Run #2407
success · fetched 2026-09-20 12:00:26 · 1.39 MB raw HTML · 130 models
Top quality: Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) (53.4 pts)
Cost/task vs quality?
130 models · 15 on the Pareto frontier · intelligence quality vs Cost per Task
| #? | Pareto? | Model? | Released? | Cost/task? | Time/task? | $/Q? | Qual? | ΔTop? | Intel? | Agent? | Pen? | Score? |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | ✓ | Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) Anthropic |
2026-09-01 | $7.63 | 12.3m | 0.1430 | 53.4 | 0.0 | 53.4 | - | 28.8 | 53.4 |
| 2 | ✓ | Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) Anthropic |
2026-09-01 | $5.98 | 11.3m | 0.1124 | 53.2 | -0.2 | 53.2 | - | 27.8 | 53.2 |
| 3 | ✓ | GPT-6 Astra (max) OpenAI |
2026-09-03 | $3.26 | 7.60m | 0.0618 | 52.7 | -0.7 | 52.7 | - | 25.1 | 52.7 |
| 4 | ✓ | GPT-6 Astra (xhigh) OpenAI |
2026-09-03 | $2.31 | 5.22m | 0.0441 | 52.4 | -1.0 | 52.4 | - | 23.6 | 52.4 |
| 5 | Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) Anthropic |
2026-09-01 | $3.91 | 7.36m | 0.0765 | 51.2 | -2.2 | 51.2 | - | 25.9 | 51.2 | |
| 6 | ✓ | GPT-6 Astra (high) OpenAI |
2026-09-03 | $1.73 | 3.74m | 0.0339 | 50.9 | -2.4 | 50.9 | - | 22.4 | 50.9 |
| 7 | Claude Opus 5 (Adaptive Reasoning, Max Effort) Anthropic |
2026-07-24 | $5.86 | 14.6m | 0.1154 | 50.8 | -2.6 | 50.8 | - | 27.7 | 50.8 | |
| 8 | Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) Anthropic |
2026-07-24 | $4.88 | 12.0m | 0.0982 | 49.7 | -3.7 | 49.7 | - | 26.9 | 49.7 | |
| 9 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) Anthropic |
2026-06-09 | $8.75 | 11.4m | 0.1762 | 49.6 | -3.7 | 49.6 | - | 29.4 | 49.6 | |
| 10 | ✓ | GPT-6 Astra (medium) OpenAI |
2026-09-03 | $1.54 | 2.99m | 0.0311 | 49.6 | -3.8 | 49.6 | - | 21.9 | 49.6 |
| 11 | Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback) Anthropic |
2026-09-01 | $2.98 | 5.60m | 0.0610 | 48.9 | -4.4 | 48.9 | - | 24.7 | 48.9 | |
| 12 | Claude Opus 5 (Adaptive Reasoning, High Effort) Anthropic |
2026-07-24 | $3.61 | 9.06m | 0.0751 | 48.1 | -5.2 | 48.1 | - | 25.6 | 48.1 | |
| 13 | Muse Spark 1.3 (max) Meta |
2026-09-02 | $1.60 | 5.02m | 0.0334 | 48.1 | -5.3 | 48.1 | - | 22.1 | 48.1 | |
| 14 | GPT-5.6 Sol (max) OpenAI |
2026-07-09 | $1.99 | 7.93m | 0.0423 | 47.0 | -6.4 | 47.0 | - | 23.0 | 47.0 | |
| 15 | Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback) Anthropic |
2026-09-01 | $2.37 | 4.59m | 0.0506 | 46.8 | -6.5 | 46.8 | - | 23.7 | 46.8 | |
| 16 | ✓ | GPT-6 Astra (low) OpenAI |
2026-09-03 | $0.818 | 1.32m | 0.0179 | 45.8 | -7.6 | 45.8 | - | 19.1 | 45.8 |
| 17 | Qwen3.8 Max (0902) Alibaba |
2026-09-02 | $5.41 | 40.0m | 0.1191 | 45.4 | -7.9 | 45.4 | - | 27.3 | 45.4 | |
| 18 | Muse Spark 1.3 (xhigh) Meta |
2026-09-02 | $1.37 | 3.73m | 0.0303 | 45.1 | -8.3 | 45.1 | - | 21.4 | 45.1 | |
| 19 | Claude Opus 5 (Adaptive Reasoning, Medium Effort) Anthropic |
2026-07-24 | $2.19 | 5.78m | 0.0488 | 44.8 | -8.5 | 44.8 | - | 23.4 | 44.8 | |
| 20 | GLM-5.3 (max) Z AI |
2026-08-18 | $2.01 | 14.4m | 0.0448 | 44.8 | -8.6 | 44.8 | - | 23.0 | 44.8 | |
| 21 | Grok 4.6 (high) SpaceXAI |
2026-08-12 | $1.86 | 10.2m | 0.0420 | 44.3 | -9.0 | 44.3 | - | 22.7 | 44.3 | |
| 22 | Grok 4.6 (xhigh) SpaceXAI |
2026-08-12 | $2.32 | 11.1m | 0.0526 | 44.2 | -9.2 | 44.2 | - | 23.7 | 44.2 | |
| 23 | GPT-5.6 Sol (xhigh) OpenAI |
2026-07-09 | $1.18 | 5.01m | 0.0269 | 44.0 | -9.3 | 44.0 | - | 20.7 | 44.0 | |
| 24 | ✓ | Step 5 Preview StepFun |
2026-09-18 | $0.715 | 12.2m | 0.0163 | 43.7 | -9.6 | 43.7 | - | 18.5 | 43.7 |
| 25 | Kimi K3 (max) Kimi |
2026-07-16 | $2.00 | 18.9m | 0.0459 | 43.6 | -9.8 | 43.6 | - | 23.0 | 43.6 | |
| 26 | Grok 4.6 (medium) SpaceXAI |
2026-08-12 | $1.50 | 8.66m | 0.0349 | 42.8 | -10.5 | 42.8 | - | 21.8 | 42.8 | |
| 27 | GPT-5.6 Sol (high) OpenAI |
2026-07-09 | $0.808 | 3.46m | 0.0191 | 42.3 | -11.0 | 42.3 | - | 19.1 | 42.3 | |
| 28 | GPT-5.6 Terra (max) OpenAI |
2026-07-09 | $1.40 | 6.90m | 0.0332 | 42.1 | -11.3 | 42.1 | - | 21.5 | 42.1 | |
| 29 | ✓ | GLM 5.3 Flash Z AI |
2026-08-26 | $0.253 | 9.43m | 0.0061 | 41.8 | -11.5 | 41.8 | - | 14.0 | 41.8 |
| 30 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) Anthropic |
2026-05-28 | $4.08 | 13.7m | 0.0977 | 41.8 | -11.6 | 41.8 | - | 26.1 | 41.8 | |
| 31 | Gemini 3.8 Flash (high) |
2026-09-02 | $1.24 | 3.77m | 0.0304 | 40.9 | -12.4 | 40.9 | - | 20.9 | 40.9 | |
| 32 | Qwen3.8 Max Alibaba |
2026-08-03 | $2.67 | 22.1m | 0.0665 | 40.2 | -13.2 | 40.2 | - | 24.3 | 40.2 | |
| 33 | Qwen3.8 2.4T A95B Alibaba |
2026-08-12 | $2.16 | 23.9m | 0.0541 | 39.9 | -13.5 | 39.9 | - | 23.3 | 39.9 | |
| 34 | Qwen3.8-Flash-Next Alibaba |
2026-08-26 | $0.372 | 23.2m | 0.0093 | 39.8 | -13.5 | 39.8 | - | 15.7 | 39.8 | |
| 35 | Gemini 3.8 Flash (medium) |
2026-09-02 | $0.931 | - | 0.0234 | 39.8 | -13.6 | 39.8 | - | 19.7 | 39.8 | |
| 36 | Muse Spark 1.2 (xhigh) Meta |
2026-08-05 | $0.975 | 3.72m | 0.0246 | 39.6 | -13.8 | 39.6 | - | 19.9 | 39.6 | |
| 37 | DeepSeek V4.1 Flash (Reasoning, Max Effort) DeepSeek |
2026-09-10 | $0.265 | 5.40m | 0.0067 | 39.5 | -13.9 | 39.5 | - | 14.2 | 39.5 | |
| 38 | Claude Opus 5 (Adaptive Reasoning, Low Effort) Anthropic |
2026-07-24 | $1.10 | 2.88m | 0.0279 | 39.4 | -14.0 | 39.4 | - | 20.4 | 39.4 | |
| 39 | GPT-5.6 Sol (medium) OpenAI |
2026-07-09 | $0.505 | 2.19m | 0.0129 | 39.2 | -14.1 | 39.2 | - | 17.0 | 39.2 | |
| 40 | Gemini 3.7 Flash (high) |
2026-08-13 | $0.925 | 2.88m | 0.0237 | 39.1 | -14.3 | 39.1 | - | 19.7 | 39.1 | |
| 41 | Grok 4.5 (high) SpaceXAI |
2026-07-08 | $1.04 | 7.64m | 0.0267 | 38.8 | -14.5 | 38.8 | - | 20.2 | 38.8 | |
| 42 | GPT-5.5 (xhigh) OpenAI |
2026-04-23 | $2.63 | 4.06m | 0.0687 | 38.4 | -15.0 | 38.4 | - | 24.2 | 38.4 | |
| 43 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) Anthropic |
2026-06-30 | $5.09 | 16.8m | 0.1334 | 38.2 | -15.2 | 38.2 | - | 27.1 | 38.2 | |
| 44 | GPT-5.6 Terra (xhigh) OpenAI |
2026-07-09 | $0.632 | 4.10m | 0.0166 | 38.0 | -15.4 | 38.0 | - | 18.0 | 38.0 | |
| 45 | ✓ | GPT-5.6 Luna (max) OpenAI |
2026-07-09 | $0.178 | 4.23m | 0.0048 | 37.3 | -16.0 | 37.3 | - | 12.5 | 37.3 |
| 46 | GPT-5.5 (high) OpenAI |
2026-04-23 | $1.54 | 2.81m | 0.0417 | 37.0 | -16.4 | 37.0 | - | 21.9 | 37.0 | |
| 47 | DeepSeek V4 Pro 0813 (Reasoning, Max Effort) DeepSeek |
2026-08-13 | $0.674 | 8.66m | 0.0187 | 36.0 | -17.4 | 36.0 | - | 18.3 | 36.0 | |
| 48 | Grok 4.6 (low) SpaceXAI |
2026-08-12 | $0.475 | 3.16m | 0.0135 | 35.1 | -18.2 | 35.1 | - | 16.8 | 35.1 | |
| 49 | DeepSeek V4 Flash Vision (Reasoning, Max Effort) DeepSeek |
2026-08-21 | $0.314 | 4.20m | 0.0090 | 34.8 | -18.5 | 34.8 | - | 15.0 | 34.8 | |
| 50 | ✓ | GPT-5.6 Luna (xhigh) OpenAI |
2026-07-09 | $0.0853 | 2.78m | 0.0025 | 34.6 | -18.8 | 34.6 | - | 9.3 | 34.6 |
| 51 | Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort) Anthropic |
2026-06-30 | $2.87 | 9.74m | 0.0835 | 34.4 | -19.0 | 34.4 | - | 24.6 | 34.4 | |
| 52 | DeepSeek V4 Flash 0731 (Reasoning, Max Effort) DeepSeek |
2026-07-31 | $0.220 | 4.12m | 0.0064 | 34.3 | -19.0 | 34.3 | - | 13.4 | 34.3 | |
| 53 | GPT-5.6 Terra (high) OpenAI |
2026-07-09 | $0.338 | 2.07m | 0.0099 | 34.2 | -19.1 | 34.2 | - | 15.3 | 34.2 | |
| 54 | Gemini 3.6 Flash (high) |
2026-07-21 | $0.929 | 3.13m | 0.0273 | 34.0 | -19.4 | 34.0 | - | 19.7 | 34.0 | |
| 55 | GPT-5.5 (medium) OpenAI |
2026-04-23 | $0.902 | 1.64m | 0.0267 | 33.8 | -19.6 | 33.8 | - | 19.6 | 33.8 | |
| 56 | Muse Spark 1.1 (xhigh) Meta |
2026-07-09 | $1.38 | - | 0.0409 | 33.7 | -19.6 | 33.7 | - | 21.4 | 33.7 | |
| 57 | GLM-5.2 (max) Z AI |
2026-06-16 | $0.965 | 11.9m | 0.0286 | 33.7 | -19.6 | 33.7 | - | 19.8 | 33.7 | |
| 58 | Qwen3.8 27B (xhigh) Alibaba |
2026-08-14 | $0.820 | 22.0m | 0.0243 | 33.7 | -19.7 | 33.7 | - | 19.1 | 33.7 | |
| 59 | GPT-5.6 Sol (low) OpenAI |
2026-07-09 | $0.261 | 1.01m | 0.0078 | 33.5 | -19.9 | 33.5 | - | 14.2 | 33.5 | |
| 60 | Gemini 3.5 Flash (high) |
2026-05-19 | $1.56 | 3.99m | 0.0479 | 32.6 | -20.8 | 32.6 | - | 21.9 | 32.6 | |
| 61 | ✓ | GPT-5.6 Luna (high) OpenAI |
2026-07-09 | $0.0440 | 1.64m | 0.0014 | 32.1 | -21.2 | 32.1 | - | 6.4 | 32.1 |
| 62 | Claude Sonnet 5 (Adaptive Reasoning, High Effort) Anthropic |
2026-06-30 | $1.79 | 7.33m | 0.0566 | 31.7 | -21.7 | 31.7 | - | 22.5 | 31.7 | |
| 63 | DeepSeek V4 Pro 0424 (Reasoning, Max Effort) DeepSeek |
2026-04-24 | $0.122 | 6.93m | 0.0040 | 30.4 | -22.9 | 30.4 | - | 10.8 | 30.4 | |
| 64 | GPT-5.6 Terra (medium) OpenAI |
2026-07-09 | $0.183 | 1.09m | 0.0061 | 30.1 | -23.3 | 30.1 | - | 12.6 | 30.1 | |
| 65 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) Anthropic |
2026-02-17 | $2.49 | 25.0m | 0.0827 | 30.1 | -23.3 | 30.1 | - | 24.0 | 30.1 | |
| 66 | Gemini 3.1 Pro Preview |
2026-02-19 | $0.675 | 2.56m | 0.0227 | 29.7 | -23.6 | 29.7 | - | 18.3 | 29.7 | |
| 67 | Qwen3.7 Max Alibaba |
2026-05-19 | $1.15 | 2.37m | 0.0389 | 29.5 | -23.9 | 29.5 | - | 20.6 | 29.5 | |
| 68 | MiniMax-M3 MiniMax |
2026-06-01 | $0.508 | 4.12m | 0.0174 | 29.2 | -24.1 | 29.2 | - | 17.1 | 29.2 | |
| 69 | Claude Sonnet 5 (Adaptive Reasoning, Medium Effort) Anthropic |
2026-06-30 | $0.999 | 4.78m | 0.0356 | 28.1 | -25.3 | 28.1 | - | 20.0 | 28.1 | |
| 70 | Qwen3.8 27B (medium) Alibaba |
2026-08-14 | $0.903 | 17.9m | 0.0328 | 27.6 | -25.8 | 27.6 | - | 19.6 | 27.6 | |
| 71 | GPT-5.6 Terra (low) OpenAI |
2026-07-09 | $0.144 | 49s | 0.0053 | 27.5 | -25.9 | 27.5 | - | 11.6 | 27.5 | |
| 72 | Kimi K2.6 Kimi |
2026-04-20 | $0.800 | 21.9m | 0.0296 | 27.0 | -26.4 | 27.0 | - | 19.0 | 27.0 | |
| 73 | Quasar 438B (max, based on GLM-5.2) Multiverse Computing |
2026-08-10 | $2.02 | 6.42m | 0.0757 | 26.7 | -26.6 | 26.7 | - | 23.1 | 26.7 | |
| 74 | Qwen3.8 27B (low) Alibaba |
2026-08-14 | $0.834 | 14.8m | 0.0318 | 26.2 | -27.2 | 26.2 | - | 19.2 | 26.2 | |
| 75 | GLM-5.1 (Reasoning) Z AI |
2026-04-07 | $0.922 | 14.8m | 0.0354 | 26.1 | -27.3 | 26.1 | - | 19.6 | 26.1 | |
| 76 | GPT-5.5 Instant (June 2026) OpenAI |
2026-06-25 | $0.691 | 39s | 0.0266 | 26.0 | -27.3 | 26.0 | - | 18.4 | 26.0 | |
| 77 | MiMo-V2.5-Pro Xiaomi |
2026-04-22 | $0.0541 | 8.94m | 0.0021 | 26.0 | -27.4 | 26.0 | - | 7.3 | 26.0 | |
| 78 | Kimi K2.7 Code Kimi |
2026-06-12 | $0.541 | 8.13m | 0.0210 | 25.8 | -27.5 | 25.8 | - | 17.3 | 25.8 | |
| 79 | Hy3 Tencent |
2026-07-06 | $0.0743 | 9.28m | 0.0029 | 25.3 | -28.1 | 25.3 | - | 8.7 | 25.3 | |
| 80 | Qwen3.7 Plus Alibaba |
2026-06-01 | $0.325 | 7.89m | 0.0129 | 25.2 | -28.2 | 25.2 | - | 15.1 | 25.2 | |
| 81 | ✓ | GPT-5.6 Luna (medium) OpenAI |
2026-07-09 | $0.0156 | 34s | 0.0006 | 25.0 | -28.3 | 25.0 | - | 1.9 | 25.0 |
| 82 | Inkling (xhigh) Thinking Machines |
2026-07-15 | $0.607 | 6.97m | 0.0243 | 25.0 | -28.4 | 25.0 | - | 17.8 | 25.0 | |
| 83 | Grok 4.3 (high) SpaceXAI |
2026-04-30 | $0.165 | 2.95m | 0.0066 | 24.9 | -28.5 | 24.9 | - | 12.2 | 24.9 | |
| 84 | Claude Sonnet 5 (Adaptive Reasoning, Low Effort) Anthropic |
2026-06-30 | $0.509 | 2.63m | 0.0210 | 24.3 | -29.1 | 24.3 | - | 17.1 | 24.3 | |
| 85 | DeepSeek V4 Flash 0420 (Reasoning, Max Effort) DeepSeek |
2026-04-24 | $0.118 | - | 0.0049 | 24.2 | -29.2 | 24.2 | - | 10.7 | 24.2 | |
| 86 | GPT-5.4 mini (xhigh) OpenAI |
2026-03-17 | $0.410 | 4.34m | 0.0170 | 24.1 | -29.3 | 24.1 | - | 16.1 | 24.1 | |
| 87 | Nemotron 3 Ultra 550B A55B (Reasoning) NVIDIA |
2026-06-04 | $0.579 | 2.78m | 0.0253 | 22.9 | -30.4 | 22.9 | - | 17.6 | 22.9 | |
| 88 | MiniMax-M2.7 MiniMax |
2026-03-18 | $0.102 | 5.32m | 0.0045 | 22.8 | -30.6 | 22.8 | - | 10.1 | 22.8 | |
| 89 | Gemini 3.5 Flash-Lite |
2026-07-21 | $0.124 | 46s | 0.0056 | 22.2 | -31.2 | 22.2 | - | 10.9 | 22.2 | |
| 90 | Qwen3.6 27B (Reasoning) Alibaba |
2026-04-22 | $0.621 | 8.78m | 0.0290 | 21.4 | -31.9 | 21.4 | - | 17.9 | 21.4 | |
| 91 | ✓ | GPT-5.6 Luna (low) OpenAI |
2026-07-09 | $0.00983 | 19s | 0.0005 | 21.0 | -32.3 | 21.0 | - | 0.0 | 21.0 |
| 92 | GPT-5.6 Terra (Non-reasoning) OpenAI |
2026-07-09 | $0.140 | 37s | 0.0067 | 20.8 | -32.6 | 20.8 | - | 11.5 | 20.8 | |
| 93 | GPT-5.4 nano (xhigh) OpenAI |
2026-03-17 | $0.183 | 6.81m | 0.0088 | 20.7 | -32.6 | 20.7 | - | 12.6 | 20.7 | |
| 94 | Claude 4.5 Sonnet (Reasoning) Anthropic |
2025-09-29 | $0.557 | 5.60m | 0.0269 | 20.7 | -32.7 | 20.7 | - | 17.5 | 20.7 | |
| 95 | LongCat 2.0 LongCat |
2026-06-29 | $0.0590 | - | 0.0031 | 19.1 | -34.2 | 19.1 | - | 7.7 | 19.1 | |
| 96 | Qwen3.5 397B A17B (Reasoning) Alibaba |
2026-02-16 | $0.475 | 3.24m | 0.0258 | 18.4 | -34.9 | 18.4 | - | 16.8 | 18.4 | |
| 97 | Qwen3.6 35B A3B (Reasoning) Alibaba |
2026-04-16 | $0.475 | 5.52m | 0.0261 | 18.2 | -35.1 | 18.2 | - | 16.8 | 18.2 | |
| 98 | Muse Glimmer (high) Meta |
2026-08-10 | $0.0551 | 2.54m | 0.0032 | 17.5 | -35.9 | 17.5 | - | 7.4 | 17.5 | |
| 99 | Claude 4.5 Haiku (Reasoning) Anthropic |
2025-10-15 | $0.208 | 2.73m | 0.0123 | 16.9 | -36.5 | 16.9 | - | 13.2 | 16.9 | |
| 100 | GPT-5 mini (high) OpenAI |
2025-08-07 | $0.0535 | 3.05m | 0.0032 | 16.8 | -36.6 | 16.8 | - | 7.3 | 16.8 |