Codex Red Herring (False Positive Detection)
Tests whether models correctly report "no violations" when a codex is fully consistent with the prose passage. Models that hallucinate false violations (false positives) fail. Uses a 2×2 matrix of text length × codex size, with bare and detailed-entry variants.
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 Luna | 70% | $0.0020 | 1.2s | |
| GPT-4.1 Nano | 63% | $0.0005 | 4.6s | |
| GPT-6 Luna | 70% | $0.0002 | 2.2s | |
| GPT-5.4 Nano | 68% | $0.0005 | 1.5s | |
| Ministral 8B | 68% | $0.0007 | 4.4s | |
| Ministral 3 8B | 78% | $0.0013 | 17.9s | |
| GPT-5.4 Nano (Reasoning, Low) | 97% | $0.0008 | 3.9s | |
| Claude Haiku 5.5 (Adaptive) | 98% | $0.0014 | 5.2s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 96% | $0.0003 | 7.3s | |
| Inception Mercury 2 | 96% | $0.0027 | 3.8s | |
| GPT-5.4 Mini (Reasoning, Low) | 95% | $0.0034 | 4.0s | |
| GPT-5.4 Nano (Reasoning) | 94% | $0.0017 | 11.4s | |
| Gemma 4 31B | 71% | $0.0009 | 11.7s | |
| Claude Haiku 5.5 (Reasoning, Low) | 97% | $0.0013 | 7.1s | |
| ByteDance Seed 1.6 Flash | 94% | $0.0008 | 9.1s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0013 | 7.4s | |
| GPT-6.1 Sol (Reasoning, Medium) | 77% | $0.0033 | 5.1s | |
| Arcee AI: Trinity Mini | 73% | $0.0009 | 26.3s | |
| GPT-5.6 Luna (Reasoning, Medium) | 92% | $0.0048 | 4.7s | |
| GPT-6 Luna (Reasoning, Medium) | 79% | $0.0005 | 10.2s | |
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.
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | 100% | 100% | |
| Nemotron 3 Super | 99% | 83% | 83% | |
| Claude Haiku 5.5 (Adaptive) | 98% | 77% | 77% | |
| Claude Haiku 5.5 (Reasoning, Low) | 97% | 72% | 72% | |
| o4 Mini High | 97% | 72% | 72% | |
| Muse Spark 1.1 (Reasoning, Minimal) | 97% | 72% | 72% | |
| GPT-5.4 Nano (Reasoning, Low) | 97% | 70% | 70% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 96% | 67% | 67% | |
| o4 Mini | 96% | 67% | 67% | |
| Inception Mercury 2 | 96% | 67% | 67% | |
| Z.AI GLM 5 Turbo | 96% | 65% | 65% | |
| Claude Opus 5.5 (Reasoning) | 95% | 64% | 64% | |
| GPT-5.1 | 95% | 64% | 64% | |
| GPT-5.4 Mini (Reasoning, Low) | 95% | 64% | 64% | |
| Muse Spark 1.1 (Reasoning, Medium) | 95% | 61% | 61% | |
| Claude Opus 4.6 (Reasoning) | 94% | 60% | 60% | |
| Grok 4.5 (Reasoning, High) | 94% | 60% | 60% | |
| Muse Spark 1.2 (Reasoning, Medium) | 95% | 59% | 59% | |
| ByteDance Seed 1.6 Flash | 94% | 59% | 59% | |
| Grok 4.5 (Reasoning, Low) | 94% | 58% | 58% | |
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, Medium) | 100% | $0.0013 | 7.4s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 98% | $0.0014 | 5.2s | 77% | |
| Claude Haiku 5.5 (Reasoning, Low) | 97% | $0.0013 | 7.1s | 72% | |
| GPT-5.4 Nano (Reasoning, Low) | 97% | $0.0008 | 3.9s | 70% | |
| Nemotron 3 Super | 99% | $0.0000 | 1.3m | 83% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 96% | $0.0003 | 7.3s | 67% | |
| Inception Mercury 2 | 96% | $0.0027 | 3.8s | 67% | |
| Muse Spark 1.1 (Reasoning, Minimal) | 97% | $0.012 | 11.2s | 72% | |
| GPT-5.4 Mini (Reasoning, Low) | 95% | $0.0034 | 4.0s | 64% | |
| Z.AI GLM 5 Turbo | 96% | $0.0071 | 16.0s | 65% | |
| ByteDance Seed 1.6 Flash | 94% | $0.0008 | 9.1s | 59% | |
| o4 Mini | 96% | $0.014 | 25.0s | 67% | |
| GPT-5.4 Nano (Reasoning) | 94% | $0.0017 | 11.4s | 57% | |
| Gemini 4 Argon (Reasoning, Medium) | 93% | $0.0083 | 4.1s | 55% | |
| Grok 4.5 (Reasoning, Low) | 94% | $0.012 | 17.0s | 58% | |
| Z.AI GLM 5.2 (Reasoning, High) | 94% | $0.0081 | 25.8s | 58% | |
| Muse Spark 1.1 (Reasoning, Medium) | 95% | $0.019 | 19.4s | 61% | |
| GPT-5.6 Luna (Reasoning, Medium) | 92% | $0.0048 | 4.7s | 51% | |
| Laguna XS 2.1 | 91% | $0.0005 | 16.4s | 52% | |
| o4 Mini High | 97% | $0.027 | 52.5s | 72% | |
| basic entries | detailed entries | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Model | Total ▼ | Short text (~524 words), small codex (11 entries) | Short text (~524 words), big codex (51 entries) | Long text (~1594 words), small codex (11 entries) | Long text (~1594 words), big codex (51 entries) | Short text (~524 words), small codex (11 detailed entries) | Short text (~524 words), big codex (51 detailed entries) | Long text (~1594 words), small codex (11 detailed entries) | Long text (~1594 words), big codex (51 detailed entries) |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% |
| Nemotron 3 Super | 99% | 100% | 100% | 100% | 93% | 100% | 100% | 100% | 100% |
| Claude Haiku 5.5 (Adaptive) | 98% | 100% | 100% | 100% | 100% | 93% | 100% | 100% | 93% |
| Muse Spark 1.1 (Reasoning, Minimal) | 97% | 93% | 85% | 100% | 100% | 100% | 100% | 100% | 100% |
| o4 Mini High | 97% | 93% | 100% | 100% | 85% | 100% | 100% | 100% | 100% |
| Claude Haiku 5.5 (Reasoning, Low) | 97% | 100% | 100% | 100% | 100% | 93% | 100% | 100% | 85% |
| GPT-5.4 Nano (Reasoning, Low) | 97% | 100% | 90% | 100% | 100% | 93% | 93% | 100% | 100% |
| o4 Mini | 96% | 100% | 100% | 100% | 85% | 93% | 100% | 93% | 100% |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 96% | 100% | 93% | 100% | 93% | 93% | 100% | 93% | 100% |
| Inception Mercury 2 | 96% | 100% | 100% | 100% | 100% | 85% | 100% | 100% | 85% |
| Z.AI GLM 5 Turbo | 96% | 100% | 100% | 100% | 68% | 100% | 100% | 100% | 100% |
| Claude Opus 5.5 (Reasoning) | 95% | 100% | 100% | 100% | 100% | 70% | 93% | 100% | 100% |
| GPT-5.1 | 95% | 93% | 93% | 100% | 100% | 93% | 85% | 100% | 100% |
| GPT-5.4 Mini (Reasoning, Low) | 95% | 93% | 85% | 100% | 85% | 100% | 100% | 100% | 100% |
| Muse Spark 1.1 (Reasoning, Medium) | 95% | 85% | 100% | 100% | 83% | 100% | 100% | 100% | 92% |
1–15 of 202
Page 1 / 14
basic entries
Short text (~524 words), small codex (11 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% | $0.0002 | 3.8s | |
| GPT-5.6 Luna | 100% | $0.0005 | 709ms | |
| GPT-6 Luna | 100% | $0.0000 | 1.6s | |
| GPT-5.4 Nano | 80% | $0.0003 | 1.0s | |
| Mistral Large 4.0 | 93% | $0.0006 | 1.7s | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0005 | 2.8s | |
| GPT-5.6 Sol | 100% | $0.0023 | 2.0s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0001 | 5.4s | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0005 | 3.5s | |
| Arcee AI: Trinity Mini | 81% | $0.0012 | 36.6s | |
| GPT-6 Luna (Reasoning, Medium) | 85% | $0.0002 | 5.8s | |
| GPT-6 Luna (Reasoning, High) | 78% | $0.0003 | 6.9s | |
| Gemma 4 31B | 100% | $0.0002 | 12.4s | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0008 | 3.9s | |
| ByteDance Seed 1.6 Flash | 100% | $0.0004 | 5.3s | |
| Inception Mercury 2 | 100% | $0.0013 | 2.0s | |
| Thinking Machines Inkling | 80% | $0.0034 | 9.0s | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0005 | 5.5s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0005 | 5.9s | |
| Laguna S 2.1 | 95% | $0.0001 | 11.8s | |
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% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 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% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.1 Pro (Preview) | 100% | 100% | 100% | |
| Gemini 4 Argon (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.1 | 100% | 100% | 100% | |
| Qwen 3.6 Max Preview | 100% | 100% | 100% | |
| Gemini 3.5 Flash (Reasoning) | 100% | 100% | 100% | |
| Z.AI GLM 5 Turbo | 100% | 100% | 100% | |
| Claude Sonnet 5.5 (Reasoning) | 100% | 100% | 100% | |
| Grok 4.6 (Reasoning, High) | 100% | 100% | 100% | |
| Claude Opus 4.7 (Reasoning) | 100% | 100% | 100% | |
| Aion 3.5 Mini (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 | ||
|---|---|---|---|---|---|
| GPT-6 Luna | 100% | $0.0000 | 1.6s | 100% | |
| GPT-5.6 Luna | 100% | $0.0005 | 709ms | 100% | |
| Gemma 4 26B | 100% | $0.0002 | 3.8s | 100% | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0005 | 2.8s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0005 | 3.5s | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0001 | 5.4s | 100% | |
| ByteDance Seed 1.6 Flash | 100% | $0.0004 | 5.3s | 100% | |
| Inception Mercury 2 | 100% | $0.0013 | 2.0s | 100% | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0008 | 3.9s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0005 | 5.5s | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0005 | 5.9s | 100% | |
| GPT-5.6 Luna (Reasoning, Medium) | 100% | $0.0016 | 2.6s | 100% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 100% | $0.0024 | 850ms | 100% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 100% | $0.0024 | 990ms | 100% | |
| GPT-5.6 Sol | 100% | $0.0023 | 2.0s | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | $0.0017 | 5.3s | 100% | |
| Mistral Small 4 (Reasoning) | 100% | $0.0009 | 9.3s | 100% | |
| Gemma 4 31B | 100% | $0.0002 | 12.4s | 100% | |
| GPT-5.5 | 100% | $0.0041 | 1.3s | 100% | |
| Gemini 4 Argon (Reasoning, Medium) | 100% | $0.0044 | 2.5s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 72.5% | Correct "no violations" response | ||
| 85.0% | No hallucinated violations |
Short text (~524 words), big codex (51 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 | ||
|---|---|---|---|---|
| Ministral 8B | 68% | $0.0003 | 3.4s | |
| GPT-6 Luna | 78% | $0.0001 | 1.4s | |
| Gemma 4 26B | 95% | $0.0003 | 2.8s | |
| Ministral 3 8B | 93% | $0.0004 | 1.2s | |
| GPT-5.6 Luna | 100% | $0.0008 | 867ms | |
| GPT-5.4 Nano | 73% | $0.0004 | 1.4s | |
| Gemma 4 31B | 100% | $0.0004 | 1.7s | |
| GPT-6 Sol | 100% | $0.0012 | 1.8s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 93% | $0.0002 | 5.7s | |
| GPT-5.4 Nano (Reasoning, Low) | 90% | $0.0006 | 3.2s | |
| GPT-4.1 | 100% | $0.0020 | 737ms | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0007 | 3.7s | |
| Laguna XS 2.1 | 100% | $0.0003 | 11.6s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0006 | 5.1s | |
| GPT-5.6 Sol | 100% | $0.0027 | 928ms | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0006 | 5.4s | |
| ByteDance Seed 1.6 Flash | 100% | $0.0005 | 6.7s | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0010 | 5.1s | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | $0.0017 | 4.7s | |
| Arcee AI: Trinity Mini | 83% | $0.0003 | 15.8s | |
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% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 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% | |
| 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% | |
| Gemini 4 Argon (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.1 | 100% | 100% | 100% | |
| Qwen 3.6 Max Preview | 100% | 100% | 100% | |
| Claude Sonnet 4.6 (Reasoning) | 100% | 100% | 100% | |
| Z.AI GLM 5.2 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.5 Flash (Reasoning) | 100% | 100% | 100% | |
| Z.AI GLM 5 Turbo | 100% | 100% | 100% | |
| Claude Sonnet 5.5 (Reasoning) | 100% | 100% | 100% | |
| Grok 4.6 (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 | ||
|---|---|---|---|---|---|
| Gemma 4 31B | 100% | $0.0004 | 1.7s | 100% | |
| GPT-5.6 Luna | 100% | $0.0008 | 867ms | 100% | |
| GPT-6 Sol | 100% | $0.0012 | 1.8s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0007 | 3.7s | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0006 | 5.1s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0006 | 5.4s | 100% | |
| GPT-4.1 | 100% | $0.0020 | 737ms | 100% | |
| ByteDance Seed 1.6 Flash | 100% | $0.0005 | 6.7s | 100% | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0010 | 5.1s | 100% | |
| Gemini 2.5 Flash Lite (Reasoning) | 100% | $0.0011 | 6.6s | 100% | |
| GPT-5.6 Sol | 100% | $0.0027 | 928ms | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | $0.0017 | 4.7s | 100% | |
| Inception Mercury 2 | 100% | $0.0024 | 3.6s | 100% | |
| Laguna XS 2.1 | 100% | $0.0003 | 11.6s | 100% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 100% | $0.0043 | 890ms | 100% | |
| Z.AI GLM 5 Turbo | 100% | $0.0034 | 7.9s | 100% | |
| Gemini 4 Argon (Reasoning, Medium) | 100% | $0.0058 | 2.4s | 100% | |
| ByteDance Seed 1.6 | 100% | $0.0021 | 16.2s | 100% | |
| Xiaomi MIMO v2.6 Flash | 100% | $0.0003 | 22.7s | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | $0.0052 | 6.1s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 70.0% | Correct "no violations" response | ||
| 83.5% | No hallucinated violations |
Long text (~1594 words), small codex (11 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 | ||
|---|---|---|---|---|
| GPT-4.1 Nano | 93% | $0.0001 | 962ms | |
| GPT-6 Luna | 100% | $0.0001 | 1.2s | |
| Gemini 2.5 Flash Lite | 74% | $0.0003 | 516ms | |
| Mistral Small 3.2 24B | 72% | $0.0003 | 1.0s | |
| Ministral 3 8B | 90% | $0.0004 | 1.4s | |
| GPT-5.6 Luna | 100% | $0.0006 | 765ms | |
| GPT-5.4 Nano | 66% | $0.0004 | 1.6s | |
| Gemini 3.1 Flash Lite | 85% | $0.0007 | 741ms | |
| Gemini 3.1 Flash Lite (Reasoning) | 79% | $0.0008 | 874ms | |
| Gemini 3.1 Flash Lite (Preview) | 70% | $0.0008 | 882ms | |
| GPT-5.6 Terra | 100% | $0.0014 | 992ms | |
| Gemma 4 31B | 100% | $0.0004 | 20.6s | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0002 | 4.1s | |
| Mistral Medium 3.1 | 95% | $0.0011 | 764ms | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0002 | 4.8s | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0006 | 3.6s | |
| GPT-4.1 | 100% | $0.0022 | 815ms | |
| Inception Mercury 2 | 100% | $0.0013 | 2.0s | |
| Cydonia 24B V4.1 | 62% | $0.0008 | 9.4s | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0008 | 4.2s | |
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 3.7 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% | |
| 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% | |
| 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 | ||
|---|---|---|---|---|---|
| GPT-6 Luna | 100% | $0.0001 | 1.2s | 100% | |
| GPT-5.6 Luna | 100% | $0.0006 | 765ms | 100% | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0002 | 4.1s | 100% | |
| GPT-5.6 Terra | 100% | $0.0014 | 992ms | 100% | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0002 | 4.8s | 100% | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0006 | 3.6s | 100% | |
| Inception Mercury 2 | 100% | $0.0013 | 2.0s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0008 | 4.2s | 100% | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0010 | 3.7s | 100% | |
| GPT-4.1 | 100% | $0.0022 | 815ms | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0002 | 7.5s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0007 | 6.4s | 100% | |
| GPT-5.6 Luna (Reasoning, Medium) | 100% | $0.0021 | 2.8s | 100% | |
| GPT-5.4 Mini (Reasoning, Low) | 100% | $0.0021 | 3.0s | 100% | |
| ByteDance Seed 1.6 Flash | 100% | $0.0005 | 7.4s | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0008 | 7.8s | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | $0.0024 | 5.4s | 100% | |
| GPT-5.6 Terra (Reasoning, Medium) | 100% | $0.0035 | 2.4s | 100% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 100% | $0.0042 | 819ms | 100% | |
| GPT-6 Sol (Reasoning, Medium) | 100% | $0.0030 | 4.2s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 95.0% | Correct "no violations" response | ||
| 95.0% | No hallucinated violations |
Long text (~1594 words), big codex (51 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 | ||
|---|---|---|---|---|
| GPT-4.1 Nano | 93% | $0.0003 | 2.2s | |
| Ministral 3 8B | 93% | $0.0006 | 1.9s | |
| Cydonia 24B V4.1 | 71% | $0.0008 | 4.4s | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0011 | 6.4s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 93% | $0.0003 | 11.5s | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | $0.0027 | 5.2s | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0016 | 9.4s | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0013 | 11.0s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0013 | 10.7s | |
| ByteDance Seed 1.6 Flash | 93% | $0.0010 | 14.8s | |
| Inception Mercury 2 | 100% | $0.0039 | 5.5s | |
| GPT-5.4 Mini (Reasoning, Low) | 85% | $0.0048 | 6.5s | |
| Laguna XS 2.1 | 93% | $0.0006 | 23.3s | |
| GPT-5.6 Luna (Reasoning, Medium) | 75% | $0.0060 | 6.0s | |
| Gemini 4 Argon (Reasoning, Medium) | 100% | $0.0082 | 2.5s | |
| Mistral Small 4 (Reasoning) | 92% | $0.0026 | 21.1s | |
| GPT-6 Sol (Reasoning, Medium) | 100% | $0.0070 | 9.8s | |
| Gemini 2.5 Flash Lite (Reasoning) | 93% | $0.0033 | 22.0s | |
| DeepSeek V4 Flash (Reasoning) | 78% | $0.0010 | 39.3s | |
| Z.AI GLM 5 Turbo | 68% | $0.0096 | 25.3s | |
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% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 4 Argon (Reasoning, Medium) | 100% | 100% | 100% | |
| Grok 4.6 (Reasoning, High) | 100% | 100% | 100% | |
| GPT-6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 5 (Reasoning, Low) | 100% | 100% | 100% | |
| Muse Spark 1.1 (Reasoning, Minimal) | 100% | 100% | 100% | |
| GPT-5.1 | 100% | 100% | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | 100% | 100% | |
| DeepSeek V4 Pro (Reasoning) | 100% | 100% | 100% | |
| Xiaomi MIMO v2.6 Flash | 100% | 100% | 100% | |
| Aion 2.0 | 100% | 100% | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | 100% | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | 100% | 100% | |
| Inception Mercury 2 | 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 | ||
|---|---|---|---|---|---|
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0011 | 6.4s | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | $0.0027 | 5.2s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0016 | 9.4s | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0013 | 10.7s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0013 | 11.0s | 100% | |
| Inception Mercury 2 | 100% | $0.0039 | 5.5s | 100% | |
| Gemini 4 Argon (Reasoning, Medium) | 100% | $0.0082 | 2.5s | 100% | |
| GPT-6 Sol (Reasoning, Medium) | 100% | $0.0070 | 9.8s | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | $0.016 | 9.6s | 100% | |
| Muse Spark 1.1 (Reasoning, Minimal) | 100% | $0.017 | 20.3s | 100% | |
| Xiaomi MIMO v2.6 Flash | 100% | $0.0011 | 1.2m | 100% | |
| GPT-5 Nano | 100% | $0.0038 | 1.3m | 100% | |
| Claude Opus 5.5 (Reasoning) | 100% | $0.032 | 9.3s | 100% | |
| Aion 2.0 | 100% | $0.0086 | 1.3m | 100% | |
| GPT-5.1 | 100% | $0.029 | 28.6s | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | $0.036 | 21.9s | 100% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | $0.044 | 47.6s | 100% | |
| Ministral 3 8B | 93% | $0.0006 | 1.9s | 56% | |
| GPT-4.1 Nano | 93% | $0.0003 | 2.2s | 55% | |
| Grok 4.5 (Reasoning, High) | 100% | $0.063 | 2.4m | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 32.5% | Correct "no violations" response | ||
| 52.1% | No hallucinated violations |
detailed entries
Short text (~524 words), small codex (11 detailed 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 | ||
|---|---|---|---|---|
| Ministral 8B | 100% | $0.0004 | 338ms | |
| GPT-6 Luna | 85% | $0.0001 | 1.7s | |
| Mistral Small 3.2 24B | 63% | $0.0004 | 1.7s | |
| GPT-5.4 Nano | 83% | $0.0005 | 1.3s | |
| GPT-5.6 Luna | 100% | $0.0008 | 969ms | |
| Ministral 3 8B | 100% | $0.0006 | 339ms | |
| Gemma 4 26B | 100% | $0.0004 | 3.9s | |
| Gemma 4 31B | 100% | $0.0005 | 7.1s | |
| GPT-4.1 Mini | 93% | $0.0007 | 1.6s | |
| Cydonia 24B V4.1 | 83% | $0.0007 | 1.4s | |
| Ministral 3 14B | 100% | $0.0008 | 531ms | |
| Mistral Large 4.0 | 100% | $0.0012 | 1.4s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 93% | $0.0002 | 4.5s | |
| GPT-5.4 Nano (Reasoning, Low) | 93% | $0.0006 | 2.8s | |
| Laguna S 2.1 | 100% | $0.0005 | 14.3s | |
| Arcee AI: Trinity Mini | 93% | $0.0013 | 41.5s | |
| Laguna XS 2.1 | 100% | $0.0003 | 7.4s | |
| Claude Haiku 5.5 (Adaptive) | 93% | $0.0010 | 4.4s | |
| Mistral Large 3 | 100% | $0.0020 | 774ms | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0009 | 5.9s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Muse Spark 1.1 (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.1 | 100% | 100% | 100% | |
| Z.AI GLM 5.2 (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5 Turbo | 100% | 100% | 100% | |
| Claude Opus 4.7 (Reasoning) | 100% | 100% | 100% | |
| GPT-5.6 Terra (Reasoning, Medium) | 100% | 100% | 100% | |
| Muse Spark 1.1 (Reasoning, Minimal) | 100% | 100% | 100% | |
| GPT-5 Mini | 100% | 100% | 100% | |
| GPT-5.4 (Reasoning, Low) | 100% | 100% | 100% | |
| Claude Sonnet 4.6 | 100% | 100% | 100% | |
| GPT-5.6 Luna (Reasoning, Medium) | 100% | 100% | 100% | |
| MiniMax M3 | 100% | 100% | 100% | |
| Qwen 3.5 27B | 100% | 100% | 100% | |
| Claude Opus 5 | 100% | 100% | 100% | |
| Claude Opus 4.7 | 100% | 100% | 100% | |
| GPT-5.4 Mini (Reasoning) | 100% | 100% | 100% | |
| Gemma 4 31B (Reasoning) | 100% | 100% | 100% | |
| Claude Opus 4.5 | 100% | 100% | 100% | |
| Z.AI GLM 5 | 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% | $0.0004 | 338ms | 100% | |
| Ministral 3 8B | 100% | $0.0006 | 339ms | 100% | |
| Ministral 3 14B | 100% | $0.0008 | 531ms | 100% | |
| GPT-5.6 Luna | 100% | $0.0008 | 969ms | 100% | |
| Mistral Large 4.0 | 100% | $0.0012 | 1.4s | 100% | |
| Gemma 4 26B | 100% | $0.0004 | 3.9s | 100% | |
| Mistral Large 3 | 100% | $0.0020 | 774ms | 100% | |
| Laguna XS 2.1 | 100% | $0.0003 | 7.4s | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0009 | 5.9s | 100% | |
| Gemma 4 31B | 100% | $0.0005 | 7.1s | 100% | |
| GPT-5.4 Mini (Reasoning, Low) | 100% | $0.0023 | 3.9s | 100% | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0012 | 7.5s | 100% | |
| GPT-4.1 | 100% | $0.0035 | 613ms | 100% | |
| GPT-5.6 Luna (Reasoning, Medium) | 100% | $0.0036 | 3.7s | 100% | |
| Laguna S 2.1 | 100% | $0.0005 | 14.3s | 100% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 100% | $0.0059 | 725ms | 100% | |
| GPT-5.6 Terra (Reasoning, Medium) | 100% | $0.0052 | 3.4s | 100% | |
| GPT-5.4 Mini (Reasoning) | 100% | $0.0050 | 6.1s | 100% | |
| Gemini 2.5 Flash Lite (Reasoning) | 100% | $0.0021 | 15.1s | 100% | |
| Mistral Large 2 | 100% | $0.0078 | 650ms | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 60.0% | Correct "no violations" response | ||
| 80.0% | No hallucinated violations |
Short text (~524 words), big codex (51 detailed 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 | ||
|---|---|---|---|---|
| GPT-5.4 Nano | 74% | $0.0006 | 1.4s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0006 | 3.7s | |
| GPT-5.4 Nano (Reasoning, Low) | 93% | $0.0008 | 3.4s | |
| Ministral 8B | 100% | $0.0013 | 564ms | |
| Mistral Large 4.0 | 100% | $0.0034 | 1.3s | |
| Gemma 4 26B | 88% | $0.0012 | 5.3s | |
| Arcee AI: Trinity Mini | 100% | $0.0007 | 6.9s | |
| Gemma 4 31B | 100% | $0.0018 | 3.1s | |
| Ministral 3 8B | 100% | $0.0020 | 589ms | |
| GPT-5.4 Mini (Reasoning, Low) | 100% | $0.0038 | 2.7s | |
| Laguna XS 2.1 | 100% | $0.0009 | 21.5s | |
| ByteDance Seed 1.6 Flash | 93% | $0.0013 | 7.7s | |
| GPT-6 Luna (Reasoning, High) | 93% | $0.0008 | 10.4s | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0023 | 3.9s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0022 | 5.8s | |
| GPT-6 Luna (Reasoning, Medium) | 85% | $0.0008 | 13.1s | |
| Inception Mercury 2 | 100% | $0.0031 | 3.7s | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0020 | 8.1s | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0023 | 6.6s | |
| Laguna S 2.1 | 95% | $0.0007 | 31.1s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| Qwen 3.7 Max | 100% | 100% | 100% | |
| Muse Spark 1.3 (Reasoning, Medium) | 100% | 100% | 100% | |
| GPT-5.4 (Reasoning) | 100% | 100% | 100% | |
| Muse Spark 1.1 (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.2 (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5 Turbo | 100% | 100% | 100% | |
| Claude Opus 4.8 (Reasoning) | 100% | 100% | 100% | |
| Claude Opus 4.6 | 100% | 100% | 100% | |
| Muse Spark 1.1 (Reasoning, Minimal) | 100% | 100% | 100% | |
| GPT-5 Mini | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, Low) | 100% | 100% | 100% | |
| Claude Sonnet 4.6 | 100% | 100% | 100% | |
| GPT-5.6 Luna (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 5 | 100% | 100% | 100% | |
| GPT-5.4 Mini (Reasoning) | 100% | 100% | 100% | |
| Qwen 3.5 Plus (2026-04-20) | 100% | 100% | 100% | |
| Gemma 4 31B (Reasoning) | 100% | 100% | 100% | |
| Claude Opus 4.5 | 100% | 100% | 100% | |
| ByteDance Seed 1.6 | 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% | $0.0013 | 564ms | 100% | |
| Ministral 3 8B | 100% | $0.0020 | 589ms | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0006 | 3.7s | 100% | |
| Gemma 4 31B | 100% | $0.0018 | 3.1s | 100% | |
| Mistral Large 4.0 | 100% | $0.0034 | 1.3s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0023 | 3.9s | 100% | |
| Arcee AI: Trinity Mini | 100% | $0.0007 | 6.9s | 100% | |
| Inception Mercury 2 | 100% | $0.0031 | 3.7s | 100% | |
| GPT-5.4 Mini (Reasoning, Low) | 100% | $0.0038 | 2.7s | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0022 | 5.8s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0023 | 6.6s | 100% | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0020 | 8.1s | 100% | |
| Mistral Large 3 | 100% | $0.0066 | 1.4s | 100% | |
| GPT-5.4 Mini (Reasoning) | 100% | $0.0063 | 5.2s | 100% | |
| GPT-4.1 | 100% | $0.0086 | 1.0s | 100% | |
| Thinking Machines Inkling | 100% | $0.0087 | 1.6s | 100% | |
| GPT-5.6 Luna (Reasoning, Medium) | 100% | $0.0075 | 5.2s | 100% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 100% | $0.0099 | 862ms | 100% | |
| DeepSeek V4 Flash (Reasoning) | 100% | $0.0009 | 19.7s | 100% | |
| Laguna XS 2.1 | 100% | $0.0009 | 21.5s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 62.5% | Correct "no violations" response | ||
| 80.0% | No hallucinated violations |
Long text (~1594 words), small codex (11 detailed 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 | ||
|---|---|---|---|---|
| GPT-4.1 Nano | 78% | $0.0003 | 1.4s | |
| GPT-6 Luna | 100% | $0.0001 | 1.8s | |
| GPT-4o Mini (temp=1) | 100% | $0.0004 | 597ms | |
| GPT-4o Mini (temp=0) | 100% | $0.0005 | 670ms | |
| GPT-5.6 Luna | 100% | $0.0010 | 717ms | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0006 | 3.0s | |
| Laguna S 2.1 | 100% | $0.0004 | 15.5s | |
| GPT-5.6 Terra | 100% | $0.0040 | 939ms | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0004 | 6.7s | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | $0.0023 | 3.7s | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0004 | 7.6s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 93% | $0.0003 | 8.3s | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0012 | 4.6s | |
| Inception Mercury 2 | 100% | $0.0018 | 2.7s | |
| GPT-5.4 Nano (Reasoning) | 93% | $0.0014 | 6.7s | |
| GPT-5.4 Mini (Reasoning, Low) | 100% | $0.0029 | 3.0s | |
| ByteDance Seed 1.6 Flash | 100% | $0.0008 | 9.1s | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0011 | 6.7s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0011 | 7.2s | |
| GPT-4.1 | 100% | $0.0045 | 728ms | |
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% | |
| 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% | |
| GPT-5.6 Sol (Reasoning, Medium) | 100% | 100% | 100% | |
| Claude Opus 4.6 (Reasoning) | 100% | 100% | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | 100% | 100% | |
| Muse Spark 1.2 (Reasoning, Medium) | 100% | 100% | 100% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 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% | |
| GPT-5.4 (Reasoning) | 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% | |
| Claude Sonnet 4.6 (Reasoning) | 100% | 100% | 100% | |
| Z.AI GLM 5.2 (Reasoning, High) | 100% | 100% | 100% | |
| Gemini 3.5 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 | ||
|---|---|---|---|---|---|
| GPT-4o Mini (temp=1) | 100% | $0.0004 | 597ms | 100% | |
| GPT-4o Mini (temp=0) | 100% | $0.0005 | 670ms | 100% | |
| GPT-6 Luna | 100% | $0.0001 | 1.8s | 100% | |
| GPT-5.6 Luna | 100% | $0.0010 | 717ms | 100% | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0006 | 3.0s | 100% | |
| GPT-6 Luna (Reasoning, High) | 100% | $0.0004 | 6.7s | 100% | |
| Inception Mercury 2 | 100% | $0.0018 | 2.7s | 100% | |
| Claude Haiku 5.5 (Adaptive) | 100% | $0.0012 | 4.6s | 100% | |
| GPT-6 Luna (Reasoning, Medium) | 100% | $0.0004 | 7.6s | 100% | |
| Claude Haiku 5.5 (Reasoning, Low) | 100% | $0.0011 | 6.7s | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0011 | 7.2s | 100% | |
| GPT-6.1 Sol (Reasoning, Medium) | 100% | $0.0023 | 3.7s | 100% | |
| ByteDance Seed 1.6 Flash | 100% | $0.0008 | 9.1s | 100% | |
| GPT-5.6 Luna (Reasoning, Medium) | 100% | $0.0030 | 2.6s | 100% | |
| GPT-5.4 Mini (Reasoning, Low) | 100% | $0.0029 | 3.0s | 100% | |
| GPT-5.6 Terra | 100% | $0.0040 | 939ms | 100% | |
| GPT-4.1 | 100% | $0.0045 | 728ms | 100% | |
| Laguna S 2.1 | 100% | $0.0004 | 15.5s | 100% | |
| GPT-5.6 Terra (Reasoning, Medium) | 100% | $0.0063 | 3.5s | 100% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 100% | $0.0077 | 710ms | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 70.0% | Correct "no violations" response | ||
| 85.0% | No hallucinated violations |
Long text (~1594 words), big codex (51 detailed 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 | ||
|---|---|---|---|---|
| GPT-5.4 Nano | 78% | $0.0008 | 1.0s | |
| Ministral 8B | 100% | $0.0014 | 525ms | |
| Ministral 3 8B | 100% | $0.0022 | 678ms | |
| Ministral 3 14B | 93% | $0.0029 | 2.7s | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0014 | 6.3s | |
| Arcee AI: Trinity Mini | 90% | $0.0018 | 45.5s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0007 | 11.6s | |
| Claude Haiku 5.5 (Adaptive) | 93% | $0.0030 | 7.7s | |
| GPT-4.1 | 100% | $0.0097 | 972ms | |
| Claude Haiku 5.5 (Reasoning, Low) | 85% | $0.0028 | 8.9s | |
| GPT-5.6 Sol | 67% | $0.016 | 2.5s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0028 | 10.5s | |
| GPT-6 Luna (Reasoning, Medium) | 85% | $0.0010 | 16.3s | |
| GPT-6 Luna (Reasoning, High) | 85% | $0.0013 | 18.1s | |
| Inception Mercury 2 | 85% | $0.0056 | 7.7s | |
| GPT-5.4 Mini (Reasoning, Low) | 100% | $0.0073 | 5.9s | |
| ByteDance Seed 1.6 Flash | 84% | $0.0016 | 13.8s | |
| Gemini 4 Argon (Reasoning, Medium) | 100% | $0.010 | 3.8s | |
| Laguna XS 2.1 | 78% | $0.0009 | 23.0s | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0035 | 40.9s | |
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% | |
| 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% | |
| 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% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 100% | 100% | 100% | |
| Grok 4.5 (Reasoning, High) | 100% | 100% | 100% | |
| Muse Spark 1.3 (Reasoning, Medium) | 100% | 100% | 100% | |
| Gemini 4 Argon (Reasoning, Medium) | 100% | 100% | 100% | |
| Z.AI GLM 5.1 | 100% | 100% | 100% | |
| Qwen 3.6 Max Preview | 100% | 100% | 100% | |
| Z.AI GLM 5.2 (Reasoning, High) | 100% | 100% | 100% | |
| Z.AI GLM 5 Turbo | 100% | 100% | 100% | |
| Kimi K3 (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 8B | 100% | $0.0014 | 525ms | 100% | |
| Ministral 3 8B | 100% | $0.0022 | 678ms | 100% | |
| GPT-5.4 Nano (Reasoning, Low) | 100% | $0.0014 | 6.3s | 100% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 100% | $0.0007 | 11.6s | 100% | |
| GPT-4.1 | 100% | $0.0097 | 972ms | 100% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 100% | $0.0028 | 10.5s | 100% | |
| GPT-5.4 Mini (Reasoning, Low) | 100% | $0.0073 | 5.9s | 100% | |
| Gemini 4 Argon (Reasoning, Medium) | 100% | $0.010 | 3.8s | 100% | |
| ByteDance Seed 2.0 Lite | 100% | $0.0056 | 25.4s | 100% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 100% | $0.019 | 12.3s | 100% | |
| Grok 4.5 (Reasoning, Low) | 100% | $0.017 | 15.1s | 100% | |
| GPT-5.4 Nano (Reasoning) | 100% | $0.0035 | 40.9s | 100% | |
| Muse Spark 1.1 (Reasoning, Minimal) | 100% | $0.024 | 16.7s | 100% | |
| Z.AI GLM 5 Turbo | 100% | $0.016 | 33.5s | 100% | |
| GPT-5 Mini | 100% | $0.0090 | 53.0s | 100% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 100% | $0.036 | 20.9s | 100% | |
| DeepSeek V4 Flash (Reasoning) | 100% | $0.0021 | 1.2m | 100% | |
| Muse Glimmer 30B (Reasoning, Medium) | 100% | $0.0088 | 1.0m | 100% | |
| o4 Mini | 100% | $0.026 | 43.6s | 100% | |
| Z.AI GLM 5.2 (Reasoning, High) | 100% | $0.018 | 53.6s | 100% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 80.0% | Correct "no violations" response | ||
| 89.2% | No hallucinated violations |