Codex Extraction
Evaluates a model's ability to extract structured codex entries (characters, locations, objects, lore) from prose passages and return them as well-formed XML.
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 5.3 Flash (Reasoning, Low) | 97% | $0.0003 | 8.6s | |
| Gemini 3 Flash (Preview) | 97% | $0.0027 | 3.9s | |
| DeepSeek V4 Flash | 95% | $0.0003 | 7.7s | |
| Claude Haiku 5.5 (Reasoning, Low) | 96% | $0.0009 | 3.2s | |
| DeepSeek V4.1 Flash (Reasoning, High) | 98% | $0.0025 | 17.5s | |
| Claude Haiku 5.5 (Adaptive) | 96% | $0.0014 | 7.9s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 96% | $0.0009 | 3.5s | |
| Xiaomi MIMO v2.6 Pro | 98% | $0.0014 | 22.9s | |
| Qwen 3.5 Plus (2026-02-15) | 98% | $0.0030 | 10.6s | |
| Mistral Medium 3.1 | 96% | $0.0026 | 5.8s | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 98% | $0.010 | 2.9s | |
| Xiaomi MIMO v2.6 Flash | 97% | $0.0005 | 25.1s | |
| Xiaomi MIMO v2.5 | 97% | $0.0034 | 13.4s | |
| GPT-6 Luna (Reasoning, Medium) | 96% | $0.0007 | 13.7s | |
| Mistral Large 3 | 94% | $0.0027 | 8.2s | |
| Gemini 3.1 Flash Lite (Reasoning) | 95% | $0.0018 | 2.0s | |
| Gemini 2.5 Flash | 94% | $0.0023 | 2.5s | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 98% | $0.010 | 3.1s | |
| Z.AI GLM 5 Turbo | 97% | $0.0068 | 16.0s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 93% | $0.0025 | 1.5s | |
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: Cydonia 24B V4.1 (86.1%), Ministral 3 3B (86.1%), Muse Glimmer 30B (Reasoning, Medium) (86.1%), ByteDance Seed 1.6 Flash (85.5%), Arcee AI: Trinity Mini (84.9%), GPT-4o Mini (temp=0) (84.6%), GPT-4o Mini (temp=1) (84.3%), Cohere Command R+ (Aug. 2024) (84.2%), Llama 3.1 70B (83.8%), GPT-5.4 Nano (Reasoning, Low) (83.8%), Gemma 3 4B (83.3%), GPT-5.4 Nano (83.2%), Gemma 4 26B (80.5%), Gemma 3 12B (77.7%), Aion 3.0 Mini (76.1%), GPT-4.1 Nano (75.3%), Mistral NeMO (26.1%).
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) | 99% | 99% | 98% | |
| Ember-1 (Reasoning, Max) | 99% | 99% | 97% | |
| Claude Opus 4.6 (Reasoning) | 98% | 99% | 97% | |
| Claude Opus 4.5 | 99% | 99% | 97% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 98% | 99% | 97% | |
| Muse Wonder (Reasoning, Medium) | 98% | 99% | 97% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 99% | 98% | 97% | |
| Claude Opus 4.6 | 98% | 98% | 97% | |
| Kimi K3 (Reasoning, Low) | 98% | 99% | 97% | |
| Z.AI GLM 5.2 (Reasoning, High) | 98% | 98% | 97% | |
| Grok 4.6 (Reasoning, High) | 98% | 98% | 97% | |
| Aion 3.5 (Reasoning, High) | 98% | 98% | 97% | |
| Hy4 Preview (Reasoning, High) | 98% | 98% | 96% | |
| Muse Spark 1.3 (Reasoning, Medium) | 98% | 98% | 96% | |
| Grok 4.5 (Reasoning, High) | 98% | 98% | 96% | |
| Xiaomi MIMO v2.6 Pro | 98% | 98% | 96% | |
| Grok 4.20 (Reasoning) | 98% | 98% | 96% | |
| Gemini 3.5 Flash (Reasoning) | 98% | 98% | 96% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 98% | 98% | 96% | |
| Claude Sonnet 4.6 | 98% | 98% | 96% | |
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) | 97% | $0.0027 | 3.9s | 95% | |
| Claude Haiku 5.5 (Reasoning, Low) | 96% | $0.0009 | 3.2s | 94% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 96% | $0.0009 | 3.5s | 94% | |
| Qwen 3.5 Plus (2026-02-15) | 98% | $0.0030 | 10.6s | 95% | |
| Claude Haiku 5.5 (Adaptive) | 96% | $0.0014 | 7.9s | 93% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 98% | $0.0025 | 17.5s | 96% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 97% | $0.0003 | 8.6s | 91% | |
| Gemini 3.1 Flash Lite (Reasoning) | 95% | $0.0018 | 2.0s | 92% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 98% | $0.010 | 2.9s | 96% | |
| Gemini 3.1 Flash Lite (Preview) | 94% | $0.0017 | 2.0s | 92% | |
| Mistral Medium 3.1 | 96% | $0.0026 | 5.8s | 92% | |
| Xiaomi MIMO v2.6 Pro | 98% | $0.0014 | 22.9s | 96% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 98% | $0.010 | 3.1s | 95% | |
| Xiaomi MIMO v2.5 | 97% | $0.0034 | 13.4s | 94% | |
| GPT-6 Luna (Reasoning, Medium) | 96% | $0.0007 | 13.7s | 93% | |
| Gemini 3.1 Flash Lite | 94% | $0.0017 | 5.1s | 92% | |
| Mistral Large 4.0 | 95% | $0.0027 | 10.0s | 93% | |
| Mistral Medium 3.5 (Reasoning) | 96% | $0.0098 | 4.1s | 95% | |
| GPT-5.6 Luna | 95% | $0.0043 | 3.6s | 92% | |
| GPT-6 Luna | 94% | $0.0004 | 6.0s | 90% | |
| Model | Total â–¼ | Short: The Rusty Lantern (Explicit) | Medium: Through the Thornveil (Scattered) | Medium: The Hollow (Inferred) | Long: The Spire of Echoes (Dense) |
|---|---|---|---|---|---|
| Claude Opus 5.5 (Reasoning) | 99% | 99% | 99% | 99% | 99% |
| Z.AI GLM 5.3 (Reasoning, Max) | 99% | 99% | 98% | 99% | 99% |
| Claude Opus 4.5 | 99% | 99% | 98% | 99% | 98% |
| Ember-1 (Reasoning, Max) | 99% | 99% | 98% | 98% | 99% |
| Claude Opus 4.6 (Reasoning) | 98% | 99% | 99% | 99% | 98% |
| Aion 3.5 (Reasoning, High) | 98% | 99% | 99% | 97% | 98% |
| Claude Opus 4.8 (Reasoning) | 98% | 97% | 98% | 99% | 99% |
| Claude Opus 4.8 (Reasoning, Low) | 98% | 97% | 99% | 99% | 99% |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 98% | 98% | 99% | 99% | 98% |
| Muse Wonder (Reasoning, Medium) | 98% | 99% | 98% | 98% | 98% |
| Hy4 Preview (Reasoning, High) | 98% | 99% | 98% | 98% | 98% |
| Z.AI GLM 5.2 (Reasoning, High) | 98% | 99% | 99% | 97% | 98% |
| Gemini 3.5 Flash (Reasoning) | 98% | 98% | 99% | 98% | 99% |
| Claude Opus 4.6 | 98% | 99% | 97% | 99% | 98% |
| Grok 4.5 (Reasoning, High) | 98% | 98% | 99% | 98% | 98% |
1–15 of 202
Page 1 / 14
Short: The Rusty Lantern (Explicit)
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 5.3 Flash (Reasoning, Low) | 99% | $0.0002 | 5.9s | |
| Ministral 3 8B | 98% | $0.0005 | 2.6s | |
| Xiaomi MIMO v2.6 Pro | 99% | $0.0008 | 14.0s | |
| DeepSeek V4 Flash | 98% | $0.0002 | 5.6s | |
| Mistral Medium 3.1 | 98% | $0.0021 | 6.5s | |
| Z.AI GLM 4.5 | 99% | $0.0013 | 8.1s | |
| Qwen 3.5 Plus (2026-02-15) | 99% | $0.0024 | 7.9s | |
| Claude Haiku 5.5 (Adaptive) | 96% | $0.0011 | 5.9s | |
| Gemini 3 Flash (Preview) | 98% | $0.0022 | 3.1s | |
| GPT-6 Luna (Reasoning, Medium) | 96% | $0.0006 | 11.4s | |
| DeepSeek V4 Pro | 97% | $0.0005 | 10.9s | |
| Xiaomi MIMO v2.6 Flash | 97% | $0.0003 | 11.5s | |
| Xiaomi MIMO v2.5 | 98% | $0.0032 | 12.3s | |
| DeepSeek V3 (2024-12-26) | 96% | $0.0016 | 11.9s | |
| Gemma 4 26B | 96% | $0.0004 | 12.8s | |
| MiniMax M2.7 | 99% | $0.0016 | 22.0s | |
| DeepSeek V4 Flash (Reasoning) | 99% | $0.0007 | 24.8s | |
| Laguna S 2.1 | 96% | $0.0002 | 28.5s | |
| Mistral Large 4.0 | 96% | $0.0021 | 4.9s | |
| GPT-5.4 Nano (Reasoning) | 96% | $0.0017 | 7.3s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Gemini 3.7 Flash (Reasoning, Medium) | 99% | 100% | 99% | |
| Aion 3.5 (Reasoning, High) | 99% | 100% | 99% | |
| Qwen 3.5 Plus (2026-02-15) | 99% | 100% | 99% | |
| Claude Sonnet 4.5 | 99% | 99% | 99% | |
| Muse Wonder (Reasoning, Medium) | 99% | 100% | 99% | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 99% | 100% | 99% | |
| Claude Sonnet 4 | 99% | 100% | 99% | |
| GPT-5 | 99% | 100% | 99% | |
| Z.AI GLM 5.1 | 99% | 99% | 99% | |
| Claude Opus 4.6 | 99% | 100% | 99% | |
| Xiaomi MIMO v2.6 Pro | 99% | 99% | 99% | |
| Qwen 3.6 Max Preview | 99% | 100% | 99% | |
| Claude Opus 4.5 | 99% | 99% | 99% | |
| Z.AI GLM 5.2 (Reasoning, High) | 99% | 100% | 99% | |
| Claude Opus 4.6 (Reasoning) | 99% | 100% | 99% | |
| Claude Opus 4 | 99% | 99% | 98% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 99% | 99% | 98% | |
| DeepSeek V4 Flash (Reasoning) | 99% | 99% | 98% | |
| Claude Sonnet 4.6 | 99% | 99% | 98% | |
| Z.AI GLM 4.5 | 99% | 99% | 98% | |
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 5.3 Flash (Reasoning, Low) | 99% | $0.0002 | 5.9s | 99% | |
| Qwen 3.5 Plus (2026-02-15) | 99% | $0.0024 | 7.9s | 99% | |
| Ministral 3 8B | 98% | $0.0005 | 2.6s | 98% | |
| Z.AI GLM 4.5 | 99% | $0.0013 | 8.1s | 98% | |
| Xiaomi MIMO v2.6 Pro | 99% | $0.0008 | 14.0s | 99% | |
| DeepSeek V4 Flash | 98% | $0.0002 | 5.6s | 97% | |
| Gemini 3 Flash (Preview) | 98% | $0.0022 | 3.1s | 96% | |
| Mistral Medium 3.1 | 98% | $0.0021 | 6.5s | 96% | |
| GPT-6 Sol | 98% | $0.0049 | 8.4s | 98% | |
| Z.AI GLM 5.2 (Reasoning, High) | 99% | $0.0047 | 15.4s | 99% | |
| DeepSeek V4 Pro | 97% | $0.0005 | 10.9s | 96% | |
| DeepSeek V4 Flash (Reasoning) | 99% | $0.0007 | 24.8s | 98% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 99% | $0.0097 | 6.3s | 99% | |
| Hermes 3 405B | 99% | $0.0034 | 16.8s | 98% | |
| MiniMax M2.7 | 99% | $0.0016 | 22.0s | 97% | |
| Xiaomi MIMO v2.5 | 98% | $0.0032 | 12.3s | 96% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 98% | $0.0088 | 2.5s | 97% | |
| Mistral Large 4.0 | 96% | $0.0021 | 4.9s | 95% | |
| Z.AI GLM 5 Turbo | 98% | $0.0053 | 12.9s | 97% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 98% | $0.0080 | 3.2s | 96% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 90.1% | Accuracy | ||
| 98.3% | Precision | ||
| 99.1% | Recall | ||
| 100.0% | Structural validity |
Medium: Through the Thornveil (Scattered)
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 Flash (Preview) | 98% | $0.0027 | 3.7s | |
| DeepSeek V4.1 Flash (Reasoning, High) | 98% | $0.0014 | 9.8s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 97% | $0.0003 | 8.4s | |
| Claude Haiku 5.5 (Reasoning, Low) | 96% | $0.0009 | 3.1s | |
| Xiaomi MIMO v2.6 Pro | 98% | $0.0013 | 20.3s | |
| Claude Haiku 5.5 (Adaptive) | 97% | $0.0014 | 8.2s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 96% | $0.0009 | 3.2s | |
| Xiaomi MIMO v2.5 | 96% | $0.0029 | 10.8s | |
| Xiaomi MIMO v2.6 Flash | 96% | $0.0004 | 16.7s | |
| Gemma 4 31B | 98% | $0.0007 | 26.6s | |
| DeepSeek V4 Flash | 95% | $0.0003 | 7.1s | |
| Mistral Medium 3.1 | 96% | $0.0025 | 5.1s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 95% | $0.0025 | 1.5s | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 99% | $0.010 | 2.6s | |
| Qwen 3.5 Plus (2026-02-15) | 97% | $0.0029 | 11.0s | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 99% | $0.011 | 2.9s | |
| Z.AI GLM 5 Turbo | 98% | $0.0061 | 13.8s | |
| Claude Haiku 4.5 | 97% | $0.0071 | 4.3s | |
| Z.AI GLM 5.2 (Reasoning, High) | 99% | $0.0067 | 18.2s | |
| GPT-6 Luna (Reasoning, Medium) | 96% | $0.0007 | 14.1s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Gemini 3.6 Flash (Reasoning, Minimal) | 99% | 100% | 98% | |
| Claude Opus 4.6 (Reasoning) | 99% | 100% | 98% | |
| Z.AI GLM 5.1 | 99% | 99% | 98% | |
| Claude Opus 4.8 (Reasoning) | 98% | 100% | 98% | |
| Z.AI GLM 5.2 (Reasoning, High) | 99% | 99% | 98% | |
| Grok 4.5 (Reasoning, High) | 99% | 99% | 98% | |
| Gemini 4 Argon (Reasoning, Medium) | 99% | 99% | 98% | |
| Claude Opus 4.8 (Reasoning, Low) | 99% | 99% | 98% | |
| Claude Sonnet 5 | 99% | 99% | 98% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 99% | 99% | 98% | |
| Muse Spark 1.1 (Reasoning, Medium) | 98% | 100% | 98% | |
| Muse Spark 1.2 (Reasoning, Medium) | 99% | 99% | 98% | |
| GPT-5.6 Terra (Reasoning, Medium) | 98% | 99% | 98% | |
| Aion 3.5 (Reasoning, High) | 99% | 99% | 98% | |
| Gemini 3.5 Flash (Reasoning) | 99% | 99% | 98% | |
| Grok 4.6 (Reasoning, High) | 99% | 99% | 98% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 99% | 99% | 98% | |
| Claude Opus 5.5 (Reasoning) | 99% | 99% | 98% | |
| Claude Sonnet 5 (Reasoning, Low) | 98% | 99% | 97% | |
| GPT-5.6 Sol | 98% | 99% | 97% | |
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 5.3 Flash (Reasoning, Low) | 97% | $0.0003 | 8.4s | 96% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 99% | $0.010 | 2.6s | 98% | |
| Gemini 3 Flash (Preview) | 98% | $0.0027 | 3.7s | 95% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 99% | $0.011 | 2.9s | 98% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 98% | $0.0014 | 9.8s | 95% | |
| Claude Haiku 5.5 (Reasoning, Low) | 96% | $0.0009 | 3.1s | 95% | |
| Z.AI GLM 5 Turbo | 98% | $0.0061 | 13.8s | 97% | |
| Z.AI GLM 5.2 (Reasoning, High) | 99% | $0.0067 | 18.2s | 98% | |
| Xiaomi MIMO v2.6 Pro | 98% | $0.0013 | 20.3s | 96% | |
| Claude Haiku 4.5 | 97% | $0.0071 | 4.3s | 97% | |
| Gemma 4 31B | 98% | $0.0007 | 26.6s | 97% | |
| Claude Haiku 5.5 (Adaptive) | 97% | $0.0014 | 8.2s | 95% | |
| Qwen 3.5 Plus (2026-02-15) | 97% | $0.0029 | 11.0s | 96% | |
| Mistral Medium 3.1 | 96% | $0.0025 | 5.1s | 96% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 96% | $0.0009 | 3.2s | 94% | |
| Gemini 4 Argon (Reasoning, Medium) | 99% | $0.013 | 5.3s | 98% | |
| Mistral Medium 3.5 (Reasoning) | 97% | $0.0094 | 3.4s | 97% | |
| Muse Spark 1.1 (Reasoning, Minimal) | 98% | $0.0082 | 7.3s | 96% | |
| GPT-5.6 Luna | 96% | $0.0041 | 5.1s | 95% | |
| DeepSeek V4 Flash | 95% | $0.0003 | 7.1s | 94% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 88.3% | Accuracy | ||
| 98.7% | Precision | ||
| 98.0% | Recall | ||
| 100.0% | Structural validity |
Medium: The Hollow (Inferred)
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 | ||
|---|---|---|---|---|
| Claude Haiku 5.5 (Reasoning, Low) | 97% | $0.0008 | 2.9s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 97% | $0.0008 | 2.8s | |
| GPT-6 Luna | 96% | $0.0003 | 4.5s | |
| Z.AI GLM 5.3 Flash (Reasoning, Low) | 94% | $0.0003 | 7.9s | |
| Gemini 3.5 Flash Lite (Reasoning) | 97% | $0.0024 | 1.4s | |
| Gemini 3.1 Flash Lite (Reasoning) | 96% | $0.0016 | 1.7s | |
| DeepSeek V4 Flash | 96% | $0.0003 | 7.0s | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 97% | $0.0023 | 1.6s | |
| Claude Haiku 5.5 (Adaptive) | 96% | $0.0013 | 7.0s | |
| Gemini 3.1 Flash Lite | 96% | $0.0016 | 1.8s | |
| Gemini 3.1 Flash Lite (Preview) | 96% | $0.0016 | 2.2s | |
| Gemma 4 31B | 97% | $0.0007 | 14.8s | |
| Laguna S 2.1 | 95% | $0.0003 | 9.6s | |
| GPT-6 Luna (Reasoning, Medium) | 96% | $0.0007 | 10.7s | |
| Gemini 2.5 Flash Lite | 92% | $0.0004 | 1.9s | |
| Mistral Large 3 | 97% | $0.0025 | 6.6s | |
| GPT-6 Luna (Reasoning, High) | 97% | $0.0010 | 20.1s | |
| Qwen 3.5 Plus (2026-02-15) | 97% | $0.0027 | 8.7s | |
| Ministral 3 8B | 94% | $0.0006 | 2.6s | |
| Gemini 2.5 Flash | 95% | $0.0019 | 2.2s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 4.8 (Reasoning, Low) | 99% | 99% | 99% | |
| Claude Opus 4.8 (Reasoning) | 99% | 99% | 99% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 99% | 99% | 99% | |
| GPT-5 | 99% | 100% | 98% | |
| Gemini 4 Argon (Reasoning, Medium) | 98% | 100% | 98% | |
| Claude Opus 5.5 (Reasoning) | 99% | 99% | 98% | |
| Claude Opus 4.7 (Reasoning) | 99% | 99% | 98% | |
| Claude Opus 4.6 | 99% | 99% | 98% | |
| Claude Sonnet 4.6 | 98% | 100% | 98% | |
| Qwen 3.8 Max (Reasoning, XHigh) | 99% | 99% | 98% | |
| GPT-5.1 | 98% | 99% | 98% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 99% | 99% | 98% | |
| Grok 4.6 (Reasoning, High) | 98% | 99% | 97% | |
| Grok 4.7 (Reasoning, High) | 99% | 99% | 97% | |
| Claude Opus 4.7 | 99% | 99% | 97% | |
| Claude Opus 4.6 (Reasoning) | 99% | 98% | 97% | |
| Gemini 3.6 Flash (Reasoning) | 98% | 99% | 97% | |
| Kimi K3 (Reasoning, Low) | 98% | 99% | 97% | |
| Ember-1 (Reasoning, Max) | 98% | 99% | 97% | |
| Kimi K3 (Reasoning, High) | 98% | 99% | 97% | |
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, Low) | 97% | $0.0008 | 2.9s | 96% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 97% | $0.0008 | 2.8s | 96% | |
| Gemini 3.5 Flash Lite (Reasoning, Minimal) | 97% | $0.0023 | 1.6s | 96% | |
| Gemini 3.5 Flash Lite (Reasoning) | 97% | $0.0024 | 1.4s | 96% | |
| Gemini 3.1 Flash Lite (Reasoning) | 96% | $0.0016 | 1.7s | 95% | |
| Gemini 3.1 Flash Lite (Preview) | 96% | $0.0016 | 2.2s | 95% | |
| Gemini 3.1 Flash Lite | 96% | $0.0016 | 1.8s | 95% | |
| GPT-6 Luna | 96% | $0.0003 | 4.5s | 94% | |
| Mistral Large 3 | 97% | $0.0025 | 6.6s | 96% | |
| DeepSeek V4 Flash | 96% | $0.0003 | 7.0s | 93% | |
| Qwen 3.5 Plus (2026-02-15) | 97% | $0.0027 | 8.7s | 96% | |
| Mistral Large 4.0 | 96% | $0.0024 | 5.6s | 95% | |
| GPT-6 Luna (Reasoning, Medium) | 96% | $0.0007 | 10.7s | 95% | |
| Gemma 4 31B | 97% | $0.0007 | 14.8s | 95% | |
| Ministral 3 8B | 94% | $0.0006 | 2.6s | 92% | |
| Laguna S 2.1 | 95% | $0.0003 | 9.6s | 94% | |
| Gemini 2.5 Flash | 95% | $0.0019 | 2.2s | 93% | |
| Claude Haiku 5.5 (Adaptive) | 96% | $0.0013 | 7.0s | 93% | |
| GPT-5.6 Luna | 95% | $0.0037 | 2.5s | 94% | |
| Ministral 8B | 93% | $0.0004 | 3.0s | 92% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 87.5% | Accuracy | ||
| 100.0% | Precision | ||
| 97.9% | Recall | ||
| 100.0% | Structural validity |
Long: The Spire of Echoes (Dense)
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 5.3 Flash (Reasoning, Low) | 98% | $0.0004 | 12.3s | |
| DeepSeek V4 Flash | 91% | $0.0005 | 11.2s | |
| Gemini 3 Flash (Preview) | 98% | $0.0033 | 5.4s | |
| DeepSeek V4.1 Flash (Reasoning, High) | 97% | $0.0015 | 10.0s | |
| Claude Haiku 5.5 (Reasoning, Low) | 96% | $0.0012 | 4.2s | |
| Claude Haiku 5.5 (Adaptive) | 97% | $0.0019 | 10.4s | |
| Claude Haiku 5.5 (Reasoning, Medium) | 96% | $0.0012 | 4.4s | |
| Mistral Medium 3.1 | 97% | $0.0035 | 7.5s | |
| Gemini 2.5 Flash | 93% | $0.0033 | 3.6s | |
| Xiaomi MIMO v2.5 | 97% | $0.0042 | 16.1s | |
| GPT-6 Luna | 95% | $0.0005 | 8.6s | |
| Qwen 3.5 Plus (2026-02-15) | 97% | $0.0041 | 14.9s | |
| Xiaomi MIMO v2.6 Pro | 98% | $0.0020 | 31.1s | |
| Gemini 3.1 Flash Lite (Preview) | 94% | $0.0022 | 2.3s | |
| Gemini 3.7 Flash (Reasoning, Medium) | 98% | $0.013 | 7.5s | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 97% | $0.012 | 4.3s | |
| GPT-5.6 Luna | 96% | $0.0063 | 3.8s | |
| GPT-5.4 Mini (Reasoning, Low) | 95% | $0.0060 | 4.5s | |
| Xiaomi MIMO v2.6 Flash | 97% | $0.0006 | 34.0s | |
| Gemini 3.1 Flash Lite (Reasoning) | 94% | $0.0023 | 2.7s | |
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
| Score | Consistency | Stability | ||
|---|---|---|---|---|
| Claude Opus 4.8 (Reasoning) | 99% | 100% | 99% | |
| Claude Opus 4.8 (Reasoning, Low) | 99% | 99% | 98% | |
| Z.AI GLM 5.3 (Reasoning, Max) | 99% | 99% | 98% | |
| Gemini 3.8 Flash (Reasoning, Medium) | 99% | 100% | 98% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 98% | 99% | 98% | |
| Claude Sonnet 5.5 (Reasoning) | 98% | 100% | 98% | |
| Claude Opus 5 | 98% | 100% | 98% | |
| Muse Spark 1.3 (Reasoning, Medium) | 98% | 100% | 98% | |
| Gemini 3.5 Flash (Reasoning) | 99% | 99% | 98% | |
| Claude Opus 4 | 98% | 100% | 98% | |
| Claude Opus 5 (Reasoning) | 98% | 100% | 98% | |
| Gemini 3 Flash (Preview, Reasoning) | 99% | 99% | 98% | |
| Claude Opus 5 (Reasoning, Low) | 98% | 100% | 98% | |
| Claude Opus 4.5 | 98% | 100% | 98% | |
| Ember-1 (Reasoning, Max) | 99% | 99% | 98% | |
| Claude Opus 4.6 | 98% | 100% | 98% | |
| Muse Spark 1.1 (Reasoning, Medium) | 98% | 99% | 98% | |
| Z.AI GLM 5.3 Flash (Reasoning, Max) | 98% | 99% | 97% | |
| Claude Opus 5.5 (Reasoning) | 99% | 99% | 97% | |
| Kimi K3 (Reasoning, High) | 99% | 99% | 97% | |
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 5.3 Flash (Reasoning, Low) | 98% | $0.0004 | 12.3s | 97% | |
| Gemini 3 Flash (Preview) | 98% | $0.0033 | 5.4s | 97% | |
| Claude Haiku 5.5 (Reasoning, Low) | 96% | $0.0012 | 4.2s | 96% | |
| DeepSeek V4.1 Flash (Reasoning, High) | 97% | $0.0015 | 10.0s | 96% | |
| Claude Haiku 5.5 (Adaptive) | 97% | $0.0019 | 10.4s | 97% | |
| Claude Haiku 5.5 (Reasoning, Medium) | 96% | $0.0012 | 4.4s | 95% | |
| Mistral Medium 3.1 | 97% | $0.0035 | 7.5s | 96% | |
| Qwen 3.5 Plus (2026-02-15) | 97% | $0.0041 | 14.9s | 96% | |
| Xiaomi MIMO v2.5 | 97% | $0.0042 | 16.1s | 96% | |
| Gemini 3.7 Flash (Reasoning, Medium) | 98% | $0.013 | 7.5s | 98% | |
| GPT-6 Luna | 95% | $0.0005 | 8.6s | 93% | |
| Grok 4.20 | 96% | $0.0064 | 7.8s | 95% | |
| Gemini 3.1 Flash Lite (Preview) | 94% | $0.0022 | 2.3s | 93% | |
| Xiaomi MIMO v2.6 Pro | 98% | $0.0020 | 31.1s | 96% | |
| Gemini 3.1 Flash Lite (Reasoning) | 94% | $0.0023 | 2.7s | 93% | |
| GPT-5.6 Luna | 96% | $0.0063 | 3.8s | 94% | |
| GPT-5.4 Mini (Reasoning, Low) | 95% | $0.0060 | 4.5s | 94% | |
| Gemini 3.5 Flash (Reasoning, Minimal) | 97% | $0.012 | 4.3s | 96% | |
| Gemini 3.6 Flash (Reasoning, Minimal) | 97% | $0.013 | 3.6s | 97% | |
| Xiaomi MIMO v2.6 Flash | 97% | $0.0006 | 34.0s | 96% | |
| Median | Evaluator | Top 3 | Flop 3 |
|---|---|---|---|
| 85.4% | Accuracy | ||
| 100.0% | Precision | ||
| 99.6% | Recall | ||
| 100.0% | Structural validity |