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.
Combined: 3rd person past → 1st person present
Text Editing
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
| Score | ||
|---|---|---|
| Claude Opus 4.6 (Reasoning) | 100% | |
| Claude Sonnet 4.6 (Reasoning) | 100% | |
| GPT-5 Mini | 100% | |
| Claude Opus 4.6 | 100% | |
| Claude Opus 4.5 | 100% | |
| GPT-4.1 | 100% | |
| Claude Opus 4 | 100% | |
| GPT-4o, Aug. 6th (temp=0) | 100% | |
| Gemini 2.5 Flash | 100% | |
| GPT-5 | 100% | |
| Aion 2.0 | 100% | |
| Z.AI GLM 4.6 | 100% | |
| Claude Sonnet 4 | 100% | |
| Z.AI GLM 4.5 | 100% | |
| MoonshotAI: Kimi K2.5 | 100% | |
| Gemini 2.5 Pro | 100% | |
| Grok 4 | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | |
| Z.AI GLM 4.7 | 100% | |
| GPT-4o, May 13th (temp=0) | 100% | |
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 | 1.6s | |
| Gemini 2.5 Flash | 100% | $0.0015 | 2.0s | |
| Mistral NeMO | 98% | $0.0002 | 2.6s | |
| Ministral 8B | 97% | $0.0001 | 2.9s | |
| Mistral Small Creative | 99% | $0.0002 | 2.8s | |
| Ministral 3 8B | 99% | $0.0002 | 3.1s | |
| 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 | |
| Llama 3.1 8B | 98% | $0.0001 | 9.4s | |
| GPT-4.1 Mini | 99% | $0.0011 | 6.4s | |
| Mistral Large 3 | 99% | $0.0011 | 7.8s | |
| Rocinante 12B | 96% | $0.0004 | 6.3s | |
| Qwen 2.5 72B | 99% | $0.0003 | 10.1s | |
| Grok 4 Fast | 99% | $0.0013 | 10.2s | |
| Z.AI GLM 4.5 | 100% | $0.0030 | 25.1s | |
| Qwen 3.5 Plus (2026-02-15) | 99% | $0.0015 | 6.6s | |
| DeepSeek-V2 Chat | 99% | $0.0008 | 14.6s | |
| Gemma 3 12B | 98% | $0.0001 | 10.0s | |
| Gemini 3 Flash (Preview) | 98% | $0.0019 | 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% | |
| Claude Sonnet 4.6 (Reasoning) | 100% | 100% | 100% | |
| GPT-5 Mini | 100% | 100% | 100% | |
| Claude Opus 4.6 | 100% | 100% | 100% | |
| Claude Opus 4.5 | 100% | 100% | 100% | |
| GPT-4.1 | 100% | 100% | 100% | |
| Claude Opus 4 | 100% | 100% | 100% | |
| GPT-4o, Aug. 6th (temp=0) | 100% | 100% | 100% | |
| Gemini 2.5 Flash | 100% | 100% | 100% | |
| GPT-5 | 100% | 100% | 100% | |
| Aion 2.0 | 100% | 100% | 100% | |
| Z.AI GLM 4.6 | 100% | 100% | 100% | |
| Claude Sonnet 4 | 100% | 100% | 100% | |
| Z.AI GLM 4.5 | 100% | 100% | 100% | |
| MoonshotAI: Kimi K2.5 | 100% | 99% | 99% | |
| Gemini 2.5 Pro | 100% | 99% | 99% | |
| Z.AI GLM 4.7 | 100% | 99% | 99% | |
| GPT-4o, May 13th (temp=0) | 100% | 99% | 99% | |
| GPT-5.2 | 99% | 100% | 99% | |
| Gemini 3 Pro (Preview) | 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 | ||
|---|---|---|---|---|---|
| Gemini 2.5 Flash | 100% | $0.0015 | 2.0s | 100% | |
| Gemini 2.5 Flash Lite | 99% | $0.0003 | 1.6s | 99% | |
| Mistral Small Creative | 99% | $0.0002 | 2.8s | 99% | |
| Ministral 3 8B | 99% | $0.0002 | 3.1s | 99% | |
| Ministral 3 14B | 99% | $0.0003 | 3.8s | 99% | |
| Mistral Small 3.2 24B | 99% | $0.0002 | 4.3s | 99% | |
| Mistral Large 3 | 99% | $0.0011 | 7.8s | 99% | |
| Mistral Medium 3.1 | 99% | $0.0013 | 7.1s | 99% | |
| Qwen 2.5 72B | 99% | $0.0003 | 10.1s | 99% | |
| GPT-4.1 | 100% | $0.0055 | 3.8s | 100% | |
| DeepSeek-V2 Chat | 99% | $0.0008 | 14.6s | 99% | |
| Claude Haiku 4.5 | 99% | $0.0036 | 3.1s | 98% | |
| Gemini 3 Flash (Preview) | 98% | $0.0019 | 3.1s | 98% | |
| Qwen 3.5 Plus (2026-02-15) | 99% | $0.0015 | 6.6s | 98% | |
| GPT-4o, Aug. 6th (temp=0) | 100% | $0.0069 | 2.5s | 100% | |
| Gemma 3 12B | 98% | $0.0001 | 10.0s | 98% | |
| Mistral Large 2 | 99% | $0.0046 | 7.1s | 99% | |
| Mistral Large | 99% | $0.0046 | 7.6s | 99% | |
| Grok 4 Fast | 99% | $0.0013 | 10.2s | 97% | |
| Grok 4.1 Fast | 100% | $0.0015 | 16.8s | 99% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 98.2% | Combined transformation accuracy | ||
| 100.0% | Dialogue content preserved | ||
| 100.0% | Setting and Gregor references preserved |