Run #3287
success · fetched 2026-10-28 11:00:56 · 1.52 MB raw HTML · 72 models
Top quality: Claude Opus 5.5 (Max, Default Fallback) (58.4 pts)
Cost/task vs quality?
72 models · 16 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 Opus 5.5 (Max, Default Fallback) Anthropic |
2026-09-22 | $10.0 | 18.9m | 0.1718 | 58.4 | 0.0 | 58.4 | - | 30.0 | 58.4 |
| 2 | ✓ | Claude Opus 5.5 (Xhigh, Default Fallback) Anthropic |
2026-09-22 | $6.05 | 13.0m | 0.1061 | 57.0 | -1.4 | 57.0 | - | 27.8 | 57.0 |
| 3 | GPT-6 Astra (Max) OpenAI |
2026-09-03 | $6.24 | 11.9m | 0.1098 | 56.9 | -1.6 | 56.9 | - | 28.0 | 56.9 | |
| 4 | ✓ | GPT-6 Astra (Xhigh) OpenAI |
2026-09-03 | $3.66 | 6.52m | 0.0662 | 55.3 | -3.2 | 55.3 | - | 25.6 | 55.3 |
| 5 | ✓ | GPT-6 Astra (High) OpenAI |
2026-09-03 | $3.24 | 6.21m | 0.0590 | 54.8 | -3.6 | 54.8 | - | 25.1 | 54.8 |
| 6 | ✓ | GPT-6.1 Sol (Max) OpenAI |
2026-09-29 | $1.27 | 14.3m | 0.0233 | 54.5 | -3.9 | 54.5 | - | 21.0 | 54.5 |
| 7 | Claude Sonnet 5.5 (Max, Default Fallback) Anthropic |
2026-09-28 | $10.0 | 22.1m | 0.1847 | 54.2 | -4.2 | 54.2 | - | 30.0 | 54.2 | |
| 8 | ✓ | GPT-6.1 Sol (Xhigh) OpenAI |
2026-09-29 | $0.764 | 7.27m | 0.0146 | 52.3 | -6.1 | 52.3 | - | 18.8 | 52.3 |
| 9 | Claude Opus 5.5 (High, Default Fallback) Anthropic |
2026-09-22 | $3.46 | 7.73m | 0.0670 | 51.7 | -6.7 | 51.7 | - | 25.4 | 51.7 | |
| 10 | GPT-6 Astra (Medium) OpenAI |
2026-09-03 | $2.73 | 5.06m | 0.0531 | 51.5 | -7.0 | 51.5 | - | 24.4 | 51.5 | |
| 11 | GPT-6.1 Terra (Max) OpenAI |
2026-10-26 | $0.961 | 10.9m | 0.0189 | 51.0 | -7.4 | 51.0 | - | 19.8 | 51.0 | |
| 12 | Gemini 4 Argon (High) |
2026-09-30 | $3.84 | 22.8m | 0.0762 | 50.4 | -8.0 | 50.4 | - | 25.8 | 50.4 | |
| 13 | ✓ | GPT-6.1 Sol (High) OpenAI |
2026-09-29 | $0.591 | 5.37m | 0.0118 | 50.2 | -8.2 | 50.2 | - | 17.7 | 50.2 |
| 14 | Claude Fable 5.1 (Xhigh, Default Fallback) Anthropic |
2026-09-01 | $10.9 | 15.8m | 0.2191 | 49.7 | -8.7 | 49.7 | - | 30.4 | 49.7 | |
| 15 | Claude Sonnet 5.5 (Xhigh, Default Fallback) Anthropic |
2026-09-28 | $4.09 | 11.5m | 0.0825 | 49.6 | -8.8 | 49.6 | - | 26.1 | 49.6 | |
| 16 | Claude Fable 5.1 (Max, Default Fallback) Anthropic |
2026-09-01 | $13.0 | 19.6m | 0.2661 | 49.0 | -9.4 | 49.0 | - | 31.2 | 49.0 | |
| 17 | Claude Opus 5.5 (Medium, Default Fallback) Anthropic |
2026-09-22 | $2.45 | 5.61m | 0.0510 | 48.1 | -10.3 | 48.1 | - | 23.9 | 48.1 | |
| 18 | Claude Fable 5.1 (High, Default Fallback) Anthropic |
2026-09-01 | $7.56 | 11.2m | 0.1608 | 47.0 | -11.4 | 47.0 | - | 28.8 | 47.0 | |
| 19 | ✓ | GPT-6.1 Sol (Medium) OpenAI |
2026-09-29 | $0.359 | 3.85m | 0.0078 | 46.1 | -12.3 | 46.1 | - | 15.6 | 46.1 |
| 20 | Kimi K3.1 Pro Kimi |
2026-10-23 | $3.68 | 25.1m | 0.0800 | 46.0 | -12.4 | 46.0 | - | 25.7 | 46.0 | |
| 21 | GPT-6.1 Terra (Xhigh) OpenAI |
2026-10-26 | $0.401 | 4.78m | 0.0089 | 45.0 | -13.5 | 45.0 | - | 16.0 | 45.0 | |
| 22 | Muse Wonder (Max) Meta |
2026-10-12 | $6.95 | 7.80m | 0.1605 | 43.3 | -15.1 | 43.3 | - | 28.4 | 43.3 | |
| 23 | GPT-6 Astra (Low) OpenAI |
2026-09-03 | $1.42 | 3.15m | 0.0331 | 43.0 | -15.4 | 43.0 | - | 21.5 | 43.0 | |
| 24 | Claude Fable 5.1 (Medium, Default Fallback) Anthropic |
2026-09-01 | $5.58 | 8.38m | 0.1299 | 43.0 | -15.4 | 43.0 | - | 27.5 | 43.0 | |
| 25 | ✓ | GPT-6.1 Terra (High) OpenAI |
2026-10-26 | $0.259 | 3.04m | 0.0061 | 42.3 | -16.1 | 42.3 | - | 14.1 | 42.3 |
| 26 | Claude Sonnet 5.5 (High, Default Fallback) Anthropic |
2026-09-28 | $1.64 | 5.53m | 0.0398 | 41.1 | -17.3 | 41.1 | - | 22.1 | 41.1 | |
| 27 | Claude Fable 5.1 (Low, Default Fallback) Anthropic |
2026-09-01 | $4.49 | 6.85m | 0.1166 | 38.5 | -19.9 | 38.5 | - | 26.5 | 38.5 | |
| 28 | ✓ | GPT-6.1 Terra (Medium) OpenAI |
2026-10-26 | $0.169 | 1.97m | 0.0044 | 38.1 | -20.3 | 38.1 | - | 12.3 | 38.1 |
| 29 | Muse Spark 1.3 (Max) Meta |
2026-09-02 | $2.39 | 7.46m | 0.0655 | 36.4 | -22.0 | 36.4 | - | 23.8 | 36.4 | |
| 30 | Claude Haiku 5.5 (Max) Anthropic |
2026-10-07 | $0.411 | 9.89m | 0.0113 | 36.2 | -22.2 | 36.2 | - | 16.1 | 36.2 | |
| 31 | Grok 4.7 (High) SpaceXAI |
2026-09-21 | $6.18 | 15.9m | 0.1766 | 35.0 | -23.4 | 35.0 | - | 27.9 | 35.0 | |
| 32 | ✓ | GPT-6.1 Sol (Low) OpenAI |
2026-09-29 | $0.161 | 1.73m | 0.0047 | 34.5 | -23.9 | 34.5 | - | 12.1 | 34.5 |
| 33 | Claude Opus 5.5 (Low, Default Fallback) Anthropic |
2026-09-22 | $0.976 | 2.45m | 0.0283 | 34.5 | -23.9 | 34.5 | - | 19.9 | 34.5 | |
| 34 | Claude Haiku 5.5 (Xhigh) Anthropic |
2026-10-07 | $0.248 | 7.35m | 0.0072 | 34.3 | -24.1 | 34.3 | - | 14.0 | 34.3 | |
| 35 | Grok 4.7 (Xhigh) SpaceXAI |
2026-09-21 | $7.51 | 16.5m | 0.2188 | 34.3 | -24.1 | 34.3 | - | 28.8 | 34.3 | |
| 36 | Qwen3.8 Max (0902) Alibaba |
2026-09-02 | $10.0 | 52.3m | 0.2987 | 33.6 | -24.9 | 33.6 | - | 30.0 | 33.6 | |
| 37 | DeepSeek V4.1 Flash 1017 (Max) DeepSeek |
2026-10-17 | $0.602 | 8.72m | 0.0185 | 32.5 | -25.9 | 32.5 | - | 17.8 | 32.5 | |
| 38 | GLM-5.3 (Max) Z AI |
2026-08-18 | $5.01 | 17.7m | 0.1583 | 31.7 | -26.8 | 31.7 | - | 27.0 | 31.7 | |
| 39 | Grok 4.7 (Low) SpaceXAI |
2026-09-21 | $2.92 | 8.97m | 0.0946 | 30.9 | -27.5 | 30.9 | - | 24.7 | 30.9 | |
| 40 | Gemini 3.8 Flash (High) |
2026-09-02 | $7.77 | 12.1m | 0.2542 | 30.5 | -27.9 | 30.5 | - | 28.9 | 30.5 | |
| 41 | GPT-6.1 Terra (Non-reasoning) OpenAI |
2026-10-26 | $0.226 | 1.73m | 0.0074 | 30.4 | -28.0 | 30.4 | - | 13.5 | 30.4 | |
| 42 | Claude Sonnet 5.5 (Medium, Default Fallback) Anthropic |
2026-09-28 | $0.781 | 2.96m | 0.0257 | 30.3 | -28.1 | 30.3 | - | 18.9 | 30.3 | |
| 43 | Gemini 3.8 Flash (Medium) |
2026-09-02 | $6.26 | - | 0.2088 | 30.0 | -28.4 | 30.0 | - | 28.0 | 30.0 | |
| 44 | MiMo-V2.6-Pro Xiaomi |
2026-09-21 | $0.257 | 30.5m | 0.0086 | 29.9 | -28.5 | 29.9 | - | 14.1 | 29.9 | |
| 45 | ✓ | Claude Haiku 5.5 (High) Anthropic |
2026-10-07 | $0.159 | 4.97m | 0.0054 | 29.6 | -28.8 | 29.6 | - | 12.0 | 29.6 |
| 46 | Ling 3.1 Flash 1019 InclusionAI |
2026-10-22 | $3.19 | - | 0.1081 | 29.5 | -28.9 | 29.5 | - | 25.0 | 29.5 | |
| 47 | ✓ | GPT-6.1 Terra (Low) OpenAI |
2026-10-26 | $0.0713 | 48s | 0.0024 | 29.2 | -29.2 | 29.2 | - | 8.5 | 29.2 |
| 48 | MiniMax-M3.1-Flash MiniMax |
2026-10-19 | $0.491 | 16.9m | 0.0170 | 28.9 | -29.5 | 28.9 | - | 16.9 | 28.9 | |
| 49 | Step 5 Preview StepFun |
2026-09-18 | $2.35 | 9.46m | 0.0822 | 28.5 | -29.9 | 28.5 | - | 23.7 | 28.5 | |
| 50 | GPT-6 Luna (Max) OpenAI |
2026-09-22 | $0.152 | 9.96m | 0.0055 | 27.8 | -30.7 | 27.8 | - | 11.8 | 27.8 | |
| 51 | MiMo-V2.6-Flash Xiaomi |
2026-09-21 | $0.129 | 37.0m | 0.0048 | 26.7 | -31.7 | 26.7 | - | 11.1 | 26.7 | |
| 52 | Claude Sonnet 5.5 (Low, Default Fallback) Anthropic |
2026-09-28 | $0.511 | 2.01m | 0.0202 | 25.3 | -33.1 | 25.3 | - | 17.1 | 25.3 | |
| 53 | Mistral Large 4 Preview Mistral |
2026-10-06 | $5.54 | 17.8m | 0.2190 | 25.3 | -33.1 | 25.3 | - | 27.4 | 25.3 | |
| 54 | Muse Spark Open (Xhigh) Meta |
2026-10-15 | $2.02 | 5.79m | 0.0817 | 24.7 | -33.7 | 24.7 | - | 23.0 | 24.7 | |
| 55 | Claude Haiku 5.5 (Medium) Anthropic |
2026-10-07 | $0.0918 | 3.22m | 0.0037 | 24.6 | -33.9 | 24.6 | - | 9.6 | 24.6 | |
| 56 | GPT-6 Luna (Xhigh) OpenAI |
2026-09-22 | $0.104 | 5.95m | 0.0045 | 23.3 | -35.1 | 23.3 | - | 10.2 | 23.3 | |
| 57 | DeepSeek V4 Pro 0813 (Max) DeepSeek |
2026-08-13 | $1.77 | 12.8m | 0.0767 | 23.1 | -35.3 | 23.1 | - | 22.5 | 23.1 | |
| 58 | GLM-5.3 (Low) Z AI |
2026-08-18 | $1.57 | 9.60m | 0.0683 | 23.1 | -35.3 | 23.1 | - | 22.0 | 23.1 | |
| 59 | GPT-6 Luna (High) OpenAI |
2026-09-22 | $0.0729 | 4.49m | 0.0034 | 21.4 | -37.0 | 21.4 | - | 8.6 | 21.4 | |
| 60 | Qwen3.8 27B (Xhigh) Alibaba |
2026-08-14 | $3.53 | 34.1m | 0.1755 | 20.1 | -38.3 | 20.1 | - | 25.5 | 20.1 | |
| 61 | MiniMax-M3 MiniMax |
2026-06-01 | $1.29 | 11.1m | 0.0686 | 18.7 | -39.7 | 18.7 | - | 21.1 | 18.7 | |
| 62 | ✓ | Claude Haiku 5.5 (Low) Anthropic |
2026-10-07 | $0.0438 | 1.63m | 0.0024 | 18.6 | -39.8 | 18.6 | - | 6.4 | 18.6 |
| 63 | ✓ | GPT-6 Luna (Medium) OpenAI |
2026-09-22 | $0.0422 | - | 0.0023 | 18.3 | -40.1 | 18.3 | - | 6.3 | 18.3 |
| 64 | Beam 1.0 Reflection |
2026-10-16 | $0.284 | 1.01m | 0.0160 | 17.7 | -40.7 | 17.7 | - | 14.5 | 17.7 | |
| 65 | Nemotron 3.5 Super VL NVIDIA |
2026-10-15 | $0.557 | 2.64m | 0.0409 | 13.6 | -44.8 | 13.6 | - | 17.5 | 13.6 | |
| 66 | Inkling Small Thinking Machines |
2026-07-30 | $0.203 | 2.46m | 0.0157 | 12.9 | -45.5 | 12.9 | - | 13.1 | 12.9 | |
| 67 | Inkling (Xhigh) Thinking Machines |
2026-07-15 | $1.35 | 3.45m | 0.1083 | 12.5 | -45.9 | 12.5 | - | 21.3 | 12.5 | |
| 68 | Nemotron 3 Ultra 550B A55B (Reasoning) NVIDIA |
2026-06-04 | $2.23 | 4.23m | 0.1893 | 11.8 | -46.6 | 11.8 | - | 23.5 | 11.8 | |
| 69 | Gemini 3.5 Flash-Lite |
2026-07-21 | $0.693 | 1.08m | 0.0594 | 11.7 | -46.7 | 11.7 | - | 18.4 | 11.7 | |
| 70 | ✓ | GPT-6 Luna (Low) OpenAI |
2026-09-22 | $0.00512 | 28s | 0.0005 | 9.7 | -48.7 | 9.7 | - | 0.0 | 9.7 |
| 71 | GPT-6 Luna (Non-reasoning) OpenAI |
2026-09-22 | $0.0714 | 1.44m | 0.0076 | 9.4 | -49.0 | 9.4 | - | 8.5 | 9.4 | |
| 72 | Muse Glimmer (High) Meta |
2026-08-10 | $0.161 | 3.50m | 0.0254 | 6.3 | -52.1 | 6.3 | - | 12.1 | 6.3 |