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.
POV shift: 3rd person to 1st person (Elena's perspective)
Text Editing
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | ||
|---|---|---|
| Gemini 3.1 Pro (Preview) | 100% | |
| GPT-5.1 | 100% | |
| GPT-5 | 100% | |
| Qwen 3.5 397B A17B | 100% | |
| Z.AI GLM 5 | 100% | |
| Claude Sonnet 4.6 | 100% | |
| MoonshotAI: Kimi K2.5 | 100% | |
| ByteDance Seed 1.6 | 100% | |
| Gemini 3 Flash (Preview, Reasoning) | 100% | |
| GPT-5.2 | 100% | |
| Grok 4.1 Fast | 100% | |
| Z.AI GLM 4.6 | 100% | |
| Gemini 3 Pro (Preview) | 100% | |
| Claude Sonnet 4 | 100% | |
| Z.AI GLM 4.7 | 100% | |
| GPT-4.1 | 100% | |
| Gemini 2.5 Pro | 100% | |
| Grok 4 | 100% | |
| Claude Sonnet 4.5 | 100% | |
| Claude Opus 4 | 100% | |
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 | |
| Grok 4 Fast | 100% | $0.0004 | 2.6s | |
| GPT-4.1 Nano | 98% | $0.0003 | 3.5s | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.2s | |
| Ministral 3 14B | 99% | $0.0002 | 3.7s | |
| Llama 3.1 8B | 99% | $0.0000 | 5.8s | |
| Gemma 3 12B | 100% | $0.0001 | 7.7s | |
| Gemini 2.5 Flash | 100% | $0.0014 | 2.1s | |
| Gemini 3 Flash (Preview) | 100% | $0.0018 | 3.2s | |
| Grok 4.1 Fast | 100% | $0.0006 | 7.3s | |
| GPT-4o Mini (temp=1) | 100% | $0.0004 | 9.2s | |
| GPT-4o Mini (temp=0) | 100% | $0.0004 | 9.0s | |
| GPT-4.1 Mini | 99% | $0.0010 | 6.3s | |
| Mistral Large 3 | 100% | $0.0010 | 7.3s | |
| Gemini 2.5 Flash Lite (Reasoning) | 100% | $0.0013 | 9.2s | |
| Qwen 2.5 72B | 100% | $0.0003 | 10.7s | |
| ByteDance Seed 1.6 Flash | 99% | $0.0005 | 9.5s | |
| Qwen 3.5 Plus (2026-02-15) | 100% | $0.0014 | 6.5s | |
| Gemma 3 4B | 95% | $0.0001 | 5.9s | |
| Arcee AI: Trinity Mini | 96% | $0.0002 | 6.7s | |
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) | 100% | 100% | 100% | |
| GPT-5.1 | 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% | |
| MoonshotAI: Kimi K2.5 | 100% | 100% | 100% | |
| ByteDance Seed 1.6 | 100% | 100% | 100% | |
| Gemini 3 Flash (Preview, Reasoning) | 100% | 100% | 100% | |
| GPT-5.2 | 100% | 100% | 100% | |
| Grok 4.1 Fast | 100% | 100% | 100% | |
| Z.AI GLM 4.6 | 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% | |
| Grok 4 | 100% | 100% | 100% | |
| Claude Sonnet 4.5 | 100% | 100% | 100% | |
| Claude Opus 4 | 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% | |
| Grok 4 Fast | 100% | $0.0004 | 2.6s | 100% | |
| Gemini 2.5 Flash | 100% | $0.0014 | 2.1s | 100% | |
| Mistral Small 3.2 24B | 100% | $0.0002 | 4.2s | 100% | |
| Gemini 3 Flash (Preview) | 100% | $0.0018 | 3.2s | 100% | |
| Ministral 3 14B | 99% | $0.0002 | 3.7s | 99% | |
| Gemma 3 12B | 100% | $0.0001 | 7.7s | 100% | |
| Grok 4.1 Fast | 100% | $0.0006 | 7.3s | 100% | |
| Claude Haiku 4.5 | 100% | $0.0033 | 2.9s | 100% | |
| Qwen 3.5 Plus (2026-02-15) | 100% | $0.0014 | 6.5s | 100% | |
| Mistral Large 3 | 100% | $0.0010 | 7.3s | 100% | |
| GPT-4.1 Nano | 98% | $0.0003 | 3.5s | 96% | |
| GPT-4o Mini (temp=0) | 100% | $0.0004 | 9.0s | 100% | |
| GPT-4o Mini (temp=1) | 100% | $0.0004 | 9.2s | 100% | |
| Llama 3.1 8B | 99% | $0.0000 | 5.8s | 96% | |
| Qwen 2.5 72B | 100% | $0.0003 | 10.7s | 100% | |
| Gemini 2.5 Flash Lite (Reasoning) | 100% | $0.0013 | 9.2s | 99% | |
| GPT-4.1 Mini | 99% | $0.0010 | 6.3s | 96% | |
| GPT-4.1 | 100% | $0.0050 | 4.5s | 100% | |
| Mistral Large 2 | 100% | $0.0041 | 6.9s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 100.0% | Dialogue and other-character pronouns preserved | ||
| 100.0% | No remaining protagonist name in narration | ||
| 99.7% | POV transformation accuracy |