning) | 100% | $0.0006 | 4.9s | 100% | |
| Gemini 2.5 Flash | 100% | $0.0014 | 2.1s | 100% | |
| Mistral Medium 3.1 | 100% | $0.0012 | 4.7s | 100% | |
| Gemma 3 12B | 100% | $0.0001 | 8.8s | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0001 | 8.9s | 100% | |
| GPT-4.1 Mini | 100% | $0.0010 | 6.2s | 100% | |
| GPT-4o Mini (temp=1) | 100% | $0.0004 | 8.5s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Forbidden words eliminated | ||
| 100.0% | Non-name text preserved | ||
| 100.0% | Structural similarity to original |
Specific Prompt
Character rename: Elena->Mirabel, Gregor->Aldric
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Ministral 3B | 100% | $0.0000 | 2.0s | |
| Mistral NeMO | 100% | $0.0002 | 1.6s | |
| Ministral 3 3B | 100% | $0.0001 | 2.3s | |
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.6s | |
| Ministral 8B | 100% | $0.0001 | 3.4s | |
| Ministral 3 8B | 100% | $0.0002 | 3.2s | |
| Gemma 3 4B | 100% | $0.0001 | 5.2s | |
| GPT-4.1 Nano | 100% | $0.0003 | 3.6s | |
| Mistral Small 4 | 100% | $0.0004 | 2.9s | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.6s | |
| Ministral 3 14B | 95% | $0.0002 | 4.3s | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0005 | 2.8s | |
| GPT-6 Luna | 100% | $0.0003 | 4.2s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0005 | 3.0s | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0003 | 4.7s | |
| Laguna XS 2.1 | 100% | $0.0002 | 7.0s | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0003 | 5.3s | |
| DeepSeek V4 Flash | 100% | $0.0002 | 6.8s | |
| Llama 3.1 70B | 100% | $0.0004 | 11.0s | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0006 | 3.6s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 5.5 (Reasoning) | 100% | 100% | 100% | |
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 100% | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Ember-1 (Reasoning, Max) | 100% | 100% | 100% | |
| Muse Wonder (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 100% | 100% | 100% | |
| GPT-5.6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Hy4 Preview (Reasoning, High) | 100% | 100% | 100% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 100% | 100% | 100% | |
| Qwen 3.8 Flash (Reasoning) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Muse Spark 1.3 (Reasoning, Medium) | 100% | 100% | 100% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Mistral NeMO | 100% | $0.0002 | 1.6s | 100% | |
| Ministral 3B | 100% | $0.0000 | 2.0s | 100% | |
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.6s | 100% | |
| Ministral 3 3B | 100% | $0.0001 | 2.3s | 100% | |
| Ministral 3 8B | 100% | $0.0002 | 3.2s | 100% | |
| Ministral 8B | 100% | $0.0001 | 3.4s | 100% | |
| Mistral Small 4 | 100% | $0.0004 | 2.9s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0005 | 2.8s | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0005 | 3.0s | 100% | |
| GPT-4.1 Nano | 100% | $0.0003 | 3.6s | 100% | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.8s | 100% | |
| Gemini 3.1 Flash Lite | 100% | $0.0009 | 1.8s | 100% | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0007 | 2.7s | 100% | |
| GPT-5.4 Nano | 100% | $0.0007 | 2.9s | 100% | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0007 | 2.9s | 100% | |
| GPT-6 Luna | 100% | $0.0003 | 4.2s | 100% | |
| Inception Mercury 2 | 100% | $0.0013 | 1.5s | 100% | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.6s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0006 | 3.6s | 100% | |
| Gemma 3 4B | 100% | $0.0001 | 5.2s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Name replacement accuracy | ||
| 100.0% | No remaining old names | ||
| 100.0% | Non-name text preserved |
Location rename: market square, outer ring, bridge, northern mines
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Ministral 3B | 100% | $0.0000 | 1.9s | |
| Ministral 3 3B | 100% | $0.0001 | 1.9s | |
| Ministral 8B | 100% | $0.0001 | 3.2s | |
| Ministral 3 8B | 100% | $0.0002 | 3.1s | |
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.5s | |
| Gemma 3 4B | 100% | $0.0001 | 5.8s | |
| Ministral 3 14B | 100% | $0.0002 | 3.8s | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.5s | |
| Gemma 3 12B | 100% | $0.0001 | 8.5s | |
| Laguna S 2.1 | 100% | $0.0002 | 7.8s | |
| DeepSeek V4 Flash | 100% | $0.0002 | 8.2s | |
| Mistral Small 4 | 100% | $0.0004 | 2.8s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0001 | 7.9s | |
| GPT-6 Luna | 100% | $0.0003 | 5.0s | |
| Laguna XS 2.1 | 100% | $0.0002 | 8.7s | |
| Gemma 4 26B | 100% | $0.0003 | 15.4s | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0004 | 6.2s | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0004 | 7.2s | |
| Qwen 2.5 72B | 100% | $0.0003 | 10.4s | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0006 | 4.3s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 5.5 (Reasoning) | 100% | 100% | 100% | |
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 100% | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Ember-1 (Reasoning, Max) | 100% | 100% | 100% | |
| Muse Wonder (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 100% | 100% | 100% | |
| GPT-5.6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Hy4 Preview (Reasoning, High) | 100% | 100% | 100% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 100% | 100% | 100% | |
| Qwen 3.8 Flash (Reasoning) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Muse Spark 1.3 (Reasoning, Medium) | 100% | 100% | 100% | |
| GPT-6 Luna (Reasoning, High) | 100% | 100% | 100% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Ministral 3B | 100% | $0.0000 | 1.9s | 100% | |
| Ministral 3 3B | 100% | $0.0001 | 1.9s | 100% | |
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.5s | 100% | |
| Ministral 8B | 100% | $0.0001 | 3.2s | 100% | |
| Ministral 3 8B | 100% | $0.0002 | 3.1s | 100% | |
| Mistral Small 4 | 100% | $0.0004 | 2.8s | 100% | |
| Ministral 3 14B | 100% | $0.0002 | 3.8s | 100% | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.5s | 100% | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.6s | 100% | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0009 | 1.7s | 100% | |
| Gemma 3 4B | 100% | $0.0001 | 5.8s | 100% | |
| Gemini 3.1 Flash Lite | 100% | $0.0009 | 1.9s | 100% | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0007 | 2.8s | 100% | |
| GPT-6 Luna | 100% | $0.0003 | 5.0s | 100% | |
| GPT-5.4 Nano | 100% | $0.0007 | 3.0s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0006 | 4.3s | 100% | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0004 | 6.2s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0014 | 1.4s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0014 | 1.4s | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0001 | 7.9s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Name replacement accuracy | ||
| 100.0% | No remaining old names | ||
| 100.0% | Non-name text preserved |
Expand all contractions
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0002 | 1.3s | |
| Ministral 8B | 100% | $0.0001 | 2.4s | |
| Ministral 3 8B | 100% | $0.0001 | 3.0s | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 3.5s | |
| Mistral Small 4 | 100% | $0.0003 | 2.6s | |
| GPT-6 Luna | 100% | $0.0002 | 4.5s | |
| Gemma 3 12B | 100% | $0.0001 | 5.9s | |
| DeepSeek V4 Flash | 100% | $0.0001 | 7.1s | |
| Gemini 3.1 Flash Lite | 100% | $0.0008 | 1.9s | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0008 | 1.6s | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0008 | 1.7s | |
| Mistral NeMO | 98% | $0.0001 | 1.8s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0001 | 7.5s | |
| Laguna S 2.1 | 100% | $0.0001 | 6.9s | |
| GPT-4o Mini (temp=0) | 100% | $0.0003 | 7.1s | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0004 | 7.2s | |
| Z.AI GLM 4.5 Air | 100% | $0.0012 | 28.2s | |
| Qwen 2.5 72B | 100% | $0.0002 | 8.5s | |
| GPT-4o Mini (temp=1) | 100% | $0.0003 | 7.6s | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0004 | 7.1s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 5.5 (Reasoning) | 100% | 100% | 100% | |
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 100% | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Ember-1 (Reasoning, Max) | 100% | 100% | 100% | |
| Muse Wonder (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 100% | 100% | 100% | |
| GPT-5.6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Hy4 Preview (Reasoning, High) | 100% | 100% | 100% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Muse Spark 1.3 (Reasoning, Medium) | 100% | 100% | 100% | |
| GPT-6 Luna (Reasoning, High) | 100% | 100% | 100% | |
| GPT-5.4 (Reasoning) | 100% | 100% | 100% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Ministral 8B | 100% | $0.0001 | 2.4s | 100% | |
| Gemini 2.5 Flash Lite | 100% | $0.0002 | 1.3s | 100% | |
| Ministral 3 8B | 100% | $0.0001 | 3.0s | 100% | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 3.5s | 100% | |
| Mistral Small 4 | 100% | $0.0003 | 2.6s | 100% | |
| Laguna S 2.1 | 100% | $0.0001 | 6.9s | 100% | |
| DeepSeek V4 Flash | 100% | $0.0001 | 7.1s | 100% | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0008 | 1.7s | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0001 | 7.5s | 100% | |
| Gemini 3.1 Flash Lite | 100% | $0.0008 | 1.9s | 100% | |
| GPT-6 Luna | 100% | $0.0002 | 4.5s | 99% | |
| Gemma 3 12B | 100% | $0.0001 | 5.9s | 99% | |
| GPT-4o Mini (temp=0) | 100% | $0.0003 | 7.1s | 100% | |
| GPT-4o Mini (temp=1) | 100% | $0.0003 | 7.6s | 100% | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0004 | 7.1s | 100% | |
| Qwen 2.5 72B | 100% | $0.0002 | 8.5s | 100% | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0008 | 1.6s | 99% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0012 | 1.2s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0012 | 1.3s | 100% | |
| Qwen 3 235B A22B Instruct 2507 | 100% | $0.0003 | 9.9s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Name replacement accuracy | ||
| 100.0% | Non-name text preserved | ||
| 100.0% | Possessive traps preserved |
Tense rewriting: past to present
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Ministral 3B | 99% | $0.0000 | 1.9s | |
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.6s | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0006 | 3.7s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0007 | 4.7s | |
| GPT-6 Luna | 100% | $0.0003 | 4.3s | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.6s | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.7s | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0009 | 1.8s | |
| Gemini 3.1 Flash Lite | 100% | $0.0009 | 2.0s | |
| Gemma 4 26B | 100% | $0.0003 | 18.6s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0015 | 1.5s | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0015 | 1.4s | |
| DeepSeek V4 Flash | 100% | $0.0002 | 9.8s | |
| Gemini 2.5 Flash | 100% | $0.0015 | 2.1s | |
| Gemma 3 12B | 100% | $0.0001 | 8.4s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0001 | 8.5s | |
| Mistral Medium 3.1 | 100% | $0.0013 | 5.3s | |
| GPT-4.1 Mini | 100% | $0.0011 | 6.5s | |
| Qwen 2.5 72B | 100% | $0.0003 | 10.7s | |
| GPT-6 Luna (Reasoning, Medium) | 99% | $0.0005 | 8.7s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 5.5 (Reasoning) | 100% | 100% | 100% | |
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 100% | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Ember-1 (Reasoning, Max) | 100% | 100% | 100% | |
| Muse Wonder (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 100% | 100% | 100% | |
| GPT-5.6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Hy4 Preview (Reasoning, High) | 100% | 100% | 100% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 100% | 100% | 100% | |
| Qwen 3.8 Flash (Reasoning) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Muse Spark 1.3 (Reasoning, Medium) | 100% | 100% | 100% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.6s | 100% | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.6s | 100% | |
| GPT-6 Luna | 100% | $0.0003 | 4.3s | 100% | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0009 | 1.8s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0006 | 3.7s | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0007 | 4.7s | 100% | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.7s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0015 | 1.4s | 100% | |
| Gemini 3.1 Flash Lite | 100% | $0.0009 | 2.0s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0015 | 1.5s | 100% | |
| Gemma 3 12B | 100% | $0.0001 | 8.4s | 100% | |
| Gemini 2.5 Flash | 100% | $0.0015 | 2.1s | 100% | |
| DeepSeek V4 Flash | 100% | $0.0002 | 9.8s | 100% | |
| Ministral 3 14B | 99% | $0.0002 | 3.9s | 99% | |
| Mistral Medium 3.1 | 100% | $0.0013 | 5.3s | 100% | |
| GPT-4.1 Mini | 100% | $0.0011 | 6.5s | 100% | |
| Qwen 2.5 72B | 100% | $0.0003 | 10.7s | 100% | |
| Mistral Large 3 | 100% | $0.0011 | 7.8s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0012 | 7.8s | 100% | |
| Qwen 3.5 Plus (2026-02-15) | 100% | $0.0015 | 6.4s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Dialogue content preserved | ||
| 100.0% | Name replacement accuracy | ||
| 100.0% | Non-name text preserved |
POV shift: 3rd person to 1st person (Elena's perspective)
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Ministral 3B | 99% | $0.0000 | 2.2s | |
| Mistral NeMO | 100% | $0.0002 | 2.0s | |
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.6s | |
| Ministral 3 3B | 100% | $0.0001 | 2.4s | |
| Ministral 8B | 100% | $0.0001 | 3.5s | |
| Ministral 3 8B | 100% | $0.0002 | 3.0s | |
| Mistral Small 4 | 100% | $0.0004 | 3.3s | |
| Ministral 3 14B | 100% | $0.0002 | 3.8s | |
| GPT-4.1 Nano | 100% | $0.0003 | 3.5s | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.8s | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0009 | 1.7s | |
| Gemini 3.1 Flash Lite | 100% | $0.0009 | 3.1s | |
| Laguna S 2.1 | 100% | $0.0001 | 21.4s | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.8s | |
| Gemma 3 4B | 100% | $0.0001 | 6.4s | |
| GPT-6 Luna | 100% | $0.0003 | 5.0s | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0003 | 5.2s | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0009 | 3.5s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0015 | 1.3s | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0015 | 1.5s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 5.5 (Reasoning) | 100% | 100% | 100% | |
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 100% | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Ember-1 (Reasoning, Max) | 100% | 100% | 100% | |
| Muse Wonder (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 100% | 100% | 100% | |
| GPT-5.6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Hy4 Preview (Reasoning, High) | 100% | 100% | 100% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 100% | 100% | 100% | |
| Qwen 3.8 Flash (Reasoning) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Muse Spark 1.3 (Reasoning, Medium) | 100% | 100% | 100% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.6s | 100% | |
| Mistral NeMO | 100% | $0.0002 | 2.0s | 100% | |
| Ministral 3 8B | 100% | $0.0002 | 3.0s | 100% | |
| Ministral 8B | 100% | $0.0001 | 3.5s | 100% | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0009 | 1.7s | 100% | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.8s | 100% | |
| Mistral Small 4 | 100% | $0.0004 | 3.3s | 100% | |
| Ministral 3 14B | 100% | $0.0002 | 3.8s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0015 | 1.3s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0015 | 1.5s | 100% | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.8s | 100% | |
| Gemini 3.1 Flash Lite | 100% | $0.0009 | 3.1s | 100% | |
| Gemini 2.5 Flash | 100% | $0.0015 | 2.1s | 100% | |
| GPT-6 Luna | 100% | $0.0003 | 5.0s | 100% | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0003 | 5.2s | 100% | |
| Ministral 3 3B | 100% | $0.0001 | 2.4s | 99% | |
| Inception Mercury 2 | 100% | $0.0018 | 2.3s | 100% | |
| Gemma 3 4B | 100% | $0.0001 | 6.4s | 100% | |
| DeepSeek V4 Flash | 100% | $0.0002 | 6.5s | 100% | |
| Gemini 3 Flash (Preview) | 100% | $0.0018 | 3.1s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Name replacement accuracy | ||
| 100.0% | No remaining old names | ||
| 100.0% | Non-name text preserved |
Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Ministral 3B | 99% | $0.0001 | 2.5s | |
| Ministral 3 3B | 100% | $0.0001 | 2.2s | |
| Mistral NeMO | 100% | $0.0002 | 3.6s | |
| Ministral 8B | 100% | $0.0001 | 3.8s | |
| Ministral 3 8B | 100% | $0.0002 | 3.9s | |
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.9s | |
| Gemma 3 4B | 100% | $0.0001 | 6.6s | |
| Ministral 3 14B | 100% | $0.0003 | 4.6s | |
| Mistral Small 3.2 24B | 86% | $0.0003 | 4.9s | |
| GPT-4.1 Nano | 95% | $0.0003 | 3.9s | |
| Laguna S 2.1 | 100% | $0.0002 | 20.9s | |
| Mistral Small 4 | 100% | $0.0005 | 3.3s | |
| DeepSeek V4 Flash | 100% | $0.0002 | 9.5s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0002 | 9.9s | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0005 | 7.7s | |
| Qwen 2.5 72B | 100% | $0.0003 | 11.4s | |
| Laguna XS 2.1 | 99% | $0.0002 | 15.3s | |
| GPT-5.4 Nano | 100% | $0.0009 | 3.3s | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0006 | 8.9s | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0011 | 1.9s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 5.5 (Reasoning) | 100% | 100% | 100% | |
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 100% | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Ember-1 (Reasoning, Max) | 100% | 100% | 100% | |
| Muse Wonder (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 100% | 100% | 100% | |
| GPT-5.6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Hy4 Preview (Reasoning, High) | 100% | 100% | 100% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 100% | 100% | 100% | |
| Qwen 3.8 Flash (Reasoning) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| GPT-6 Luna (Reasoning, High) | 100% | 100% | 100% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Ministral 3 3B | 100% | $0.0001 | 2.2s | 100% | |
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.9s | 100% | |
| Ministral 8B | 100% | $0.0001 | 3.8s | 100% | |
| Mistral NeMO | 100% | $0.0002 | 3.6s | 100% | |
| Ministral 3 8B | 100% | $0.0002 | 3.9s | 100% | |
| Mistral Small 4 | 100% | $0.0005 | 3.3s | 100% | |
| Ministral 3 14B | 100% | $0.0003 | 4.6s | 100% | |
| Gemini 3.1 Flash Lite | 100% | $0.0011 | 1.9s | 100% | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0011 | 2.0s | 100% | |
| Gemma 3 4B | 100% | $0.0001 | 6.6s | 100% | |
| GPT-5.4 Nano | 100% | $0.0009 | 3.3s | 100% | |
| Gemini 2.5 Flash | 100% | $0.0017 | 2.4s | 100% | |
| DeepSeek V4 Flash | 100% | $0.0002 | 9.5s | 100% | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0006 | 8.9s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0011 | 6.9s | 100% | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0005 | 7.7s | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0011 | 7.6s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0011 | 8.0s | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0002 | 9.9s | 100% | |
| Qwen 2.5 72B | 100% | $0.0003 | 11.4s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Dialogue content preserved | ||
| 100.0% | Mara pronouns preserved (coreference test) | ||
| 100.0% | Name replacement accuracy | ||
| 100.0% | Non-name text preserved |
Combined: 3rd person past → 1st person present
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| GPT-6 Luna | 100% | $0.0003 | 4.2s | |
| Gemini 2.5 Flash Lite | 99% | $0.0003 | 1.6s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0015 | 1.4s | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0015 | 1.5s | |
| Gemini 2.5 Flash | 100% | $0.0015 | 2.0s | |
| Gemma 4 26B | 100% | $0.0002 | 13.3s | |
| Gemini 3.1 Flash Lite (Preview) | 99% | $0.0009 | 1.8s | |
| Gemini 3.1 Flash Lite | 99% | $0.0009 | 1.8s | |
| Gemini 3.1 Flash Lite (Reasoning) | 99% | $0.0009 | 8.0s | |
| Qwen 3 235B A22B Instruct 2507 | 99% | $0.0003 | 8.6s | |
| Mistral NeMO | 98% | $0.0002 | 2.6s | |
| Ministral 8B | 97% | $0.0001 | 2.9s | |
| Laguna S 2.1 | 99% | $0.0002 | 6.9s | |
| Ministral 3 8B | 99% | $0.0002 | 3.1s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 99% | $0.0002 | 8.7s | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0006 | 11.4s | |
| Ministral 3 14B | 99% | $0.0003 | 3.8s | |
| Mistral Small 3.2 24B | 99% | $0.0002 | 4.3s | |
| Mistral Medium 3.1 | 99% | $0.0013 | 7.1s | |
| Mistral Small 4 | 97% | $0.0004 | 2.8s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 100% | 100% | |
| GPT-5.6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| GPT-5.4 (Reasoning) | 100% | 100% | 100% | |
| Gemini 4 Argon (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Sonnet 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.5 Flash (Reasoning) | 100% | 100% | 100% | |
| Claude Opus 4.6 | 100% | 100% | 100% | |
| GPT-5 Mini | 100% | 100% | 100% | |
| GPT-5.6 Sol | 100% | 100% | 100% | |
| GPT-6 Sol | 100% | 100% | 100% | |
| Claude Opus 4.5 | 100% | 100% | 100% | |
| GPT-5.6 Terra | 100% | 100% | 100% | |
| Claude Opus 4 | 100% | 100% | 100% | |
| GPT-4.1 | 100% | 100% | 100% | |
| Gemma 4 31B | 100% | 100% | 100% | |
| Mistral Medium 3.5 | 100% | 100% | 100% | |
| GPT-4o, Aug. 6th (temp=0) | 100% | 100% | 100% | |
| Gemini 2.5 Flash | 100% | 100% | 100% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Gemini 2.5 Flash | 100% | $0.0015 | 2.0s | 100% | |
| Gemini 2.5 Flash Lite | 99% | $0.0003 | 1.6s | 99% | |
| GPT-6 Luna | 100% | $0.0003 | 4.2s | 99% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0015 | 1.4s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0015 | 1.5s | 100% | |
| Gemini 3.1 Flash Lite | 99% | $0.0009 | 1.8s | 99% | |
| Gemini 3.1 Flash Lite (Preview) | 99% | $0.0009 | 1.8s | 99% | |
| Qwen 3 235B A22B Instruct 2507 | 99% | $0.0003 | 8.6s | 99% | |
| Ministral 3 8B | 99% | $0.0002 | 3.1s | 99% | |
| Gemma 4 26B | 100% | $0.0002 | 13.3s | 100% | |
| Ministral 3 14B | 99% | $0.0003 | 3.8s | 99% | |
| Mistral Small 3.2 24B | 99% | $0.0002 | 4.3s | 99% | |
| Gemini 3.1 Flash Lite (Reasoning) | 99% | $0.0009 | 8.0s | 99% | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0006 | 11.4s | 99% | |
| Mistral Large 3 | 99% | $0.0011 | 7.8s | 99% | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0008 | 13.3s | 99% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 99% | $0.0002 | 8.7s | 98% | |
| Mistral Medium 3.1 | 99% | $0.0013 | 7.1s | 99% | |
| Laguna S 2.1 | 99% | $0.0002 | 6.9s | 98% | |
| Claude Haiku 5.5 (Adaptive) | 99% | $0.0016 | 10.6s | 99% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Dialogue content preserved | ||
| 98.2% | Name replacement accuracy | ||
| 100.0% | Non-name text preserved |
Passive voice → active voice
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Gemini 3 Flash (Preview) | 99% | $0.0027 | 4.4s | |
| Claude Haiku 5.5 (Reasoning, Low) | 97% | $0.0019 | 13.0s | |
| DeepSeek V4 Flash | 98% | $0.0003 | 11.7s | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 99% | $0.0071 | 3.1s | |
| Claude Haiku 5.5 (Adaptive) | 98% | $0.0021 | 13.9s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 98% | $0.0019 | 14.8s | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 99% | $0.0082 | 3.4s | |
| Grok 4.20 | 97% | $0.0029 | 6.9s | |
| Gemini 3.5 Flash Lite (Reasoning) | 97% | $0.0022 | 1.9s | |
| GPT-6 Luna | 97% | $0.0005 | 7.2s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 97% | $0.0022 | 2.0s | |
| Gemini 4 Argon (Reasoning, Medium) | 99% | $0.0095 | 6.1s | |
| Gemini 2.5 Flash | 97% | $0.0021 | 3.1s | |
| GPT-6 Luna (Reasoning, Medium) | 98% | $0.0012 | 22.1s | |
| Laguna S 2.1 | 96% | $0.0002 | 12.3s | |
| Qwen 3.5 Plus (2026-02-15) | 97% | $0.0022 | 9.5s | |
| GPT-6 Sol | 99% | $0.0093 | 14.1s | |
| Mistral Large 4.0 | 96% | $0.0021 | 8.7s | |
| Gemini 3.1 Flash Lite (Preview) | 95% | $0.0014 | 2.4s | |
| Gemma 4 31B | 99% | $0.0004 | 48.7s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Gemini 3.1 Pro (Preview) | 99% | 100% | 99% | |
| Gemini 4 Argon (Reasoning, Medium) | 99% | 100% | 99% | |
| Aion 3.0 | 99% | 100% | 99% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 99% | 99% | 99% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 99% | 99% | 99% | |
| Grok 4.6 (Reasoning, High) | 99% | 99% | 99% | |
| Claude Opus 4.8 (Reasoning) | 99% | 99% | 99% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 99% | 99% | 99% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 99% | 99% | 99% | |
| Gemini 3.6 Flash (Reasoning) | 99% | 99% | 99% | |
| Claude Opus 4.8 (Reasoning, Low) | 99% | 99% | 99% | |
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 99% | 98% | |
| Claude Opus 5 (Reasoning, Low) | 99% | 99% | 98% | |
| Claude Opus 4.6 | 98% | 100% | 98% | |
| GPT-5.5 (Reasoning, Medium) | 99% | 99% | 98% | |
| Z.AI GLM 5.2 (Reasoning, High) | 99% | 99% | 98% | |
| GPT-6 Sol | 99% | 99% | 98% | |
| GPT-5.6 Sol (Reasoning, Medium) | 99% | 99% | 98% | |
| GPT-5.6 Luna (Reasoning, Medium) | 99% | 99% | 98% | |
| Claude Opus 5.5 (Reasoning) | 99% | 99% | 98% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Gemini 3 Flash (Preview) | 99% | $0.0027 | 4.4s | 97% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 99% | $0.0082 | 3.4s | 99% | |
| Gemini 4 Argon (Reasoning, Medium) | 99% | $0.0095 | 6.1s | 99% | |
| DeepSeek V4 Flash | 98% | $0.0003 | 11.7s | 97% | |
| Claude Haiku 5.5 (Adaptive) | 98% | $0.0021 | 13.9s | 97% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 99% | $0.0071 | 3.1s | 98% | |
| GPT-6 Sol | 99% | $0.0093 | 14.1s | 98% | |
| Grok 4.20 | 97% | $0.0029 | 6.9s | 97% | |
| Gemini 3.5 Flash Lite (Reasoning) | 97% | $0.0022 | 1.9s | 96% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 97% | $0.0022 | 2.0s | 96% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 98% | $0.0019 | 14.8s | 96% | |
| GPT-6 Luna (Reasoning, Medium) | 98% | $0.0012 | 22.1s | 97% | |
| GPT-6 Luna | 97% | $0.0005 | 7.2s | 95% | |
| Gemini 2.5 Flash | 97% | $0.0021 | 3.1s | 95% | |
| Gemma 4 31B | 99% | $0.0004 | 48.7s | 98% | |
| GPT-5.6 Luna (Reasoning, Medium) | 99% | $0.013 | 13.6s | 98% | |
| Qwen 3.5 Plus (2026-02-15) | 97% | $0.0022 | 9.5s | 95% | |
| Claude Haiku 5.5 (Reasoning, Low) | 97% | $0.0019 | 13.0s | 94% | |
| Mistral Large 4.0 | 96% | $0.0021 | 8.7s | 95% | |
| DeepSeek V3.2 | 99% | $0.0006 | 54.4s | 97% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Dialogue content preserved | ||
| 100.0% | No hallucinated or fabricated content | ||
| 98.2% | Non-passive narration preserved | ||
| 90.7% | Passive → active voice transformations | ||
| 100.0% | Structural similarity to original |
Avoid said/asked/replied/answered
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | Cost | Time | ||
|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.5s | |
| Gemma 3 4B | 98% | $0.0001 | 5.5s | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 6.2s | |
| Mistral Small 4 | 99% | $0.0004 | 3.1s | |
| Gemma 3 12B | 98% | $0.0001 | 7.4s | |
| GPT-6 Luna | 100% | $0.0003 | 4.6s | |
| DeepSeek V4 Flash | 98% | $0.0002 | 9.5s | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0004 | 5.4s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 83% | $0.0002 | 9.5s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 98% | $0.0006 | 4.2s | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0006 | 4.8s | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0007 | 4.5s | |
| Qwen 2.5 72B | 100% | $0.0003 | 10.4s | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0004 | 8.0s | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.7s | |
| GPT-4o Mini (temp=1) | 100% | $0.0004 | 9.5s | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0009 | 1.8s | |
| Gemini 3.1 Flash Lite | 100% | $0.0009 | 2.6s | |
| Xiaomi MIMO v2.6 Flash | 100% | $0.0003 | 15.5s | |
| GPT-4o Mini (temp=0) | 100% | $0.0004 | 9.7s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 5.5 (Reasoning) | 100% | 100% | 100% | |
| Qwen 3.8 Max (Reasoning, XHigh) | 100% | 100% | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Ember-1 (Reasoning, Max) | 100% | 100% | 100% | |
| Muse Wonder (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 100% | 100% | 100% | |
| GPT-5.6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Hy4 Preview (Reasoning, High) | 100% | 100% | 100% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 100% | 100% | 100% | |
| Qwen 3.8 Flash (Reasoning) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Muse Spark 1.3 (Reasoning, Medium) | 100% | 100% | 100% | |
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Score | Cost | Speed | Stability | ||
|---|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.5s | 100% | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0009 | 1.7s | 100% | |
| Gemini 3.1 Flash Lite (Reasoning) | 100% | $0.0009 | 1.8s | 100% | |
| GPT-6 Luna | 100% | $0.0003 | 4.6s | 100% | |
| Gemini 3.1 Flash Lite | 100% | $0.0009 | 2.6s | 100% | |
| Inception Mercury 2 | 100% | $0.0012 | 1.7s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0014 | 1.4s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0014 | 1.6s | 100% | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0004 | 5.4s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0007 | 4.5s | 100% | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 6.2s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0006 | 4.8s | 100% | |
| Gemini 2.5 Flash | 100% | $0.0014 | 2.0s | 100% | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0004 | 8.0s | 100% | |
| Mistral Medium 3.1 | 100% | $0.0012 | 5.1s | 100% | |
| Gemini 3 Flash (Preview) | 100% | $0.0018 | 3.2s | 100% | |
| GPT-4.1 Mini | 100% | $0.0010 | 6.3s | 100% | |
| GPT-4o Mini (temp=1) | 100% | $0.0004 | 9.5s | 100% | |
| Mistral Large 3 | 100% | $0.0011 | 7.2s | 100% | |
| GPT-4o Mini (temp=0) | 100% | $0.0004 | 9.7s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Forbidden words eliminated | ||
| 100.0% | Non-name text preserved | ||
| 100.0% | Structural similarity to original |