Run #2036

success · fetched 2026-09-04 19:00:14 · 1.32 MB raw HTML · 168 models

Open this run in comparison view · Download raw HTML · JSON results

Top quality: Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) (65.7 pts)

Cost/task vs quality?

168 models · 19 on the Pareto frontier · intelligence quality vs Cost per Task

420365369$0.01$0.10$1 cost per task, log scale intelligence quality Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) · Cost/task: $3.14 · Time/task: 5.14m · Quality: 62.1GPT-6 Astra (max) · Cost/task: $1.67 · Time/task: - · Quality: 61.2Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback) · Cost/task: $1.00 · Time/task: 1.84m · Quality: 60.5GPT-6 Astra (high) · Cost/task: $0.962 · Time/task: - · Quality: 60.3Grok 4.6 (xhigh) · Cost/task: $1.23 · Time/task: 6.09m · Quality: 60.0Kimi K3 (max) · Cost/task: $0.837 · Time/task: 10.5m · Quality: 59.7GLM-5.3 (max) · Cost/task: $0.683 · Time/task: 6.10m · Quality: 59.5GPT-6 Astra (medium) · Cost/task: $0.747 · Time/task: - · Quality: 59.2GPT-5.6 Sol (xhigh) · Cost/task: $0.628 · Time/task: 2.29m · Quality: 59.0Grok 4.6 (medium) · Cost/task: $0.783 · Time/task: 4.44m · Quality: 59.0Gemini 3.8 Flash (high) · Cost/task: $0.577 · Time/task: 1.80m · Quality: 58.7Claude Opus 5 (Adaptive Reasoning, Medium Effort) · Cost/task: $0.724 · Time/task: 2.38m · Quality: 58.6Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback) · Cost/task: $0.774 · Time/task: 1.30m · Quality: 58.1Qwen3.8 Max · Cost/task: $0.913 · Time/task: 11.4m · Quality: 58.1Qwen3.8 2.4T A95B · Cost/task: $0.807 · Time/task: 10.8m · Quality: 57.7GPT-5.6 Sol (high) · Cost/task: $0.427 · Time/task: 1.77m · Quality: 57.3Claude Opus 4.8 (Adaptive Reasoning, Max Effort) · Cost/task: $2.03 · Time/task: 7.54m · Quality: 57.3Muse Spark 1.2 (xhigh) · Cost/task: $0.399 · Time/task: 1.99m · Quality: 56.8GPT-6 Astra (low) · Cost/task: $0.459 · Time/task: - · Quality: 56.7Gemini 3.8 Flash (medium) · Cost/task: $0.410 · Time/task: 1.71m · Quality: 56.6GPT-5.6 Terra (max) · Cost/task: $0.526 · Time/task: 3.27m · Quality: 56.6GPT-5.5 (xhigh) · Cost/task: $1.19 · Time/task: 3.33m · Quality: 56.3Gemini 3.7 Flash (high) · Cost/task: $0.402 · Time/task: 1.76m · Quality: 56.0Qwen3.8-Flash-Next · Cost/task: $0.0970 · Time/task: 10.1m · Quality: 55.8Grok 4.5 (high) · Cost/task: $0.426 · Time/task: 4.43m · Quality: 55.8GPT-5.6 Sol (medium) · Cost/task: $0.290 · Time/task: 1.10m · Quality: 55.6GPT-6 Astra (Non-reasoning) · Cost/task: $0.932 · Time/task: - · Quality: 55.3Claude Sonnet 5 (Adaptive Reasoning, Max Effort) · Cost/task: $1.72 · Time/task: 8.34m · Quality: 55.3Claude Opus 4.7 (Adaptive Reasoning, Max Effort) · Cost/task: $2.23 · Time/task: 6.39m · Quality: 55.0GPT-5.5 (high) · Cost/task: $0.815 · Time/task: 2.24m · Quality: 54.7Gemini 3.7 Flash (medium) · Cost/task: $0.263 · Time/task: 1.21m · Quality: 53.4Muse Spark 1.1 (xhigh) · Cost/task: $0.292 · Time/task: - · Quality: 53.2DeepSeek V4 Pro 0813 (Reasoning, Max Effort) · Cost/task: $0.265 · Time/task: 6.50m · Quality: 53.2GPT-5.4 (xhigh) · Cost/task: $1.12 · Time/task: 4.15m · Quality: 53.1GPT-5.6 Terra (xhigh) · Cost/task: $0.318 · Time/task: 2.26m · Quality: 52.8GLM-5.2 (max) · Cost/task: $0.445 · Time/task: 9.49m · Quality: 52.6Claude Opus 5 (Adaptive Reasoning, Low Effort) · Cost/task: $0.425 · Time/task: 1.27m · Quality: 52.5Qwen3.8 27B (xhigh) · Cost/task: $0.369 · Time/task: 13.4m · Quality: 52.0Gemini 3.5 Flash (high) · Cost/task: $0.693 · Time/task: 2.39m · Quality: 52.0DeepSeek V4 Flash 0731 (Reasoning, Max Effort) · Cost/task: $0.112 · Time/task: 4.29m · Quality: 51.8Gemini 3.8 Flash (low) · Cost/task: $0.239 · Time/task: 43s · Quality: 51.8Grok 4.6 (low) · Cost/task: $0.255 · Time/task: 1.73m · Quality: 51.7Gemini 3.6 Flash (high) · Cost/task: $0.344 · Time/task: 1.97m · Quality: 51.6DeepSeek V4 Flash Vision (Reasoning, Max Effort) · Cost/task: $0.116 · Time/task: 5.72m · Quality: 51.5GPT-5.5 (medium) · Cost/task: $0.508 · Time/task: 1.27m · Quality: 51.4Gemini 3.7 Flash (low) · Cost/task: $0.165 · Time/task: 49s · Quality: 50.9GPT-5.6 Sol (low) · Cost/task: $0.180 · Time/task: 42s · Quality: 50.7GPT-5.6 Terra (high) · Cost/task: $0.228 · Time/task: 1.61m · Quality: 50.1Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) · Cost/task: $1.22 · Time/task: 12.8m · Quality: 48.4Kimi K3 (low) · Cost/task: $0.242 · Time/task: 1.70m · Quality: 48.3Gemini 3.1 Pro Preview · Cost/task: $0.335 · Time/task: 1.91m · Quality: 47.7GPT-5.6 Terra (medium) · Cost/task: $0.123 · Time/task: 50s · Quality: 46.8Qwen3.7 Max · Cost/task: $0.679 · Time/task: 1.62m · Quality: 46.7MiniMax-M3 · Cost/task: $0.139 · Time/task: 4.46m · Quality: 45.4DeepSeek V4 Pro (Reasoning, Max Effort) · Cost/task: $0.0498 · Time/task: 6.73m · Quality: 45.3Kimi K2.6 · Cost/task: $0.389 · Time/task: 13.6m · Quality: 45.1GPT-5.5 (low) · Cost/task: $0.262 · Time/task: 32s · Quality: 44.5Qwen3.8 27B (medium) · Cost/task: $0.284 · Time/task: 9.61m · Quality: 44.5Apodex 1.1 · Cost/task: $0.232 · Time/task: - · Quality: 44.0DeepSeek V4 Pro (Reasoning, High Effort) · Cost/task: $0.0432 · Time/task: 5.29m · Quality: 43.7Kimi K2.7 Code · Cost/task: $0.222 · Time/task: 6.79m · Quality: 43.0Quasar 438B (max, based on GLM-5.2) · Cost/task: $0.596 · Time/task: 5.00m · Quality: 43.0MiMo-V2.5-Pro · Cost/task: $0.0339 · Time/task: 8.96m · Quality: 42.9Qwen3.8 27B (low) · Cost/task: $0.265 · Time/task: 7.84m · Quality: 42.9Claude Sonnet 5 (Non-reasoning, High Effort) · Cost/task: $0.417 · Time/task: 1.70m · Quality: 42.6Inkling (xhigh) · Cost/task: $0.339 · Time/task: 5.54m · Quality: 42.3Hy3 · Cost/task: $0.0357 · Time/task: 5.23m · Quality: 42.2DeepSeek V4 Flash (Reasoning, Max Effort) · Cost/task: $0.0545 · Time/task: - · Quality: 42.1GPT-5.6 Sol (Non-reasoning) · Cost/task: $0.180 · Time/task: 34s · Quality: 41.9Solar Pro 4 · Cost/task: $0.303 · Time/task: 8.27m · Quality: 41.6GPT-5.6 Terra (low) · Cost/task: $0.0962 · Time/task: 30s · Quality: 41.3Inkling Small · Cost/task: $0.0735 · Time/task: 3.80m · Quality: 41.2GLM-5.1 (Reasoning) · Cost/task: $0.286 · Time/task: 8.59m · Quality: 41.0GPT-5.4 mini (xhigh) · Cost/task: $0.495 · Time/task: 7.53m · Quality: 40.9Grok Build 0.1 0616 · Cost/task: $0.225 · Time/task: 4.68m · Quality: 40.7Qwen3.6 Plus · Cost/task: $0.357 · Time/task: 6.42m · Quality: 40.5GPT-5.4 nano (xhigh) · Cost/task: $0.149 · Time/task: 7.63m · Quality: 39.7Qwen3.7 Plus · Cost/task: $0.170 · Time/task: 6.39m · Quality: 39.4DeepSeek V4 Flash (Reasoning, High Effort) · Cost/task: $0.0529 · Time/task: - · Quality: 39.0MiniMax-M2.7 · Cost/task: $0.0777 · Time/task: 4.03m · Quality: 38.9Nemotron 3 Ultra 550B A55B (Reasoning) · Cost/task: $0.314 · Time/task: 2.35m · Quality: 38.3Grok 4.3 (high) · Cost/task: $0.145 · Time/task: 1.77m · Quality: 37.9Ling 3.0 Flash · Cost/task: $0.0377 · Time/task: 1.48m · Quality: 37.8Qwen3.6 27B (Reasoning) · Cost/task: $0.292 · Time/task: 7.87m · Quality: 37.7GPT-5.1 (high) · Cost/task: $0.304 · Time/task: 4.87m · Quality: 37.5Gemini 3.5 Flash-Lite · Cost/task: $0.0965 · Time/task: 35s · Quality: 37.4Claude 4.5 Sonnet (Reasoning) · Cost/task: $0.464 · Time/task: 5.02m · Quality: 37.4Kimi K2.5 (Reasoning) · Cost/task: $0.217 · Time/task: - · Quality: 36.0GPT-5.5 (Non-reasoning) · Cost/task: $0.208 · Time/task: 24s · Quality: 35.8GPT-5 (high) · Cost/task: $0.244 · Time/task: 3.04m · Quality: 35.3Muse Glimmer (high) · Cost/task: $0.0473 · Time/task: 2.02m · Quality: 35.1Qwen3.8 27B (Non-reasoning) · Cost/task: $0.426 · Time/task: 5.55m · Quality: 34.7GPT-5.6 Terra (Non-reasoning) · Cost/task: $0.103 · Time/task: 29s · Quality: 34.6GLM-4.7 (Reasoning) · Cost/task: $0.359 · Time/task: 3.72m · Quality: 34.5Qwen3.5 397B A17B (Reasoning) · Cost/task: $0.357 · Time/task: 2.86m · Quality: 34.3LongCat 2.0 · Cost/task: $0.121 · Time/task: 6.49m · Quality: 34.0Qwen3.5 122B A10B (Reasoning) · Cost/task: $0.253 · Time/task: 1.98m · Quality: 32.8Qwen3.6 35B A3B (Reasoning) · Cost/task: $0.294 · Time/task: 3.65m · Quality: 32.1Ring-2.6-1T · Cost/task: $0.360 · Time/task: 3.11m · Quality: 31.7Qwen3.6 27B (Non-reasoning) · Cost/task: $0.398 · Time/task: 3.40m · Quality: 31.3Step 3.7 Flash · Cost/task: $0.0913 · Time/task: 6.73m · Quality: 30.9Mistral Medium 3.5 · Cost/task: $0.406 · Time/task: 3.08m · Quality: 30.4Claude 4.5 Haiku (Reasoning) · Cost/task: $0.217 · Time/task: 2.88m · Quality: 29.9GLM-4.6 (Reasoning) · Cost/task: $0.305 · Time/task: 6.01m · Quality: 29.3GPT-5.5 Instant (June 2026) · Cost/task: $0.537 · Time/task: 19s · Quality: 29.2Qwen3.5 122B A10B (Non-reasoning) · Cost/task: $0.195 · Time/task: 1.02m · Quality: 28.2GPT-5.6 Luna (Non-reasoning) · Cost/task: $0.0117 · Time/task: 20s · Quality: 26.8Gemma 4 26B A4B (Reasoning) · Cost/task: $0.0391 · Time/task: - · Quality: 26.1Gemini 2.5 Pro · Cost/task: $0.216 · Time/task: 1.61m · Quality: 25.9GPT-5 mini (high) · Cost/task: $0.0366 · Time/task: 2.08m · Quality: 25.8Nemotron 3 Super 120B A12B (Reasoning) · Cost/task: $0.229 · Time/task: 2.99m · Quality: 25.7Gemini 3.1 Flash-Lite · Cost/task: $0.0432 · Time/task: 1.12m · Quality: 25.6Grok 4.3 (Non-reasoning) · Cost/task: $0.295 · Time/task: 1.52m · Quality: 25.0Qwen3.6 35B A3B (Non-reasoning) · Cost/task: $0.630 · Time/task: 2.12m · Quality: 24.6Qwen3.5 35B A3B (Non-reasoning) · Cost/task: $0.241 · Time/task: 1.27m · Quality: 24.3gpt-oss-120b (high) · Cost/task: $0.0727 · Time/task: 3.44m · Quality: 24.1Granite 4.2 30B · Cost/task: $0.0290 · Time/task: 3.13m · Quality: 23.7Nemotron 3.5 Lightning · Cost/task: $0.0773 · Time/task: 1.63m · Quality: 23.6Gemma 4 31B (Non-reasoning) · Cost/task: $0.0424 · Time/task: 1.26m · Quality: 22.3Mercury 2 · Cost/task: $0.0798 · Time/task: 35s · Quality: 21.9Qwen3.5 9B (Reasoning) · Cost/task: $0.242 · Time/task: 5.76m · Quality: 21.8Qwen3 Coder Next · Cost/task: $0.337 · Time/task: 2.35m · Quality: 21.3Qwen3 235B A22B 2507 (Reasoning) · Cost/task: $0.0637 · Time/task: 4.45m · Quality: 19.9Mistral Small 4 (Reasoning) · Cost/task: $0.100 · Time/task: 1.93m · Quality: 19.7Granite 4.2 8B · Cost/task: $0.0158 · Time/task: 2.66m · Quality: 19.6Trinity Large Thinking · Cost/task: $0.200 · Time/task: 2.07m · Quality: 18.7DeepSeek R1 (Jan '25) · Cost/task: $0.324 · Time/task: - · Quality: 18.6HyperNova 60B 2605 (high, based on gpt-oss-120b) · Cost/task: $0.0243 · Time/task: 1.59m · Quality: 18.3Qwen3 Next 80B A3B (Reasoning) · Cost/task: $0.0419 · Time/task: 2.05m · Quality: 16.9Mistral Large 3 · Cost/task: $0.0806 · Time/task: 43s · Quality: 15.9DeepSeek V3 0324 · Cost/task: $0.0484 · Time/task: - · Quality: 15.2gpt-oss-20b (high) · Cost/task: $0.0250 · Time/task: 2.71m · Quality: 15.2gpt-oss-120b (low) · Cost/task: $0.0202 · Time/task: 17s · Quality: 14.9Mistral Small 3.1 · Cost/task: $0.0443 · Time/task: 34s · Quality: 14.9GPT-4.1 mini · Cost/task: $0.0549 · Time/task: 39s · Quality: 14.8Mistral Medium 3.1 · Cost/task: $0.166 · Time/task: 40s · Quality: 14.7Qwen3 30B A3B 2507 (Reasoning) · Cost/task: $0.0787 · Time/task: 1.81m · Quality: 14.6NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) · Cost/task: $0.0249 · Time/task: 2.65m · Quality: 14.5Solar Pro 3 · Cost/task: $0.132 · Time/task: 6.21m · Quality: 14.5Llama 4 Maverick · Cost/task: $0.0346 · Time/task: 28s · Quality: 14.5DeepSeek V3 (Dec '24) · Cost/task: $0.0255 · Time/task: - · Quality: 14.2Celeris-1 · Cost/task: $0.258 · Time/task: 9.0s · Quality: 12.4Magistral Small 1.2 · Cost/task: $0.295 · Time/task: - · Quality: 11.5Ministral 3 14B · Cost/task: $0.158 · Time/task: 2.08m · Quality: 11.2Mistral Small 3.2 · Cost/task: $0.140 · Time/task: 57s · Quality: 10.7Llama 4 Scout · Cost/task: $0.0111 · Time/task: 16s · Quality: 10.3GPT-4.1 nano · Cost/task: $0.0349 · Time/task: 1.01m · Quality: 9.6Ministral 3 8B · Cost/task: $0.185 · Time/task: 2.52m · Quality: 9.0Ministral 3 3B · Cost/task: $0.130 · Time/task: 1.53m · Quality: 7.1Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) · Cost/task: $3.69 · Time/task: 7.29m · Quality: 65.7 · Pareto frontierClaude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) · Cost/task: $2.65 · Time/task: 4.70m · Quality: 64.8 · Pareto frontierClaude Opus 5 (Adaptive Reasoning, Max Effort) · Cost/task: $2.34 · Time/task: 6.91m · Quality: 63.1 · Pareto frontierClaude Opus 5 (Adaptive Reasoning, Xhigh Effort) · Cost/task: $1.80 · Time/task: 5.66m · Quality: 62.5 · Pareto frontierClaude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) · Cost/task: $1.43 · Time/task: 2.82m · Quality: 62.5 · Pareto frontierClaude Opus 5 (Adaptive Reasoning, High Effort) · Cost/task: $1.23 · Time/task: 3.98m · Quality: 61.5 · Pareto frontierGPT-6 Astra (xhigh) · Cost/task: $1.20 · Time/task: - · Quality: 61.0 · Pareto frontierGPT-5.6 Sol (max) · Cost/task: $0.953 · Time/task: 3.20m · Quality: 60.9 · Pareto frontierGrok 4.6 (high) · Cost/task: $0.937 · Time/task: 5.35m · Quality: 60.9 · Pareto frontierMuse Spark 1.3 (xhigh) · Cost/task: $0.547 · Time/task: 3.43m · Quality: 60.8 · Pareto frontierGLM-5.3-Flash · Cost/task: $0.0869 · Time/task: 13.3m · Quality: 57.5 · Pareto frontierGPT-5.6 Luna (max) · Cost/task: $0.0487 · Time/task: 2.63m · Quality: 52.3 · Pareto frontierGPT-5.6 Luna (xhigh) · Cost/task: $0.0328 · Time/task: 1.89m · Quality: 50.1 · Pareto frontierAgnes 2.5 Pro Beta · Cost/task: $0.0273 · Time/task: - · Quality: 49.1 · Pareto frontierGPT-5.6 Luna (high) · Cost/task: $0.0223 · Time/task: 1.23m · Quality: 47.0 · Pareto frontierGPT-5.6 Luna (medium) · Cost/task: $0.0116 · Time/task: 37s · Quality: 38.9 · Pareto frontierMiMo-V2.5 · Cost/task: $0.0104 · Time/task: 5.09m · Quality: 38.0 · Pareto frontierGPT-5.6 Luna (low) · Cost/task: $0.00898 · Time/task: 23s · Quality: 33.9 · Pareto frontierGranite 4.2 3B · Cost/task: $0.00475 · Time/task: 50s · Quality: 14.3 · Pareto frontier Granite 4.2 3BGPT-5.6 Luna (low)MiMo-V2.5GPT-5.6 Luna (med…GPT-5.6 Luna (hig…Agnes 2.5 Pro BetaGPT-5.6 Luna (xhi…GPT-5.6 Luna (max)GLM-5.3-FlashMuse Spark 1.3 (x…Grok 4.6 (high)GPT-5.6 Sol (max)GPT-6 Astra (xhig…Claude Opus 5 (hi…Claude Fable 5.1 …Claude Opus 5 (xh…Claude Opus 5 (ma…Claude Fable 5.1 …Claude Fable 5.1 …
#?Pareto?Model?Released?Cost/task?Time/task?$/Q?Qual?ΔTop?Intel?Agent?Pen?Score?
1 Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Anthropic
2026-09-01 $3.69 7.29m 0.0562 65.7 0.0 65.7 - 25.7 65.7
2 Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)
Anthropic
2026-09-01 $2.65 4.70m 0.0409 64.8 -0.9 64.8 - 24.2 64.8
3 Claude Opus 5 (Adaptive Reasoning, Max Effort)
Anthropic
2026-07-24 $2.34 6.91m 0.0371 63.1 -2.6 63.1 - 23.7 63.1
4 Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
Anthropic
2026-07-24 $1.80 5.66m 0.0288 62.5 -3.1 62.5 - 22.6 62.5
5 Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)
Anthropic
2026-09-01 $1.43 2.82m 0.0229 62.5 -3.2 62.5 - 21.6 62.5
6 Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
Anthropic
2026-06-09 $3.14 5.14m 0.0506 62.1 -3.6 62.1 - 25.0 62.1
7 Claude Opus 5 (Adaptive Reasoning, High Effort)
Anthropic
2026-07-24 $1.23 3.98m 0.0200 61.5 -4.2 61.5 - 20.9 61.5
8 GPT-6 Astra (max)
OpenAI
2026-09-03 $1.67 - 0.0273 61.2 -4.4 61.2 - 22.2 61.2
9 GPT-6 Astra (xhigh)
OpenAI
2026-09-03 $1.20 - 0.0197 61.0 -4.7 61.0 - 20.8 61.0
10 GPT-5.6 Sol (max)
OpenAI
2026-07-09 $0.953 3.20m 0.0156 60.9 -4.7 60.9 - 19.8 60.9
11 Grok 4.6 (high)
SpaceXAI
2026-08-12 $0.937 5.35m 0.0154 60.9 -4.7 60.9 - 19.7 60.9
12 Muse Spark 1.3 (xhigh)
Meta
2026-09-02 $0.547 3.43m 0.0090 60.8 -4.9 60.8 - 17.4 60.8
13 Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)
Anthropic
2026-09-01 $1.00 1.84m 0.0165 60.5 -5.2 60.5 - 20.0 60.5
14 GPT-6 Astra (high)
OpenAI
2026-09-03 $0.962 - 0.0159 60.3 -5.3 60.3 - 19.8 60.3
15 Grok 4.6 (xhigh)
SpaceXAI
2026-08-12 $1.23 6.09m 0.0205 60.0 -5.6 60.0 - 20.9 60.0
16 Kimi K3 (max)
Kimi
2026-07-16 $0.837 10.5m 0.0140 59.7 -6.0 59.7 - 19.2 59.7
17 GLM-5.3 (max)
Z AI
2026-08-18 $0.683 6.10m 0.0115 59.5 -6.1 59.5 - 18.3 59.5
18 GPT-6 Astra (medium)
OpenAI
2026-09-03 $0.747 - 0.0126 59.2 -6.5 59.2 - 18.7 59.2
19 GPT-5.6 Sol (xhigh)
OpenAI
2026-07-09 $0.628 2.29m 0.0106 59.0 -6.6 59.0 - 18.0 59.0
20 Grok 4.6 (medium)
SpaceXAI
2026-08-12 $0.783 4.44m 0.0133 59.0 -6.6 59.0 - 18.9 59.0
21 Gemini 3.8 Flash (high)
Google
2026-09-02 $0.577 1.80m 0.0098 58.7 -7.0 58.7 - 17.6 58.7
22 Claude Opus 5 (Adaptive Reasoning, Medium Effort)
Anthropic
2026-07-24 $0.724 2.38m 0.0124 58.6 -7.0 58.6 - 18.6 58.6
23 Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)
Anthropic
2026-09-01 $0.774 1.30m 0.0133 58.1 -7.5 58.1 - 18.9 58.1
24 Qwen3.8 Max
Alibaba
2026-08-03 $0.913 11.4m 0.0157 58.1 -7.6 58.1 - 19.6 58.1
25 Qwen3.8 2.4T A95B
Alibaba
2026-08-12 $0.807 10.8m 0.0140 57.7 -7.9 57.7 - 19.1 57.7
26 GLM-5.3-Flash
Z AI
2026-08-26 $0.0869 13.3m 0.0015 57.5 -8.2 57.5 - 9.4 57.5
27 GPT-5.6 Sol (high)
OpenAI
2026-07-09 $0.427 1.77m 0.0074 57.3 -8.3 57.3 - 16.3 57.3
28 Claude Opus 4.8 (Adaptive Reasoning, Max Effort)
Anthropic
2026-05-28 $2.03 7.54m 0.0354 57.3 -8.3 57.3 - 23.1 57.3
29 Muse Spark 1.2 (xhigh)
Meta
2026-08-05 $0.399 1.99m 0.0070 56.8 -8.9 56.8 - 16.0 56.8
30 GPT-6 Astra (low)
OpenAI
2026-09-03 $0.459 - 0.0081 56.7 -8.9 56.7 - 16.6 56.7
31 Gemini 3.8 Flash (medium)
Google
2026-09-02 $0.410 1.71m 0.0072 56.6 -9.0 56.6 - 16.1 56.6
32 GPT-5.6 Terra (max)
OpenAI
2026-07-09 $0.526 3.27m 0.0093 56.6 -9.1 56.6 - 17.2 56.6
33 GPT-5.5 (xhigh)
OpenAI
2026-04-23 $1.19 3.33m 0.0212 56.3 -9.3 56.3 - 20.8 56.3
34 Gemini 3.7 Flash (high)
Google
2026-08-13 $0.402 1.76m 0.0072 56.0 -9.6 56.0 - 16.0 56.0
35 Qwen3.8-Flash-Next
Alibaba
2026-08-26 $0.0970 10.1m 0.0017 55.8 -9.8 55.8 - 9.9 55.8
36 Grok 4.5 (high)
SpaceXAI
2026-07-08 $0.426 4.43m 0.0076 55.8 -9.9 55.8 - 16.3 55.8
37 GPT-5.6 Sol (medium)
OpenAI
2026-07-09 $0.290 1.10m 0.0052 55.6 -10.1 55.6 - 14.6 55.6
38 GPT-6 Astra (Non-reasoning)
OpenAI
2026-09-03 $0.932 - 0.0168 55.3 -10.3 55.3 - 19.7 55.3
39 Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
Anthropic
2026-06-30 $1.72 8.34m 0.0311 55.3 -10.4 55.3 - 22.3 55.3
40 Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
Anthropic
2026-04-16 $2.23 6.39m 0.0405 55.0 -10.7 55.0 - 23.5 55.0
41 GPT-5.5 (high)
OpenAI
2026-04-23 $0.815 2.24m 0.0149 54.7 -11.0 54.7 - 19.1 54.7
42 Gemini 3.7 Flash (medium)
Google
2026-08-13 $0.263 1.21m 0.0049 53.4 -12.2 53.4 - 14.2 53.4
43 Muse Spark 1.1 (xhigh)
Meta
2026-07-09 $0.292 - 0.0055 53.2 -12.5 53.2 - 14.7 53.2
44 DeepSeek V4 Pro 0813 (Reasoning, Max Effort)
DeepSeek
2026-08-13 $0.265 6.50m 0.0050 53.2 -12.5 53.2 - 14.2 53.2
45 GPT-5.4 (xhigh)
OpenAI
2026-03-05 $1.12 4.15m 0.0211 53.1 -12.5 53.1 - 20.5 53.1
46 GPT-5.6 Terra (xhigh)
OpenAI
2026-07-09 $0.318 2.26m 0.0060 52.8 -12.9 52.8 - 15.0 52.8
47 GLM-5.2 (max)
Z AI
2026-06-16 $0.445 9.49m 0.0084 52.6 -13.0 52.6 - 16.5 52.6
48 Claude Opus 5 (Adaptive Reasoning, Low Effort)
Anthropic
2026-07-24 $0.425 1.27m 0.0081 52.5 -13.2 52.5 - 16.3 52.5
49 GPT-5.6 Luna (max)
OpenAI
2026-07-09 $0.0487 2.63m 0.0009 52.3 -13.3 52.3 - 6.9 52.3
50 Qwen3.8 27B (xhigh)
Alibaba
2026-08-14 $0.369 13.4m 0.0071 52.0 -13.6 52.0 - 15.7 52.0
51 Gemini 3.5 Flash (high)
Google
2026-05-19 $0.693 2.39m 0.0133 52.0 -13.7 52.0 - 18.4 52.0
52 DeepSeek V4 Flash 0731 (Reasoning, Max Effort)
DeepSeek
2026-07-31 $0.112 4.29m 0.0022 51.8 -13.9 51.8 - 10.5 51.8
53 Gemini 3.8 Flash (low)
Google
2026-09-02 $0.239 43s 0.0046 51.8 -13.9 51.8 - 13.8 51.8
54 Grok 4.6 (low)
SpaceXAI
2026-08-12 $0.255 1.73m 0.0049 51.7 -14.0 51.7 - 14.1 51.7
55 Gemini 3.6 Flash (high)
Google
2026-07-21 $0.344 1.97m 0.0067 51.6 -14.1 51.6 - 15.4 51.6
56 DeepSeek V4 Flash Vision (Reasoning, Max Effort)
DeepSeek
2026-08-21 $0.116 5.72m 0.0023 51.5 -14.2 51.5 - 10.7 51.5
57 GPT-5.5 (medium)
OpenAI
2026-04-23 $0.508 1.27m 0.0099 51.4 -14.2 51.4 - 17.1 51.4
58 Gemini 3.7 Flash (low)
Google
2026-08-13 $0.165 49s 0.0032 50.9 -14.7 50.9 - 12.2 50.9
59 GPT-5.6 Sol (low)
OpenAI
2026-07-09 $0.180 42s 0.0035 50.7 -14.9 50.7 - 12.6 50.7
60 GPT-5.6 Terra (high)
OpenAI
2026-07-09 $0.228 1.61m 0.0045 50.1 -15.5 50.1 - 13.6 50.1
61 GPT-5.6 Luna (xhigh)
OpenAI
2026-07-09 $0.0328 1.89m 0.0007 50.1 -15.6 50.1 - 5.2 50.1
62 Agnes 2.5 Pro Beta
Sapiens AI
2026-08-26 $0.0273 - 0.0006 49.1 -16.6 49.1 - 4.4 49.1
63 Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)
Anthropic
2026-02-17 $1.22 12.8m 0.0252 48.4 -17.3 48.4 - 20.9 48.4
64 Kimi K3 (low)
Kimi
2026-07-16 $0.242 1.70m 0.0050 48.3 -17.4 48.3 - 13.8 48.3
65 Gemini 3.1 Pro Preview
Google
2026-02-19 $0.335 1.91m 0.0070 47.7 -17.9 47.7 - 15.2 47.7
66 GPT-5.6 Luna (high)
OpenAI
2026-07-09 $0.0223 1.23m 0.0005 47.0 -18.7 47.0 - 3.5 47.0
67 GPT-5.6 Terra (medium)
OpenAI
2026-07-09 $0.123 50s 0.0026 46.8 -18.9 46.8 - 10.9 46.8
68 Qwen3.7 Max
Alibaba
2026-05-19 $0.679 1.62m 0.0145 46.7 -18.9 46.7 - 18.3 46.7
69 MiniMax-M3
MiniMax
2026-06-01 $0.139 4.46m 0.0031 45.4 -20.3 45.4 - 11.4 45.4
70 DeepSeek V4 Pro (Reasoning, Max Effort)
DeepSeek
2026-04-24 $0.0498 6.73m 0.0011 45.3 -20.4 45.3 - 7.0 45.3
71 Kimi K2.6
Kimi
2026-04-20 $0.389 13.6m 0.0086 45.1 -20.5 45.1 - 15.9 45.1
72 GPT-5.5 (low)
OpenAI
2026-04-23 $0.262 32s 0.0059 44.5 -21.2 44.5 - 14.2 44.5
73 Qwen3.8 27B (medium)
Alibaba
2026-08-14 $0.284 9.61m 0.0064 44.5 -21.2 44.5 - 14.5 44.5
74 Apodex 1.1
Apodex
2026-08-30 $0.232 - 0.0053 44.0 -21.7 44.0 - 13.7 44.0
75 DeepSeek V4 Pro (Reasoning, High Effort)
DeepSeek
2026-04-24 $0.0432 5.29m 0.0010 43.7 -21.9 43.7 - 6.4 43.7
76 Kimi K2.7 Code
Kimi
2026-06-12 $0.222 6.79m 0.0052 43.0 -22.6 43.0 - 13.5 43.0
77 Quasar 438B (max, based on GLM-5.2)
Multiverse Computing
2026-08-10 $0.596 5.00m 0.0139 43.0 -22.7 43.0 - 17.8 43.0
78 MiMo-V2.5-Pro
Xiaomi
2026-04-22 $0.0339 8.96m 0.0008 42.9 -22.8 42.9 - 5.3 42.9
79 Qwen3.8 27B (low)
Alibaba
2026-08-14 $0.265 7.84m 0.0062 42.9 -22.8 42.9 - 14.2 42.9
80 Claude Sonnet 5 (Non-reasoning, High Effort)
Anthropic
2026-06-30 $0.417 1.70m 0.0098 42.6 -23.1 42.6 - 16.2 42.6
81 Inkling (xhigh)
Thinking Machines
2026-07-15 $0.339 5.54m 0.0080 42.3 -23.4 42.3 - 15.3 42.3
82 Hy3
Tencent
2026-07-06 $0.0357 5.23m 0.0008 42.2 -23.4 42.2 - 5.5 42.2
83 DeepSeek V4 Flash (Reasoning, Max Effort)
DeepSeek
2026-04-24 $0.0545 - 0.0013 42.1 -23.5 42.1 - 7.4 42.1
84 GPT-5.6 Sol (Non-reasoning)
OpenAI
2026-07-09 $0.180 34s 0.0043 41.9 -23.8 41.9 - 12.6 41.9
85 Solar Pro 4
Upstage
2026-08-06 $0.303 8.27m 0.0073 41.6 -24.0 41.6 - 14.8 41.6
86 GPT-5.6 Terra (low)
OpenAI
2026-07-09 $0.0962 30s 0.0023 41.3 -24.4 41.3 - 9.8 41.3
87 Inkling Small
Thinking Machines
2026-07-30 $0.0735 3.80m 0.0018 41.2 -24.5 41.2 - 8.7 41.2
88 GLM-5.1 (Reasoning)
Z AI
2026-04-07 $0.286 8.59m 0.0070 41.0 -24.7 41.0 - 14.6 41.0
89 GPT-5.4 mini (xhigh)
OpenAI
2026-03-17 $0.495 7.53m 0.0121 40.9 -24.7 40.9 - 16.9 40.9
90 Grok Build 0.1 0616
SpaceXAI
2026-06-16 $0.225 4.68m 0.0055 40.7 -25.0 40.7 - 13.5 40.7
91 Qwen3.6 Plus
Alibaba
2026-04-02 $0.357 6.42m 0.0088 40.5 -25.2 40.5 - 15.5 40.5
92 GPT-5.4 nano (xhigh)
OpenAI
2026-03-17 $0.149 7.63m 0.0038 39.7 -25.9 39.7 - 11.7 39.7
93 Qwen3.7 Plus
Alibaba
2026-06-01 $0.170 6.39m 0.0043 39.4 -26.3 39.4 - 12.3 39.4
94 DeepSeek V4 Flash (Reasoning, High Effort)
DeepSeek
2026-04-24 $0.0529 - 0.0014 39.0 -26.6 39.0 - 7.2 39.0
95 GPT-5.6 Luna (medium)
OpenAI
2026-07-09 $0.0116 37s 0.0003 38.9 -26.7 38.9 - 0.6 38.9
96 MiniMax-M2.7
MiniMax
2026-03-18 $0.0777 4.03m 0.0020 38.9 -26.8 38.9 - 8.9 38.9
97 Nemotron 3 Ultra 550B A55B (Reasoning)
NVIDIA
2026-06-04 $0.314 2.35m 0.0082 38.3 -27.3 38.3 - 15.0 38.3
98 MiMo-V2.5
Xiaomi
2026-04-22 $0.0104 5.09m 0.0003 38.0 -27.6 38.0 - 0.2 38.0
99 Grok 4.3 (high)
SpaceXAI
2026-04-30 $0.145 1.77m 0.0038 37.9 -27.7 37.9 - 11.6 37.9
100 Ling 3.0 Flash
InclusionAI
2026-08-04 $0.0377 1.48m 0.0010 37.8 -27.8 37.8 - 5.8 37.8