Codex Violation Detection
Detects factual inconsistencies between a story bible and prose passages. The model must output structured XML identifying each violation with paragraph number and substring.
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-5.6 Terra | 98% | $0.011 | 3.8s | |
| Z.AI GLM 5 Turbo | 97% | $0.0072 | 17.1s | |
| GPT-5.4 | 97% | $0.013 | 8.8s | |
| Gemini 2.5 Flash (Reasoning) | 97% | $0.0079 | 12.5s | |
| Z.AI GLM 5.2 (Reasoning, High) | 97% | $0.0100 | 27.9s | |
| Gemma 4 31B | 97% | $0.0009 | 37.9s | |
| Gemini 3 Flash (Preview, Reasoning) | 97% | $0.011 | 18.0s | |
| Muse Spark 1.1 (Reasoning, Minimal) | 97% | $0.011 | 10.5s | |
| Grok 4.5 (Reasoning, Low) | 99% | $0.013 | 29.6s | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 95% | $0.011 | 3.6s | |
| GPT-5.6 Sol | 99% | $0.026 | 6.4s | |
| DeepSeek V4 Flash (Reasoning) | 97% | $0.0010 | 40.3s | |
| Muse Spark 1.1 (Reasoning, Medium) | 97% | $0.016 | 16.1s | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 95% | $0.011 | 3.3s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 94% | $0.0030 | 2.1s | |
| Xiaomi MIMO v2.5 | 95% | $0.0058 | 21.8s | |
| Qwen 3.6 Flash | 96% | $0.011 | 29.9s | |
| Gemini 2.5 Flash | 91% | $0.0025 | 2.8s | |
| GPT-5.4 (Reasoning, Low) | 96% | $0.020 | 13.5s | |
| Inception Mercury 2 | 92% | $0.0030 | 4.6s | |
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.
17 low-scoring outliers hidden: Ministral 3 8B (65.2%), GPT-4o Mini (temp=0) (64.9%), GPT-4o Mini (temp=1) (64.9%), Cydonia 24B V4.1 (64.3%), Mistral Small 4 (62.0%), Ministral 3 3B (61.5%), Cohere Command R+ (Aug. 2024) (61.4%), Hermes 3 70B (60.5%), Ministral 8B (59.6%), Ministral 3B (59.5%), Mistral NeMO (53.6%), Aion 3.0 Mini (47.3%), GPT-5.4 Nano (Reasoning, Low) (42.6%), Gemma 3 4B (39.2%), WizardLM 2 8x22b (36.9%), GPT-5.4 Nano (36.6%), GPT-4.1 Nano (21.9%).
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% | 97% | 97% | |
| Claude Opus 4.5 | 99% | 97% | 97% | |
| MoonshotAI: Kimi K3 (Reasoning, High) | 99% | 97% | 97% | |
| Gemini 3.6 Flash (Reasoning) | 99% | 96% | 96% | |
| Claude Opus 4.6 (Reasoning) | 99% | 96% | 96% | |
| Gemini 2.5 Pro | 99% | 95% | 95% | |
| Grok 4.5 (Reasoning, High) | 98% | 95% | 95% | |
| Grok 4.20 (Reasoning) | 98% | 95% | 95% | |
| GPT-5.6 Sol | 99% | 95% | 95% | |
| Qwen3.6 Max Preview | 98% | 95% | 95% | |
| MoonshotAI: Kimi K3 (Reasoning, Low) | 99% | 95% | 95% | |
| Grok 4.5 (Reasoning, Low) | 99% | 95% | 95% | |
| GPT-5.6 Terra | 98% | 94% | 94% | |
| Gemini 3.5 Flash (Reasoning) | 98% | 94% | 94% | |
| Claude Opus 4.6 | 99% | 94% | 94% | |
| Qwen 3.5 27B | 98% | 94% | 94% | |
| Z.AI GLM 5.1 | 98% | 94% | 94% | |
| GPT-5.5 | 98% | 93% | 93% | |
| Muse Spark 1.1 (Reasoning, Medium) | 97% | 93% | 93% | |
| GPT-5.5 (Reasoning) | 97% | 93% | 93% | |
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-5.6 Terra | 98% | $0.011 | 3.8s | 94% | |
| Gemini 2.5 Flash (Reasoning) | 97% | $0.0079 | 12.5s | 92% | |
| Z.AI GLM 5 Turbo | 97% | $0.0072 | 17.1s | 92% | |
| Muse Spark 1.1 (Reasoning, Minimal) | 97% | $0.011 | 10.5s | 92% | |
| GPT-5.4 | 97% | $0.013 | 8.8s | 91% | |
| Gemini 3 Flash (Preview, Reasoning) | 97% | $0.011 | 18.0s | 92% | |
| Gemma 4 31B | 97% | $0.0009 | 37.9s | 90% | |
| DeepSeek V4 Flash (Reasoning) | 97% | $0.0010 | 40.3s | 90% | |
| Grok 4.5 (Reasoning, Low) | 99% | $0.013 | 29.6s | 95% | |
| Muse Spark 1.1 (Reasoning, Medium) | 97% | $0.016 | 16.1s | 93% | |
| Gemini 3 Flash (Preview) | 94% | $0.0031 | 4.5s | 83% | |
| GPT-5.6 Sol | 99% | $0.026 | 6.4s | 95% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 95% | $0.011 | 3.3s | 87% | |
| Inception Mercury 2 | 92% | $0.0030 | 4.6s | 83% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 95% | $0.011 | 3.6s | 86% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 94% | $0.0030 | 2.1s | 80% | |
| Z.AI GLM 5.2 (Reasoning, High) | 97% | $0.0100 | 27.9s | 90% | |
| Gemini 2.5 Flash | 91% | $0.0025 | 2.8s | 82% | |
| Gemini 2.5 Flash Lite (Reasoning) | 93% | $0.0020 | 17.6s | 84% | |
| Grok 4.20 (Reasoning) | 98% | $0.015 | 45.4s | 95% | |
| matrix | tiers | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Model | Total â–¼ | Small codex (7 entries), short passage (165 words) | Large codex (40 entries), short passage (165 words) | Small codex (7 entries), long passage (734 words) | Large codex (40 entries), long passage (1,019 words) | 5 codex entries | 10 codex entries | 20 codex entries | 40 codex entries |
| Claude Opus 4.5 | 99% | 100% | 100% | 100% | 96% | 100% | 100% | 100% | 98% |
| Gemini 3.1 Pro (Preview) | 99% | 100% | 99% | 99% | 96% | 100% | 100% | 99% | 100% |
| MoonshotAI: Kimi K3 (Reasoning, High) | 99% | 100% | 99% | 98% | 98% | 100% | 100% | 98% | 100% |
| Gemini 3.6 Flash (Reasoning) | 99% | 100% | 98% | 98% | 97% | 100% | 99% | 98% | 100% |
| Claude Opus 4.6 (Reasoning) | 99% | 100% | 97% | 98% | 96% | 100% | 100% | 100% | 100% |
| GPT-5.6 Sol | 99% | 100% | 99% | 99% | 97% | 100% | 100% | 94% | 100% |
| Gemini 2.5 Pro | 99% | 99% | 100% | 99% | 96% | 100% | 99% | 97% | 99% |
| Claude Opus 4.6 | 99% | 100% | 98% | 99% | 91% | 100% | 100% | 100% | 100% |
| Grok 4.5 (Reasoning, Low) | 99% | 100% | 98% | 99% | 94% | 100% | 100% | 97% | 100% |
| MoonshotAI: Kimi K3 (Reasoning, Low) | 99% | 100% | 99% | 97% | 96% | 100% | 100% | 96% | 100% |
| Grok 4.5 (Reasoning, High) | 98% | 100% | 98% | 98% | 97% | 100% | 98% | 96% | 100% |
| Qwen3.6 Max Preview | 98% | 100% | 97% | 98% | 98% | 100% | 100% | 94% | 100% |
| Qwen3.7 Max | 98% | 100% | 98% | 95% | 98% | 100% | 100% | 95% | 100% |
| Grok 4.20 (Reasoning) | 98% | 100% | 97% | 97% | 98% | 100% | 97% | 96% | 100% |
| Gemini 3.5 Flash (Reasoning) | 98% | 100% | 98% | 98% | 95% | 100% | 99% | 95% | 100% |
1–15 of 161
Page 1 / 11
matrix
Small codex (7 entries), short passage (165 words)
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 | ||
|---|---|---|---|---|
| Laguna S 2.1 | 99% | $0.0002 | 13.6s | |
| Gemini 3.1 Flash Lite | 100% | $0.0012 | 2.0s | |
| Gemini 3.1 Flash Lite (Preview) | 100% | $0.0012 | 1.9s | |
| Gemini 3.1 Flash Lite (Reasoning) | 90% | $0.0011 | 6.5s | |
| DeepSeek V3.2 | 98% | $0.0006 | 16.2s | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0018 | 1.6s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0018 | 1.7s | |
| DeepSeek V3 (2024-12-26) | 100% | $0.0011 | 14.8s | |
| Mistral Medium 3.1 | 97% | $0.0018 | 5.6s | |
| DeepSeek-V2 Chat | 99% | $0.0011 | 12.7s | |
| Gemini 3 Flash (Preview) | 100% | $0.0025 | 3.6s | |
| DeepSeek V4 Flash | 96% | $0.0002 | 6.6s | |
| GPT-5.4 Nano (Reasoning) | 89% | $0.0022 | 9.4s | |
| GPT-5.6 Luna | 98% | $0.0036 | 3.6s | |
| Xiaomi MIMO v2.5 | 99% | $0.0031 | 11.9s | |
| Gemini 2.5 Flash Lite (Reasoning) | 95% | $0.0012 | 6.9s | |
| Llama 3.1 70B | 97% | $0.0009 | 14.9s | |
| Gemma 4 26B | 97% | $0.0003 | 24.6s | |
| DeepSeek V3 (2025-03-24) | 99% | $0.0007 | 36.3s | |
| Gemini 2.5 Flash | 97% | $0.0017 | 2.1s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| GPT-5.6 Sol (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Qwen3.7 Max | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| GPT-5.4 (Reasoning) | 100% | 100% | 100% | |
| Z.AI GLM 5.1 | 100% | 100% | 100% | |
| Qwen3.6 Max Preview | 100% | 100% | 100% | |
| GPT-5.5 (Reasoning) | 100% | 100% | 100% | |
| Claude Sonnet 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.5 Flash (Reasoning) | 100% | 100% | 100% | |
| MoonshotAI: Kimi K3 (Reasoning, High) | 100% | 100% | 100% | |
| Claude Opus 4.7 (Reasoning) | 100% | 100% | 100% | |
| GPT-5.6 Terra (Reasoning) | 100% | 100% | 100% | |
| Claude Opus 4.8 (Reasoning) | 100% | 100% | 100% | |
| Claude Opus 4.6 | 100% | 100% | 100% | |
| Claude Opus 5 (Reasoning, Low) | 100% | 100% | 100% | |
| Claude Opus 4.8 (Reasoning, Low) | 100% | 100% | 100% | |
| GPT-5 | 100% | 100% | 100% | |
| GPT-5 Mini | 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% | $0.0012 | 1.9s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0018 | 1.6s | 100% | |
| Gemini 3 Flash (Preview) | 100% | $0.0025 | 3.6s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0018 | 1.7s | 98% | |
| Gemini 3.1 Flash Lite | 100% | $0.0012 | 2.0s | 97% | |
| DeepSeek V3 (2024-12-26) | 100% | $0.0011 | 14.8s | 98% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 100% | $0.0066 | 2.5s | 100% | |
| Gemini 2.5 Flash (Reasoning) | 100% | $0.0052 | 7.8s | 100% | |
| Gemini 2.5 Flash | 97% | $0.0017 | 2.1s | 97% | |
| Inception Mercury 2 | 97% | $0.0018 | 2.6s | 97% | |
| Laguna S 2.1 | 99% | $0.0002 | 13.6s | 96% | |
| GPT-5.4 Mini (Reasoning, Low) | 99% | $0.0041 | 4.4s | 97% | |
| Xiaomi MIMO v2.5 | 99% | $0.0031 | 11.9s | 97% | |
| Z.AI GLM 5 Turbo | 100% | $0.0047 | 10.5s | 98% | |
| DeepSeek-V2 Chat | 99% | $0.0011 | 12.7s | 95% | |
| GPT-5.6 Terra | 100% | $0.0086 | 3.3s | 100% | |
| DeepSeek V4 Flash | 96% | $0.0002 | 6.6s | 93% | |
| GPT-5.6 Luna | 98% | $0.0036 | 3.6s | 93% | |
| Xiaomi MIMO v2.5 Pro | 100% | $0.0051 | 20.3s | 100% | |
| DeepSeek V3.2 | 98% | $0.0006 | 16.2s | 94% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 97.0% | Accuracy (recall) | ||
| 100.0% | Precision | ||
| 100.0% | Structural validity |
Large codex (40 entries), short passage (165 words)
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 | ||
|---|---|---|---|---|
| Z.AI GLM 5 Turbo | 98% | $0.0097 | 19.4s | |
| Grok 4.20 | 94% | $0.0081 | 8.6s | |
| Gemini 3 Flash (Preview) | 93% | $0.0039 | 6.2s | |
| DeepSeek V4 Flash | 92% | $0.0005 | 12.9s | |
| Inception Mercury 2 | 92% | $0.0040 | 5.5s | |
| Gemma 4 31B | 94% | $0.0013 | 1.2m | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 92% | $0.0044 | 2.7s | |
| Muse Spark 1.1 (Reasoning, Minimal) | 98% | $0.014 | 12.6s | |
| DeepSeek V4 Flash (Reasoning) | 96% | $0.0015 | 58.3s | |
| Gemini 2.5 Flash | 90% | $0.0038 | 4.0s | |
| GPT-5.4 | 98% | $0.018 | 11.4s | |
| Xiaomi MIMO v2.5 | 94% | $0.0071 | 25.0s | |
| Gemini 3.5 Flash Lite (Reasoning) | 92% | $0.0044 | 2.6s | |
| GPT-5.4 Mini (Reasoning, Low) | 92% | $0.0070 | 6.8s | |
| Xiaomi MIMO v2.5 Pro | 96% | $0.0093 | 35.3s | |
| Gemini 3.1 Flash Lite (Reasoning) | 90% | $0.0027 | 3.2s | |
| Qwen 3.6 Flash | 97% | $0.012 | 33.9s | |
| GPT-4.1 | 94% | $0.011 | 15.1s | |
| MiniMax M2.5 | 91% | $0.0023 | 30.1s | |
| Gemini 2.5 Flash (Reasoning) | 95% | $0.0098 | 14.4s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 4.5 | 100% | 100% | 100% | |
| GPT-5.5 | 100% | 100% | 100% | |
| Claude Sonnet 4.5 | 100% | 100% | 100% | |
| GPT-5.6 Sol | 99% | 98% | 98% | |
| Gemini 3.1 Pro (Preview) | 99% | 98% | 98% | |
| Gemini 2.5 Pro | 100% | 97% | 97% | |
| Gemini 3.6 Flash (Reasoning) | 98% | 99% | 97% | |
| MoonshotAI: Kimi K3 (Reasoning, Low) | 99% | 97% | 97% | |
| GPT-5.5 (Reasoning, Low) | 99% | 97% | 96% | |
| MoonshotAI: Kimi K3 (Reasoning, High) | 99% | 98% | 96% | |
| Gemini 3.5 Flash (Reasoning) | 98% | 97% | 96% | |
| Z.AI GLM 5.1 | 98% | 97% | 96% | |
| GPT-5.5 (Reasoning) | 97% | 98% | 96% | |
| Grok 4.5 (Reasoning, Low) | 98% | 96% | 95% | |
| Qwen3.7 Max | 98% | 97% | 95% | |
| MiniMax M3 | 98% | 97% | 95% | |
| Grok 4.5 (Reasoning, High) | 98% | 98% | 95% | |
| Claude Sonnet 4.6 (Reasoning) | 97% | 97% | 95% | |
| Claude Opus 4.6 | 98% | 97% | 95% | |
| MoonshotAI: Kimi K2.6 | 98% | 97% | 95% | |
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 | ||
|---|---|---|---|---|---|
| Z.AI GLM 5 Turbo | 98% | $0.0097 | 19.4s | 94% | |
| Muse Spark 1.1 (Reasoning, Minimal) | 98% | $0.014 | 12.6s | 94% | |
| GPT-5.4 | 98% | $0.018 | 11.4s | 93% | |
| Grok 4.5 (Reasoning, Low) | 98% | $0.018 | 20.6s | 95% | |
| Gemini 3 Flash (Preview) | 93% | $0.0039 | 6.2s | 88% | |
| GPT-5.6 Sol | 99% | $0.033 | 7.7s | 98% | |
| Claude Sonnet 4.5 | 100% | $0.036 | 11.3s | 100% | |
| Inception Mercury 2 | 92% | $0.0040 | 5.5s | 88% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 92% | $0.0044 | 2.7s | 88% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 94% | $0.016 | 5.0s | 92% | |
| Gemini 2.5 Flash (Reasoning) | 95% | $0.0098 | 14.4s | 90% | |
| Gemini 3.5 Flash Lite (Reasoning) | 92% | $0.0044 | 2.6s | 87% | |
| GPT-5.6 Terra | 96% | $0.018 | 5.2s | 91% | |
| Qwen 3.6 Flash | 97% | $0.012 | 33.9s | 94% | |
| Grok 4.20 | 94% | $0.0081 | 8.6s | 87% | |
| Gemini 3 Flash (Preview, Reasoning) | 96% | $0.012 | 19.4s | 91% | |
| GPT-5.5 | 100% | $0.042 | 10.0s | 100% | |
| Z.AI GLM 5.2 (Reasoning, High) | 97% | $0.012 | 35.5s | 92% | |
| Muse Spark 1.1 (Reasoning, Medium) | 96% | $0.021 | 19.0s | 93% | |
| GPT-5.6 Luna (Reasoning) | 95% | $0.016 | 13.3s | 90% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 85.8% | Accuracy (recall) | ||
| 94.3% | Precision | ||
| 100.0% | Structural validity |
Small codex (7 entries), long passage (734 words)
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 | ||
|---|---|---|---|---|
| Gemma 4 31B | 97% | $0.0005 | 44.4s | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 94% | $0.0076 | 2.9s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 93% | $0.0022 | 1.8s | |
| Gemini 3.5 Flash Lite (Reasoning) | 90% | $0.0021 | 1.7s | |
| Muse Spark 1.1 (Reasoning, Minimal) | 99% | $0.011 | 11.5s | |
| GPT-5.6 Terra | 97% | $0.0097 | 3.6s | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 96% | $0.0087 | 2.9s | |
| Claude Haiku 4.5 | 93% | $0.0051 | 4.6s | |
| DeepSeek V4 Flash (Reasoning) | 94% | $0.0010 | 45.3s | |
| GPT-4.1 Mini | 87% | $0.0011 | 4.4s | |
| MiniMax M2.7 | 91% | $0.0021 | 28.0s | |
| Qwen 3.5 Plus (2026-02-15) | 95% | $0.0025 | 21.6s | |
| Z.AI GLM 4.5 Air | 92% | $0.0026 | 39.2s | |
| Laguna S 2.1 | 85% | $0.0003 | 13.3s | |
| Gemma 4 26B | 90% | $0.0005 | 15.6s | |
| DeepSeek V4 Flash | 89% | $0.0002 | 8.0s | |
| Z.AI GLM 5 Turbo | 94% | $0.0077 | 19.5s | |
| DeepSeek-V2 Chat | 85% | $0.0013 | 9.8s | |
| Xiaomi MIMO v2.5 | 93% | $0.0057 | 22.2s | |
| Gemini 3 Flash (Preview) | 88% | $0.0022 | 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 4.5 | 100% | 100% | 100% | |
| Muse Spark 1.1 (Reasoning, Medium) | 100% | 97% | 97% | |
| Gemini 3.1 Pro (Preview) | 99% | 97% | 97% | |
| Claude Opus 4.7 | 97% | 100% | 97% | |
| Grok 4.5 (Reasoning, Low) | 99% | 96% | 96% | |
| Gemini 2.5 Pro | 99% | 96% | 96% | |
| GPT-5.6 Sol (Reasoning) | 95% | 100% | 95% | |
| Gemini 3.6 Flash (Reasoning) | 98% | 97% | 95% | |
| Qwen 3.5 27B | 98% | 97% | 95% | |
| GPT-5.6 Sol | 99% | 95% | 95% | |
| Claude Opus 4.6 | 99% | 95% | 95% | |
| Claude Opus 4.8 (Reasoning, Low) | 99% | 95% | 95% | |
| Muse Spark 1.1 (Reasoning, Minimal) | 99% | 95% | 95% | |
| Gemini 3.5 Flash (Reasoning) | 98% | 95% | 95% | |
| Qwen 3.5 397B A17B | 98% | 95% | 95% | |
| MoonshotAI: Kimi K3 (Reasoning, High) | 98% | 94% | 94% | |
| Qwen3.6 Max Preview | 98% | 97% | 94% | |
| Claude Opus 4.6 (Reasoning) | 98% | 93% | 93% | |
| Claude Haiku 4.5 | 93% | 100% | 93% | |
| Gemma 4 31B | 97% | 96% | 93% | |
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 | ||
|---|---|---|---|---|---|
| Muse Spark 1.1 (Reasoning, Minimal) | 99% | $0.011 | 11.5s | 95% | |
| Claude Haiku 4.5 | 93% | $0.0051 | 4.6s | 93% | |
| Gemma 4 31B | 97% | $0.0005 | 44.4s | 93% | |
| GPT-5.6 Terra | 97% | $0.0097 | 3.6s | 92% | |
| Muse Spark 1.1 (Reasoning, Medium) | 100% | $0.016 | 17.2s | 97% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 93% | $0.0022 | 1.8s | 86% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 96% | $0.0087 | 2.9s | 89% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 94% | $0.0076 | 2.9s | 89% | |
| GPT-5.6 Sol | 99% | $0.020 | 5.3s | 95% | |
| Gemini 3.5 Flash Lite (Reasoning) | 90% | $0.0021 | 1.7s | 87% | |
| Gemini 3 Flash (Preview, Reasoning) | 97% | $0.012 | 20.1s | 92% | |
| Qwen 3.5 Plus (2026-02-15) | 95% | $0.0025 | 21.6s | 84% | |
| Grok 4.5 (Reasoning, Low) | 99% | $0.015 | 45.7s | 96% | |
| DeepSeek V4 Flash (Reasoning) | 94% | $0.0010 | 45.3s | 88% | |
| Claude Opus 4.5 | 100% | $0.030 | 9.1s | 100% | |
| Xiaomi MIMO v2.5 | 93% | $0.0057 | 22.2s | 87% | |
| Gemma 4 26B | 90% | $0.0005 | 15.6s | 83% | |
| Qwen 3.5 Flash | 98% | $0.0044 | 1.3m | 93% | |
| Gemini 2.5 Flash (Reasoning) | 95% | $0.0094 | 16.9s | 87% | |
| Inception Mercury 2 | 88% | $0.0032 | 4.9s | 86% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 79.0% | Accuracy (recall) | ||
| 90.9% | Precision | ||
| 100.0% | Structural validity |
Large codex (40 entries), long passage (1,019 words)
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 | ||
|---|---|---|---|---|
| Muse Spark 1.1 (Reasoning, Minimal) | 96% | $0.022 | 18.9s | |
| Gemini 2.5 Flash (Reasoning) | 95% | $0.016 | 24.6s | |
| Inception Mercury 2 | 89% | $0.0066 | 10.4s | |
| Gemini 3 Flash (Preview) | 90% | $0.0068 | 9.3s | |
| Gemma 4 31B | 92% | $0.0018 | 55.9s | |
| DeepSeek V4 Flash (Reasoning) | 96% | $0.0022 | 1.5m | |
| GPT-5.6 Luna (Reasoning) | 95% | $0.022 | 18.1s | |
| GPT-5.6 Terra | 94% | $0.025 | 7.8s | |
| Gemini 2.5 Flash | 87% | $0.0051 | 5.7s | |
| Z.AI GLM 5 Turbo | 94% | $0.016 | 36.7s | |
| Gemini 2.5 Flash Lite (Reasoning) | 89% | $0.0041 | 42.5s | |
| Muse Spark 1.1 (Reasoning, Medium) | 96% | $0.031 | 32.6s | |
| GPT-5.4 | 95% | $0.028 | 20.6s | |
| Qwen 3.5 Flash | 93% | $0.0058 | 1.4m | |
| GPT-5.4 Mini (Reasoning, Low) | 87% | $0.010 | 9.6s | |
| GPT-5 Mini | 95% | $0.017 | 1.3m | |
| Grok 4.5 (Reasoning, Low) | 94% | $0.024 | 30.4s | |
| Qwen 3.6 Flash | 94% | $0.020 | 54.5s | |
| Xiaomi MIMO v2.5 | 86% | $0.014 | 51.9s | |
| Gemini 3 Flash (Preview, Reasoning) | 92% | $0.021 | 33.3s | |
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 (Reasoning, Low) | 98% | 99% | 97% | |
| Qwen3.6 Max Preview | 98% | 99% | 97% | |
| Claude Opus 5 (Reasoning) | 98% | 98% | 96% | |
| Qwen3.7 Max | 98% | 98% | 96% | |
| MoonshotAI: Kimi K3 (Reasoning, High) | 98% | 97% | 95% | |
| Claude Sonnet 4.6 (Reasoning) | 97% | 97% | 95% | |
| GPT-5 | 97% | 98% | 95% | |
| GPT-5.5 (Reasoning) | 97% | 97% | 95% | |
| Claude Opus 4.6 (Reasoning) | 96% | 97% | 94% | |
| Grok 4.20 (Reasoning) | 98% | 97% | 94% | |
| Gemini 3.1 Pro (Preview) | 96% | 98% | 94% | |
| GPT-5.6 Sol (Reasoning) | 96% | 99% | 94% | |
| Muse Spark 1.1 (Reasoning, Medium) | 96% | 97% | 94% | |
| Gemini 3.6 Flash (Reasoning) | 97% | 96% | 94% | |
| Qwen 3.5 27B | 96% | 99% | 94% | |
| Claude Opus 4.5 | 96% | 98% | 94% | |
| Claude Opus 4.7 (Reasoning) | 96% | 98% | 94% | |
| Claude Sonnet 5 (Reasoning, Low) | 97% | 97% | 94% | |
| GPT-5.5 | 95% | 98% | 94% | |
| GPT-5.6 Sol | 97% | 97% | 93% | |
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 | ||
|---|---|---|---|---|---|
| Muse Spark 1.1 (Reasoning, Minimal) | 96% | $0.022 | 18.9s | 93% | |
| Gemini 2.5 Flash (Reasoning) | 95% | $0.016 | 24.6s | 92% | |
| GPT-5.6 Luna (Reasoning) | 95% | $0.022 | 18.1s | 93% | |
| GPT-5.6 Terra | 94% | $0.025 | 7.8s | 92% | |
| GPT-5.4 | 95% | $0.028 | 20.6s | 93% | |
| Z.AI GLM 5 Turbo | 94% | $0.016 | 36.7s | 92% | |
| Muse Spark 1.1 (Reasoning, Medium) | 96% | $0.031 | 32.6s | 94% | |
| Gemini 3 Flash (Preview) | 90% | $0.0068 | 9.3s | 87% | |
| Gemma 4 31B | 92% | $0.0018 | 55.9s | 90% | |
| DeepSeek V4 Flash (Reasoning) | 96% | $0.0022 | 1.5m | 93% | |
| Grok 4.5 (Reasoning, Low) | 94% | $0.024 | 30.4s | 89% | |
| Inception Mercury 2 | 89% | $0.0066 | 10.4s | 85% | |
| Qwen 3.6 Flash | 94% | $0.020 | 54.5s | 91% | |
| GPT-5 Mini | 95% | $0.017 | 1.3m | 93% | |
| Grok 4.20 (Reasoning) | 98% | $0.030 | 1.4m | 94% | |
| Gemini 3 Flash (Preview, Reasoning) | 92% | $0.021 | 33.3s | 88% | |
| GPT-5.4 (Reasoning, Low) | 95% | $0.042 | 30.5s | 92% | |
| GPT-5.4 Mini (Reasoning, Low) | 87% | $0.010 | 9.6s | 84% | |
| Gemini 2.5 Flash Lite (Reasoning) | 89% | $0.0041 | 42.5s | 85% | |
| GPT-5.6 Sol | 97% | $0.063 | 14.1s | 93% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 77.7% | Accuracy (recall) | ||
| 92.3% | Precision | ||
| 100.0% | Structural validity |
tiers
5 codex entries
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 | ||
|---|---|---|---|---|
| DeepSeek V4 Flash | 98% | $0.0001 | 3.4s | |
| Gemini 3.1 Flash Lite (Reasoning) | 96% | $0.0008 | 1.4s | |
| Gemini 3.1 Flash Lite (Preview) | 97% | $0.0008 | 1.3s | |
| Laguna XS 2.1 | 98% | $0.0002 | 6.2s | |
| Gemini 3.5 Flash Lite (Reasoning) | 100% | $0.0010 | 1.0s | |
| Gemma 4 26B | 100% | $0.0002 | 8.4s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0011 | 1.1s | |
| Gemini 2.5 Flash Lite (Reasoning) | 98% | $0.0008 | 5.2s | |
| Gemini 3 Flash (Preview) | 100% | $0.0015 | 2.3s | |
| GPT-5.6 Luna | 100% | $0.0022 | 1.9s | |
| DeepSeek-V2 Chat | 96% | $0.0007 | 6.2s | |
| DeepSeek V3 (2024-12-26) | 96% | $0.0007 | 7.3s | |
| DeepSeek V4 Flash (Reasoning) | 99% | $0.0003 | 12.7s | |
| Qwen 3 32B | 100% | $0.0005 | 13.1s | |
| Gemma 4 31B | 100% | $0.0003 | 23.4s | |
| GPT-5.4 Nano (Reasoning) | 89% | $0.0014 | 6.3s | |
| Qwen 3.5 Plus (2026-02-15) | 97% | $0.0014 | 12.5s | |
| DeepSeek V4 Pro | 97% | $0.0010 | 8.1s | |
| DeepSeek V3 (2025-03-24) | 99% | $0.0006 | 9.6s | |
| Z.AI GLM 4.5 Air | 95% | $0.0011 | 13.4s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| GPT-5.6 Sol (Reasoning) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Qwen3.7 Max | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| GPT-5.4 (Reasoning) | 100% | 100% | 100% | |
| Muse Spark 1.1 (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.1 | 100% | 100% | 100% | |
| Qwen3.6 Max Preview | 100% | 100% | 100% | |
| GPT-5.5 (Reasoning) | 100% | 100% | 100% | |
| Claude Sonnet 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.5 Flash (Reasoning) | 100% | 100% | 100% | |
| MoonshotAI: Kimi K3 (Reasoning, High) | 100% | 100% | 100% | |
| MoonshotAI: Kimi K2.6 | 100% | 100% | 100% | |
| Claude Opus 4.7 (Reasoning) | 100% | 100% | 100% | |
| GPT-5.6 Terra (Reasoning) | 100% | 100% | 100% | |
| Claude Opus 4.8 (Reasoning) | 100% | 100% | 100% | |
| Claude Opus 4.6 | 100% | 100% | 100% | |
| MoonshotAI: Kimi K3 (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 3.5 Flash Lite (Reasoning) | 100% | $0.0010 | 1.0s | 100% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100% | $0.0011 | 1.1s | 100% | |
| Gemini 3 Flash (Preview) | 100% | $0.0015 | 2.3s | 100% | |
| Gemma 4 26B | 100% | $0.0002 | 8.4s | 100% | |
| GPT-5.6 Luna | 100% | $0.0022 | 1.9s | 100% | |
| Qwen 3 32B | 100% | $0.0005 | 13.1s | 100% | |
| GPT-5.4 Mini (Reasoning, Low) | 100% | $0.0032 | 3.8s | 100% | |
| DeepSeek V4 Flash | 98% | $0.0001 | 3.4s | 94% | |
| GPT-4.1 | 100% | $0.0035 | 3.2s | 100% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 100% | $0.0041 | 1.5s | 100% | |
| Hermes 3 405B | 100% | $0.0016 | 10.8s | 100% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 100% | $0.0044 | 1.7s | 100% | |
| GPT-5.6 Terra | 100% | $0.0045 | 2.1s | 100% | |
| GPT-5.6 Luna (Reasoning) | 100% | $0.0042 | 3.9s | 100% | |
| Gemini 2.5 Flash (Reasoning) | 100% | $0.0037 | 5.9s | 100% | |
| Gemini 2.5 Flash Lite (Reasoning) | 98% | $0.0008 | 5.2s | 94% | |
| Gemini 3.1 Flash Lite (Preview) | 97% | $0.0008 | 1.3s | 92% | |
| DeepSeek V3 (2025-03-24) | 99% | $0.0006 | 9.6s | 95% | |
| Muse Spark 1.1 (Reasoning, Minimal) | 100% | $0.0045 | 5.2s | 100% | |
| Gemini 3.1 Flash Lite (Reasoning) | 96% | $0.0008 | 1.4s | 91% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 99.0% | Accuracy (recall) | ||
| 100.0% | Precision | ||
| 100.0% | Structural validity |
10 codex entries
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 | ||
|---|---|---|---|---|
| Gemma 4 26B | 100% | $0.0003 | 10.1s | |
| Gemini 3.1 Flash Lite (Preview) | 94% | $0.0011 | 1.5s | |
| Gemini 3 Flash (Preview) | 100% | $0.0015 | 2.7s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 93% | $0.0015 | 1.2s | |
| Gemini 3.5 Flash Lite (Reasoning) | 81% | $0.0015 | 1.4s | |
| DeepSeek V4 Pro | 98% | $0.0027 | 11.8s | |
| Mistral Medium 3.1 | 99% | $0.0015 | 3.7s | |
| Gemma 4 31B | 100% | $0.0005 | 32.7s | |
| Inception Mercury 2 | 98% | $0.0020 | 3.2s | |
| Qwen3 235B A22B Instruct 2507 | 96% | $0.0004 | 10.3s | |
| DeepSeek V4 Flash (Reasoning) | 98% | $0.0005 | 17.7s | |
| Qwen 3.5 Plus (2026-02-15) | 94% | $0.0018 | 12.4s | |
| MiniMax M2.5 | 97% | $0.0014 | 17.9s | |
| Mistral Small 4 (Reasoning) | 93% | $0.0014 | 11.4s | |
| Laguna XS 2.1 | 94% | $0.0002 | 9.4s | |
| MiniMax M2.7 | 98% | $0.0014 | 19.7s | |
| Z.AI GLM 5 Turbo | 100% | $0.0035 | 9.0s | |
| Writer: Palmyra X5 | 94% | $0.0034 | 6.6s | |
| Xiaomi MIMO v2.5 | 99% | $0.0031 | 12.0s | |
| GPT-5.4 Nano (Reasoning) | 87% | $0.0018 | 7.4s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Qwen3.7 Max | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Qwen3.6 Max Preview | 100% | 100% | 100% | |
| GPT-5.5 (Reasoning) | 100% | 100% | 100% | |
| Z.AI GLM 5.2 (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5 Turbo | 100% | 100% | 100% | |
| MoonshotAI: Kimi K3 (Reasoning, High) | 100% | 100% | 100% | |
| GPT-5.5 (Reasoning, Low) | 100% | 100% | 100% | |
| Claude Opus 4.8 (Reasoning) | 100% | 100% | 100% | |
| Claude Opus 4.6 | 100% | 100% | 100% | |
| MoonshotAI: Kimi K3 (Reasoning, Low) | 100% | 100% | 100% | |
| Claude Opus 4.8 (Reasoning, Low) | 100% | 100% | 100% | |
| Claude Opus 5 (Reasoning) | 100% | 100% | 100% | |
| Qwen 3.5 397B A17B | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, Low) | 100% | 100% | 100% | |
| GPT-5.4 (Reasoning, Low) | 100% | 100% | 100% | |
| MoonshotAI: Kimi K2.5 | 100% | 100% | 100% | |
| GPT-5.6 Sol | 100% | 100% | 100% | |
| Claude Sonnet 5 (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 3 Flash (Preview) | 100% | $0.0015 | 2.7s | 100% | |
| Gemma 4 26B | 100% | $0.0003 | 10.1s | 100% | |
| Z.AI GLM 5 Turbo | 100% | $0.0035 | 9.0s | 100% | |
| GPT-5.6 Terra | 100% | $0.0051 | 2.2s | 100% | |
| Mistral Medium 3.1 | 99% | $0.0015 | 3.7s | 96% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 100% | $0.0055 | 1.7s | 100% | |
| Gemini 2.5 Flash (Reasoning) | 100% | $0.0049 | 7.5s | 100% | |
| Z.AI GLM 5.2 (Reasoning, High) | 100% | $0.0044 | 11.2s | 100% | |
| GPT-5.4 | 100% | $0.0061 | 4.2s | 100% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 100% | $0.0065 | 2.2s | 100% | |
| Gemma 4 31B | 100% | $0.0005 | 32.7s | 100% | |
| Inception Mercury 2 | 98% | $0.0020 | 3.2s | 94% | |
| DeepSeek V4 Flash (Reasoning) | 98% | $0.0005 | 17.7s | 94% | |
| Gemini 3 Flash (Preview, Reasoning) | 100% | $0.0067 | 11.1s | 100% | |
| Z.AI GLM 4.7 | 100% | $0.0047 | 26.8s | 100% | |
| GPT-5.4 (Reasoning, Low) | 100% | $0.0096 | 6.3s | 100% | |
| Qwen3 235B A22B Instruct 2507 | 96% | $0.0004 | 10.3s | 90% | |
| MiniMax M2.7 | 98% | $0.0014 | 19.7s | 93% | |
| Xiaomi MIMO v2.5 | 99% | $0.0031 | 12.0s | 92% | |
| GPT-5.6 Sol | 100% | $0.011 | 3.2s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 92.5% | Accuracy (recall) | ||
| 96.1% | Precision | ||
| 100.0% | Structural validity |
20 codex entries
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 3.5 Flash Lite (Reasoning, Minimal) | 99% | $0.0027 | 1.8s | |
| Gemini 3.5 Flash Lite (Reasoning) | 96% | $0.0027 | 1.9s | |
| Grok 4.20 | 99% | $0.0047 | 5.5s | |
| DeepSeek V4 Flash (Reasoning) | 94% | $0.0009 | 34.1s | |
| Gemini 2.5 Flash | 93% | $0.0023 | 2.5s | |
| Gemma 4 31B | 92% | $0.0007 | 20.8s | |
| Gemini 3 Flash (Preview) | 92% | $0.0031 | 4.0s | |
| DeepSeek V4 Flash | 88% | $0.0003 | 8.1s | |
| Mistral Medium 3.1 | 92% | $0.0027 | 8.1s | |
| ByteDance Seed 1.6 Flash | 87% | $0.0009 | 11.8s | |
| Gemini 2.5 Flash Lite (Reasoning) | 91% | $0.0022 | 17.1s | |
| GPT-5.6 Terra | 96% | $0.0098 | 3.1s | |
| Laguna XS 2.1 | 89% | $0.0003 | 18.3s | |
| Z.AI GLM 5 Turbo | 95% | $0.0077 | 20.7s | |
| GPT-4.1 | 75% | $0.0076 | 8.2s | |
| Gemini 3.1 Flash Lite (Reasoning) | 90% | $0.0018 | 2.1s | |
| Gemini 3.1 Flash Lite | 89% | $0.0018 | 2.6s | |
| ByteDance Seed 2.0 Lite | 97% | $0.0065 | 1.0m | |
| Gemini 3.1 Flash Lite (Preview) | 88% | $0.0019 | 2.2s | |
| Z.AI GLM 5.2 (Reasoning, High) | 97% | $0.0091 | 27.8s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Claude Opus 4.6 | 100% | 100% | 100% | |
| Claude Opus 4.5 | 100% | 100% | 100% | |
| Grok 4.20 | 99% | 98% | 98% | |
| Gemini 3.1 Pro (Preview) | 99% | 97% | 97% | |
| MoonshotAI: Kimi K3 (Reasoning, High) | 98% | 96% | 96% | |
| Gemini 3.6 Flash (Reasoning) | 98% | 97% | 96% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 99% | 95% | 95% | |
| Claude Opus 5 (Reasoning) | 99% | 95% | 95% | |
| GPT-5 | 97% | 97% | 94% | |
| Claude Opus 5 (Reasoning, Low) | 98% | 94% | 94% | |
| Grok 4.20 (Reasoning) | 96% | 96% | 93% | |
| GPT-5.1 | 96% | 96% | 93% | |
| Claude Opus 5 | 95% | 97% | 93% | |
| GPT-5.4 | 95% | 97% | 93% | |
| Claude Sonnet 4.5 | 97% | 93% | 93% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 92% | 100% | 92% | |
| Gemini 3 Flash (Preview) | 92% | 100% | 92% | |
| Gemma 4 31B | 92% | 100% | 92% | |
| GPT-5.2 | 95% | 96% | 92% | |
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 3.5 Flash Lite (Reasoning, Minimal) | 99% | $0.0027 | 1.8s | 95% | |
| Grok 4.20 | 99% | $0.0047 | 5.5s | 98% | |
| Gemini 3.5 Flash Lite (Reasoning) | 96% | $0.0027 | 1.9s | 90% | |
| Gemini 3 Flash (Preview) | 92% | $0.0031 | 4.0s | 92% | |
| Gemma 4 31B | 92% | $0.0007 | 20.8s | 92% | |
| Gemini 2.5 Flash | 93% | $0.0023 | 2.5s | 88% | |
| GPT-5.6 Terra | 96% | $0.0098 | 3.1s | 91% | |
| Mistral Medium 3.1 | 92% | $0.0027 | 8.1s | 88% | |
| GPT-5.4 | 95% | $0.011 | 8.4s | 93% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 92% | $0.010 | 3.1s | 92% | |
| Z.AI GLM 5.2 (Reasoning, High) | 97% | $0.0091 | 27.8s | 91% | |
| Gemini 3.1 Flash Lite (Preview) | 88% | $0.0019 | 2.2s | 88% | |
| Z.AI GLM 5 Turbo | 95% | $0.0077 | 20.7s | 89% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 92% | $0.012 | 3.3s | 90% | |
| Gemini 3.1 Flash Lite (Reasoning) | 90% | $0.0018 | 2.1s | 83% | |
| GPT-5.6 Luna (Reasoning) | 91% | $0.0083 | 8.7s | 89% | |
| Gemini 2.5 Flash Lite (Reasoning) | 91% | $0.0022 | 17.1s | 86% | |
| DeepSeek V4 Flash (Reasoning) | 94% | $0.0009 | 34.1s | 85% | |
| Gemini 2.5 Flash (Reasoning) | 93% | $0.0076 | 12.3s | 86% | |
| ByteDance Seed 2.0 Lite | 97% | $0.0065 | 1.0m | 91% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 81.8% | Accuracy (recall) | ||
| 90.2% | Precision | ||
| 100.0% | Structural validity |
40 codex entries
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 | ||
|---|---|---|---|---|
| Gemma 4 31B | 100% | $0.0012 | 29.3s | |
| DeepSeek V4 Flash (Reasoning) | 99% | $0.0010 | 36.2s | |
| Gemini 2.5 Flash Lite (Reasoning) | 97% | $0.0016 | 11.6s | |
| Z.AI GLM 5 Turbo | 100% | $0.0057 | 13.3s | |
| Gemini 2.5 Flash | 96% | $0.0027 | 3.3s | |
| GPT-5.6 Terra | 99% | $0.0100 | 2.8s | |
| Xiaomi MIMO v2.5 | 97% | $0.0045 | 16.2s | |
| MiniMax M3 | 98% | $0.0025 | 38.8s | |
| Z.AI GLM 5.2 (Reasoning, High) | 100% | $0.0076 | 17.0s | |
| Inception Mercury 2 | 94% | $0.0029 | 4.4s | |
| Laguna S 2.1 | 96% | $0.0007 | 27.4s | |
| Xiaomi MIMO v2.5 Pro | 99% | $0.0082 | 28.3s | |
| GPT-5.4 | 99% | $0.011 | 7.9s | |
| Gemini 2.5 Flash (Reasoning) | 98% | $0.0072 | 10.7s | |
| GPT-5.4 Mini (Reasoning, Low) | 94% | $0.0054 | 6.2s | |
| GPT-5.6 Luna (Reasoning) | 99% | $0.0094 | 9.3s | |
| Qwen 3.5 Flash | 98% | $0.0036 | 47.1s | |
| Mistral Large 3 | 94% | $0.0040 | 6.6s | |
| Z.AI GLM 4.7 | 98% | $0.0070 | 28.9s | |
| Mistral Small 4 (Reasoning) | 94% | $0.0020 | 15.1s | |
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 3.6 Flash (Reasoning) | 100% | 100% | 100% | |
| Qwen3.7 Max | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Muse Spark 1.1 (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen3.6 Max Preview | 100% | 100% | 100% | |
| GPT-5.5 (Reasoning) | 100% | 100% | 100% | |
| Claude Sonnet 4.6 (Reasoning) | 100% | 100% | 100% | |
| Z.AI GLM 5.2 (Reasoning, High) | 100% | 100% | 100% | |
| MoonshotAI: Kimi K3 (Reasoning, High) | 100% | 100% | 100% | |
| Claude Opus 4.7 (Reasoning) | 100% | 100% | 100% | |
| Claude Opus 4.6 | 100% | 100% | 100% | |
| MoonshotAI: Kimi K3 (Reasoning, Low) | 100% | 100% | 100% | |
| Claude Opus 5 (Reasoning, Low) | 100% | 100% | 100% | |
| Claude Opus 5 (Reasoning) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, Low) | 100% | 100% | 100% | |
| GPT-5.4 (Reasoning, Low) | 100% | 100% | 100% | |
| Grok 4.20 (Reasoning) | 100% | 100% | 100% | |
| GPT-5.6 Sol | 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 | ||
|---|---|---|---|---|---|
| Gemma 4 31B | 100% | $0.0012 | 29.3s | 100% | |
| Z.AI GLM 5 Turbo | 100% | $0.0057 | 13.3s | 98% | |
| Z.AI GLM 5.2 (Reasoning, High) | 100% | $0.0076 | 17.0s | 100% | |
| GPT-5.6 Terra | 99% | $0.0100 | 2.8s | 96% | |
| Muse Spark 1.1 (Reasoning, Medium) | 100% | $0.014 | 12.4s | 100% | |
| Grok 4.5 (Reasoning, Low) | 100% | $0.013 | 14.8s | 100% | |
| Muse Spark 1.1 (Reasoning, Minimal) | 100% | $0.014 | 8.4s | 98% | |
| GPT-5.6 Luna (Reasoning) | 99% | $0.0094 | 9.3s | 96% | |
| GPT-5.4 | 99% | $0.011 | 7.9s | 96% | |
| GPT-5.4 (Reasoning, Low) | 100% | $0.017 | 11.0s | 100% | |
| Gemini 2.5 Flash (Reasoning) | 98% | $0.0072 | 10.7s | 94% | |
| GPT-5.5 | 100% | $0.022 | 5.8s | 100% | |
| Gemini 2.5 Flash Lite (Reasoning) | 97% | $0.0016 | 11.6s | 91% | |
| Gemini 2.5 Flash | 96% | $0.0027 | 3.3s | 90% | |
| DeepSeek V4 Flash (Reasoning) | 99% | $0.0010 | 36.2s | 95% | |
| Xiaomi MIMO v2.5 | 97% | $0.0045 | 16.2s | 93% | |
| GPT-5.6 Terra (Reasoning) | 99% | $0.019 | 7.8s | 97% | |
| GPT-5.4 Mini (Reasoning) | 99% | $0.013 | 18.6s | 97% | |
| Xiaomi MIMO v2.5 Pro | 99% | $0.0082 | 28.3s | 95% | |
| Grok 4.20 (Reasoning) | 100% | $0.015 | 33.6s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 89.5% | Accuracy (recall) | ||
| 97.0% | Precision | ||
| 100.0% | Structural validity |