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.
Tense rewriting: past to present
Text Editing
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 | |
| Mistral Small Creative | 100% | $0.0002 | 2.9s | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.6s | |
| Llama 3.1 8B | 100% | $0.0001 | 10.6s | |
| Ministral 3 14B | 99% | $0.0002 | 3.9s | |
| Claude 3 Haiku | 100% | $0.0009 | 4.5s | |
| Mistral NeMO | 99% | $0.0002 | 2.7s | |
| Gemma 3 12B | 100% | $0.0001 | 8.4s | |
| Gemini 2.5 Flash | 100% | $0.0015 | 2.1s | |
| Ministral 3 8B | 99% | $0.0002 | 3.5s | |
| Ministral 8B | 98% | $0.0001 | 3.2s | |
| Mistral Medium 3.1 | 100% | $0.0013 | 5.3s | |
| Qwen 2.5 72B | 100% | $0.0003 | 10.7s | |
| GPT-4.1 Mini | 100% | $0.0011 | 6.5s | |
| Mistral Large 3 | 100% | $0.0011 | 7.8s | |
| Qwen 3.5 Plus (2026-02-15) | 100% | $0.0015 | 6.4s | |
| Grok 4 Fast | 100% | $0.0010 | 8.9s | |
| Gemma 3 27B | 100% | $0.0002 | 13.2s | |
| Gemini 3 Flash (Preview) | 99% | $0.0018 | 3.1s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Claude Sonnet 4.6 (Reasoning) | 100% | 100% | 100% | |
| GPT-5 Mini | 100% | 100% | 100% | |
| Claude Opus 4.6 | 100% | 100% | 100% | |
| GPT-5 | 100% | 100% | 100% | |
| Qwen 3.5 397B A17B | 100% | 100% | 100% | |
| Z.AI GLM 5 | 100% | 100% | 100% | |
| Claude Sonnet 4.6 | 100% | 100% | 100% | |
| Gemini 3 Flash (Preview, Reasoning) | 100% | 100% | 100% | |
| Claude Opus 4.5 | 100% | 100% | 100% | |
| Aion 2.0 | 100% | 100% | 100% | |
| Gemini 3 Pro (Preview) | 100% | 100% | 100% | |
| Claude Sonnet 4 | 100% | 100% | 100% | |
| Z.AI GLM 4.7 | 100% | 100% | 100% | |
| GPT-4.1 | 100% | 100% | 100% | |
| Gemini 2.5 Pro | 100% | 100% | 100% | |
| Claude Sonnet 4.5 | 100% | 100% | 100% | |
| Claude Opus 4 | 100% | 100% | 100% | |
| Gemini 2.5 Flash (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 | ||
|---|---|---|---|---|---|
| Gemini 2.5 Flash Lite | 100% | $0.0003 | 1.6s | 100% | |
| Mistral Small Creative | 100% | $0.0002 | 2.9s | 100% | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.6s | 100% | |
| Claude 3 Haiku | 100% | $0.0009 | 4.5s | 100% | |
| Gemini 2.5 Flash | 100% | $0.0015 | 2.1s | 100% | |
| Gemma 3 12B | 100% | $0.0001 | 8.4s | 100% | |
| Ministral 3 14B | 99% | $0.0002 | 3.9s | 99% | |
| Mistral Medium 3.1 | 100% | $0.0013 | 5.3s | 100% | |
| Llama 3.1 8B | 100% | $0.0001 | 10.6s | 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% | |
| Mistral NeMO | 99% | $0.0002 | 2.7s | 99% | |
| Qwen 3.5 Plus (2026-02-15) | 100% | $0.0015 | 6.4s | 100% | |
| Ministral 3B | 99% | $0.0000 | 1.9s | 97% | |
| Ministral 3 8B | 99% | $0.0002 | 3.5s | 98% | |
| Grok 4 Fast | 100% | $0.0010 | 8.9s | 99% | |
| Gemma 3 27B | 100% | $0.0002 | 13.2s | 100% | |
| Claude Haiku 4.5 | 100% | $0.0034 | 2.8s | 100% | |
| DeepSeek V3 (2024-12-26) | 100% | $0.0007 | 14.1s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Dialogue content preserved | ||
| 100.0% | Setting descriptions preserved | ||
| 100.0% | Tense transformation accuracy |