Run #1386

success · fetched 2026-08-03 15:00:05 · 1.20 MB raw HTML · 129 models

Open this run in comparison view · JSON results

Top quality: Claude Opus 5 (Adaptive Reasoning, Max Effort) (64.6 pts)

Cost/task vs quality?

129 models · 14 on the Pareto frontier · combined quality vs Cost per Task

118355168$0.01$0.02$0.05$0.10$0.20$0.50$1$2 cost per task, log scale combined quality Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) · Cost/task: $3.15 · Time/task: 4.98m · Quality: 63.1Claude Opus 5 (Adaptive Reasoning, High Effort) · Cost/task: $1.23 · Time/task: 4.33m · Quality: 62.5Kimi K3 (max) · Cost/task: $0.855 · Time/task: 11.4m · Quality: 61.1Claude Opus 5 (Adaptive Reasoning, Medium Effort) · Cost/task: $0.722 · Time/task: 2.57m · Quality: 59.2Claude Opus 4.8 (Adaptive Reasoning, Max Effort) · Cost/task: $2.03 · Time/task: 8.38m · Quality: 59.0GPT-5.5 (xhigh) · Cost/task: $1.17 · Time/task: 3.57m · Quality: 58.2Claude Sonnet 5 (Adaptive Reasoning, Max Effort) · Cost/task: $1.72 · Time/task: 9.61m · Quality: 57.2Claude Opus 4.7 (Adaptive Reasoning, Max Effort) · Cost/task: $2.22 · Time/task: 6.92m · Quality: 57.2GPT-5.5 (high) · Cost/task: $0.801 · Time/task: 2.43m · Quality: 56.1GPT-5.6 Terra (xhigh) · Cost/task: $0.305 · Time/task: 1.79m · Quality: 55.6GPT-5.4 (xhigh) · Cost/task: $1.11 · Time/task: 3.95m · Quality: 54.5GLM-5.2 (max) · Cost/task: $0.594 · Time/task: 4.10m · Quality: 54.3GPT-5.6 Luna (xhigh) · Cost/task: $0.0317 · Time/task: 1.37m · Quality: 53.5GPT-5.5 (medium) · Cost/task: $0.495 · Time/task: 1.35m · Quality: 53.2Muse Spark 1.1 (xhigh) · Cost/task: $0.292 · Time/task: 2.09m · Quality: 53.2GPT-5.6 Sol (low) · Cost/task: $0.245 · Time/task: 47s · Quality: 53.0Gemini 3.6 Flash (high) · Cost/task: $0.557 · Time/task: 1.98m · Quality: 52.7Gemini 3.5 Flash (high) · Cost/task: $0.691 · Time/task: 2.75m · Quality: 52.6GPT-5.6 Terra (high) · Cost/task: $0.220 · Time/task: 1.30m · Quality: 52.5Claude Opus 5 (Adaptive Reasoning, Low Effort) · Cost/task: $0.426 · Time/task: 1.34m · Quality: 52.4Kimi K3 (low) · Cost/task: $0.243 · Time/task: 2.00m · Quality: 51.9Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) · Cost/task: $1.22 · Time/task: 14.2m · Quality: 50.3GPT-5.6 Terra (medium) · Cost/task: $0.119 · Time/task: 39s · Quality: 49.1Qwen3.7 Max · Cost/task: $1.28 · Time/task: 1.61m · Quality: 47.5Claude Sonnet 5 (Non-reasoning, High Effort) · Cost/task: $0.422 · Time/task: 1.78m · Quality: 47.3GPT-5.6 Sol (Non-reasoning) · Cost/task: $0.238 · Time/task: 36s · Quality: 47.1DeepSeek V4 Pro (Reasoning, Max Effort) · Cost/task: $0.0475 · Time/task: 10.0m · Quality: 46.7MiniMax-M3 · Cost/task: $0.137 · Time/task: 4.58m · Quality: 46.1Gemini 3.1 Pro Preview · Cost/task: $0.339 · Time/task: 1.73m · Quality: 45.6Kimi K2.6 · Cost/task: $0.365 · Time/task: 18.2m · Quality: 45.4DeepSeek V4 Pro (Reasoning, High Effort) · Cost/task: $0.0432 · Time/task: 7.31m · Quality: 45.4GPT-5.5 (low) · Cost/task: $0.260 · Time/task: 35s · Quality: 44.9Kimi K2.7 Code · Cost/task: $0.221 · Time/task: 7.93m · Quality: 44.1MiMo-V2.5-Pro · Cost/task: $0.0340 · Time/task: 8.68m · Quality: 43.8Hy3 · Cost/task: $0.0357 · Time/task: 6.80m · Quality: 43.6GPT-5.6 Terra (low) · Cost/task: $0.0912 · Time/task: 24s · Quality: 43.1DeepSeek V4 Flash (Reasoning, Max Effort) · Cost/task: $0.0691 · Time/task: - · Quality: 42.5GPT-5.4 mini (xhigh) · Cost/task: $0.494 · Time/task: 6.99m · Quality: 42.1GLM-5.1 (Reasoning) · Cost/task: $0.273 · Time/task: 5.98m · Quality: 41.9Inkling Small · Cost/task: $0.0733 · Time/task: 3.42m · Quality: 41.3GPT-5.4 nano (xhigh) · Cost/task: $0.150 · Time/task: 7.46m · Quality: 40.6Qwen3.6 Plus · Cost/task: $0.357 · Time/task: 6.42m · Quality: 40.5Grok Build 0.1 0616 · Cost/task: $0.223 · Time/task: 3.62m · Quality: 39.8Qwen3.6 27B (Reasoning) · Cost/task: $0.293 · Time/task: 7.64m · Quality: 39.3GPT-5.5 (Non-reasoning) · Cost/task: $0.206 · Time/task: 27s · Quality: 39.2DeepSeek V4 Flash (Reasoning, High Effort) · Cost/task: $0.0505 · Time/task: - · Quality: 39.2Qwen3.7 Plus · Cost/task: $0.226 · Time/task: 6.68m · Quality: 38.5GPT-5.6 Terra (Non-reasoning) · Cost/task: $0.103 · Time/task: 23s · Quality: 38.5Nemotron 3 Ultra 550B A55B (Reasoning) · Cost/task: $0.413 · Time/task: 2.61m · Quality: 38.1Claude 4.5 Sonnet (Reasoning) · Cost/task: $0.462 · Time/task: 4.99m · Quality: 37.7Gemini 3.5 Flash-Lite · Cost/task: $0.0961 · Time/task: 36s · Quality: 37.5GPT-5.1 (high) · Cost/task: $0.300 · Time/task: 3.65m · Quality: 35.8GLM-4.7 (Reasoning) · Cost/task: $0.353 · Time/task: 3.76m · Quality: 34.8Grok 4.3 (high) · Cost/task: $0.145 · Time/task: 1.82m · Quality: 34.6Kimi K2.5 (Reasoning) · Cost/task: $0.0957 · Time/task: 3.56m · Quality: 34.6Qwen3.5 397B A17B (Reasoning) · Cost/task: $0.359 · Time/task: 4.01m · Quality: 33.9LongCat 2.0 · Cost/task: $0.122 · Time/task: 7.29m · Quality: 33.5Qwen3.6 27B (Non-reasoning) · Cost/task: $0.396 · Time/task: 3.35m · Quality: 33.5Qwen3.5 122B A10B (Reasoning) · Cost/task: $0.257 · Time/task: 2.01m · Quality: 32.9GPT-5 (high) · Cost/task: $0.257 · Time/task: 3.09m · Quality: 32.7Mistral Medium 3.5 · Cost/task: $0.460 · Time/task: 2.85m · Quality: 31.9Qwen3.6 35B A3B (Reasoning) · Cost/task: $0.194 · Time/task: 3.45m · Quality: 31.6Ring-2.6-1T · Cost/task: $0.366 · Time/task: - · Quality: 30.8GLM-4.6 (Reasoning) · Cost/task: $0.302 · Time/task: 5.28m · Quality: 30.7Step 3.7 Flash · Cost/task: $0.0906 · Time/task: 2.24m · Quality: 30.5Claude 4.5 Haiku (Reasoning) · Cost/task: $0.216 · Time/task: 3.19m · Quality: 30.0GPT-5.6 Luna (Non-reasoning) · Cost/task: $0.0118 · Time/task: 15s · Quality: 29.3Qwen3.5 122B A10B (Non-reasoning) · Cost/task: $0.193 · Time/task: 1.01m · Quality: 28.9Grok 4.3 (Non-reasoning) · Cost/task: $0.294 · Time/task: 1.26m · Quality: 27.6GPT-5.5 Instant (June 2026) · Cost/task: $0.537 · Time/task: - · Quality: 26.4Gemma 4 26B A4B (Reasoning) · Cost/task: $0.0439 · Time/task: - · Quality: 25.3Qwen3.5 35B A3B (Non-reasoning) · Cost/task: $0.241 · Time/task: 1.23m · Quality: 24.3NVIDIA Nemotron 3 Super 120B A12B (Reasoning) · Cost/task: $0.231 · Time/task: 3.00m · Quality: 23.9Qwen3.6 35B A3B (Non-reasoning) · Cost/task: $0.630 · Time/task: 1.75m · Quality: 23.8gpt-oss-120b (high) · Cost/task: $0.0750 · Time/task: 2.91m · Quality: 22.5Gemini 2.5 Pro · Cost/task: $0.215 · Time/task: 1.42m · Quality: 22.1Qwen3 Coder Next · Cost/task: $0.334 · Time/task: 1.81m · Quality: 22.0Gemini 3.1 Flash-Lite · Cost/task: $0.0431 · Time/task: 1.05m · Quality: 22.0Gemma 4 31B (Non-reasoning) · Cost/task: $0.0369 · Time/task: 1.10m · Quality: 22.0Nova 2.0 Pro Preview (medium) · Cost/task: $0.183 · Time/task: 1.74m · Quality: 20.9Mercury 2 · Cost/task: $0.0791 · Time/task: 38s · Quality: 20.7Gemma 4 12B (Reasoning) · Cost/task: $0.0763 · Time/task: 3.79m · Quality: 20.2GPT-5 mini (high) · Cost/task: $0.0361 · Time/task: 2.33m · Quality: 20.1Qwen3.5 9B (Reasoning) · Cost/task: $0.243 · Time/task: 5.94m · Quality: 19.2Nova 2.0 Pro Preview (low) · Cost/task: $0.227 · Time/task: 44s · Quality: 17.3Mistral Small 4 (Reasoning) · Cost/task: $0.101 · Time/task: 2.06m · Quality: 17.0HyperNova 60B 2605 · Cost/task: $0.0236 · Time/task: 1.46m · Quality: 15.9Trinity Large Thinking · Cost/task: $0.164 · Time/task: 3.69m · Quality: 15.9DeepSeek R1 (Jan '25) · Cost/task: $0.292 · Time/task: - · Quality: 15.4Mistral Small 3.1 · Cost/task: $0.0443 · Time/task: 33s · Quality: 15.4Qwen3 235B A22B 2507 (Reasoning) · Cost/task: $0.222 · Time/task: 6.01m · Quality: 15.2Nova 2.0 Lite (high) · Cost/task: $0.241 · Time/task: 5.14m · Quality: 14.8Mistral Large 3 · Cost/task: $0.0805 · Time/task: 1.08m · Quality: 13.8Mistral Medium 3.1 · Cost/task: $0.163 · Time/task: 60s · Quality: 13.8Magistral Medium 1.2 · Cost/task: $0.844 · Time/task: 1.62m · Quality: 13.7DeepSeek V3 (Dec '24) · Cost/task: $0.0248 · Time/task: - · Quality: 12.9gpt-oss-20b (high) · Cost/task: $0.0286 · Time/task: 1.78m · Quality: 12.9DeepSeek V3 0324 · Cost/task: $0.0473 · Time/task: - · Quality: 12.7Nova 2.0 Pro Preview (Non-reasoning) · Cost/task: $0.259 · Time/task: 39s · Quality: 12.7gpt-oss-120b (low) · Cost/task: $0.0203 · Time/task: 10s · Quality: 12.4GPT-4.1 mini · Cost/task: $0.0664 · Time/task: 40s · Quality: 12.2Qwen3 Next 80B A3B (Reasoning) · Cost/task: $0.191 · Time/task: 1.83m · Quality: 12.1Solar Pro 3 · Cost/task: $0.145 · Time/task: 7.07m · Quality: 11.0Llama 4 Maverick · Cost/task: $0.0352 · Time/task: 21s · Quality: 10.6NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) · Cost/task: $0.0245 · Time/task: 1.72m · Quality: 10.2Qwen3 30B A3B 2507 (Reasoning) · Cost/task: $0.0785 · Time/task: 2.30m · Quality: 9.4Ministral 3 14B · Cost/task: $0.159 · Time/task: 1.96m · Quality: 9.2Magistral Small 1.2 · Cost/task: $0.286 · Time/task: 1.17m · Quality: 9.2Mistral Small 3.2 · Cost/task: $0.138 · Time/task: 59s · Quality: 8.4Gemma 4 E4B (Reasoning) · Cost/task: $0.0149 · Time/task: 1.62m · Quality: 7.8GPT-4.1 nano · Cost/task: $0.0352 · Time/task: 34s · Quality: 7.3Llama 3.3 Instruct 70B · Cost/task: $0.0902 · Time/task: 21s · Quality: 7.2Ministral 3 8B · Cost/task: $0.184 · Time/task: 2.09m · Quality: 6.6Llama 4 Scout · Cost/task: $0.0105 · Time/task: 9.8s · Quality: 6.4Ministral 3 3B · Cost/task: $0.130 · Time/task: 1.53m · Quality: 4.4Claude Opus 5 (Adaptive Reasoning, Max Effort) · Cost/task: $2.34 · Time/task: 7.85m · Quality: 64.6 · Pareto frontierClaude Opus 5 (Adaptive Reasoning, Xhigh Effort) · Cost/task: $1.80 · Time/task: 6.10m · Quality: 63.9 · Pareto frontierGPT-5.6 Sol (max) · Cost/task: $1.23 · Time/task: 4.08m · Quality: 63.4 · Pareto frontierGPT-5.6 Sol (xhigh) · Cost/task: $0.832 · Time/task: 2.66m · Quality: 62.6 · Pareto frontierGPT-5.6 Sol (high) · Cost/task: $0.549 · Time/task: 2.06m · Quality: 60.5 · Pareto frontierGPT-5.6 Terra (max) · Cost/task: $0.510 · Time/task: 2.53m · Quality: 59.7 · Pareto frontierGPT-5.6 Sol (medium) · Cost/task: $0.390 · Time/task: 1.26m · Quality: 58.1 · Pareto frontierGrok 4.5 (high) · Cost/task: $0.365 · Time/task: 4.40m · Quality: 57.3 · Pareto frontierGPT-5.6 Luna (max) · Cost/task: $0.0473 · Time/task: 1.88m · Quality: 56.1 · Pareto frontierDeepSeek V4 Flash 0731 (Reasoning, Max Effort) · Cost/task: $0.0271 · Time/task: 5.32m · Quality: 54.9 · Pareto frontierGPT-5.6 Luna (high) · Cost/task: $0.0216 · Time/task: 55s · Quality: 49.8 · Pareto frontierGPT-5.6 Luna (medium) · Cost/task: $0.0113 · Time/task: 26s · Quality: 39.9 · Pareto frontierMiMo-V2.5 · Cost/task: $0.0104 · Time/task: 3.69m · Quality: 39.2 · Pareto frontierGPT-5.6 Luna (low) · Cost/task: $0.00883 · Time/task: 17s · Quality: 34.3 · Pareto frontier GPT-5.6 Luna (low)MiMo-V2.5GPT-5.6 Luna (med…GPT-5.6 Luna (hig…DeepSeek V4 Flash…GPT-5.6 Luna (max)Grok 4.5 (high)GPT-5.6 Sol (medi…GPT-5.6 Terra (ma…GPT-5.6 Sol (high)GPT-5.6 Sol (xhig…GPT-5.6 Sol (max)Claude Opus 5 (xh…Claude Opus 5 (ma…
#?Pareto?Model?Released?Cost/task?Time/task?$/Q?Qual?ΔTop?Intel?Code?Agent?Pen?Score?
1 Claude Opus 5 (Adaptive Reasoning, Max Effort)
Anthropic
2026-07-24 $2.34 7.85m 0.0361 64.6 0.0 60.7 78.0 55.3 23.7 64.6
2 Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
Anthropic
2026-07-24 $1.80 6.10m 0.0282 63.9 -0.8 60.1 77.0 54.5 22.6 63.9
3 GPT-5.6 Sol (max)
OpenAI
2026-07-09 $1.23 4.08m 0.0194 63.4 -1.2 58.9 77.4 54.0 20.9 63.4
4 Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
Anthropic
2026-06-09 $3.15 4.98m 0.0499 63.1 -1.6 59.9 76.5 52.8 25.0 63.1
5 GPT-5.6 Sol (xhigh)
OpenAI
2026-07-09 $0.832 2.66m 0.0133 62.6 -2.0 57.7 78.3 51.8 19.2 62.6
6 Claude Opus 5 (Adaptive Reasoning, High Effort)
Anthropic
2026-07-24 $1.23 4.33m 0.0196 62.5 -2.2 58.9 76.5 52.1 20.9 62.5
7 Kimi K3 (max)
Kimi
2026-07-16 $0.855 11.4m 0.0140 61.1 -3.5 57.1 76.2 50.1 19.3 61.1
8 GPT-5.6 Sol (high)
OpenAI
2026-07-09 $0.549 2.06m 0.0091 60.5 -4.1 55.9 77.2 48.5 17.4 60.5
9 GPT-5.6 Terra (max)
OpenAI
2026-07-09 $0.510 2.53m 0.0085 59.7 -5.0 55.0 76.7 47.4 17.1 59.7
10 Claude Opus 5 (Adaptive Reasoning, Medium Effort)
Anthropic
2026-07-24 $0.722 2.57m 0.0122 59.2 -5.4 56.3 74.3 47.1 18.6 59.2
11 Claude Opus 4.8 (Adaptive Reasoning, Max Effort)
Anthropic
2026-05-28 $2.03 8.38m 0.0344 59.0 -5.6 55.7 74.3 47.2 23.1 59.0
12 GPT-5.5 (xhigh)
OpenAI
2026-04-23 $1.17 3.57m 0.0202 58.2 -6.4 54.8 74.9 44.9 20.7 58.2
13 GPT-5.6 Sol (medium)
OpenAI
2026-07-09 $0.390 1.26m 0.0067 58.1 -6.5 53.6 76.3 44.5 15.9 58.1
14 Grok 4.5 (high)
SpaceXAI
2026-07-08 $0.365 4.40m 0.0064 57.3 -7.3 53.8 72.4 45.7 15.6 57.3
15 Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
Anthropic
2026-06-30 $1.72 9.61m 0.0300 57.2 -7.4 53.4 71.5 46.7 22.3 57.2
16 Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
Anthropic
2026-04-16 $2.22 6.92m 0.0389 57.2 -7.5 53.5 73.6 44.4 23.5 57.2
17 GPT-5.6 Luna (max)
OpenAI
2026-07-09 $0.0473 1.88m 0.0008 56.1 -8.5 51.2 71.4 45.6 6.8 56.1
18 GPT-5.5 (high)
OpenAI
2026-04-23 $0.801 2.43m 0.0143 56.1 -8.6 53.1 71.6 43.5 19.0 56.1
19 GPT-5.6 Terra (xhigh)
OpenAI
2026-07-09 $0.305 1.79m 0.0055 55.6 -9.0 51.6 70.6 44.7 14.8 55.6
20 DeepSeek V4 Flash 0731 (Reasoning, Max Effort)
DeepSeek
2026-07-31 $0.0271 5.32m 0.0005 54.9 -9.8 49.9 69.1 45.7 4.3 54.9
21 GPT-5.4 (xhigh)
OpenAI
2026-03-05 $1.11 3.95m 0.0203 54.5 -10.1 51.4 71.1 41.1 20.4 54.5
22 GLM-5.2 (max)
Z AI
2026-06-16 $0.594 4.10m 0.0109 54.3 -10.3 51.1 68.8 43.1 17.7 54.3
23 GPT-5.6 Luna (xhigh)
OpenAI
2026-07-09 $0.0317 1.37m 0.0006 53.5 -11.1 49.1 68.6 42.9 5.0 53.5
24 GPT-5.5 (medium)
OpenAI
2026-04-23 $0.495 1.35m 0.0093 53.2 -11.4 50.4 71.5 37.8 16.9 53.2
25 Muse Spark 1.1 (xhigh)
Meta
2026-07-09 $0.292 2.09m 0.0055 53.2 -11.5 50.6 71.3 37.5 14.7 53.2
26 GPT-5.6 Sol (low)
OpenAI
2026-07-09 $0.245 47s 0.0046 53.0 -11.6 49.4 69.7 40.0 13.9 53.0
27 Gemini 3.6 Flash (high)
Google
2026-07-21 $0.557 1.98m 0.0106 52.7 -12.0 50.1 69.2 38.7 17.5 52.7
28 Gemini 3.5 Flash (high)
Google
2026-05-19 $0.691 2.75m 0.0131 52.6 -12.0 50.2 70.1 37.4 18.4 52.6
29 GPT-5.6 Terra (high)
OpenAI
2026-07-09 $0.220 1.30m 0.0042 52.5 -12.2 49.0 67.1 41.3 13.4 52.5
30 Claude Opus 5 (Adaptive Reasoning, Low Effort)
Anthropic
2026-07-24 $0.426 1.34m 0.0081 52.4 -12.2 50.6 66.9 39.8 16.3 52.4
31 Kimi K3 (low)
Kimi
2026-07-16 $0.243 2.00m 0.0047 51.9 -12.8 46.6 72.0 37.0 13.9 51.9
32 Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)
Anthropic
2026-02-17 $1.22 14.2m 0.0242 50.3 -14.3 47.2 63.0 40.8 20.9 50.3
33 GPT-5.6 Luna (high)
OpenAI
2026-07-09 $0.0216 55s 0.0004 49.8 -14.8 46.1 63.3 40.1 3.3 49.8
34 GPT-5.6 Terra (medium)
OpenAI
2026-07-09 $0.119 39s 0.0024 49.1 -15.5 45.6 64.7 37.0 10.8 49.1
35 Qwen3.7 Max
Alibaba
2026-05-19 $1.28 1.61m 0.0269 47.5 -17.1 46.0 66.0 30.6 21.1 47.5
36 Claude Sonnet 5 (Non-reasoning, High Effort)
Anthropic
2026-06-30 $0.422 1.78m 0.0089 47.3 -17.4 41.7 66.4 33.7 16.3 47.3
37 GPT-5.6 Sol (Non-reasoning)
OpenAI
2026-07-09 $0.238 36s 0.0051 47.1 -17.6 41.2 65.1 34.9 13.8 47.1
38 DeepSeek V4 Pro (Reasoning, Max Effort)
DeepSeek
2026-04-24 $0.0475 10.0m 0.0010 46.7 -18.0 44.3 59.4 36.4 6.8 46.7
39 MiniMax-M3
MiniMax
2026-06-01 $0.137 4.58m 0.0030 46.1 -18.5 44.4 58.6 35.4 11.4 46.1
40 Gemini 3.1 Pro Preview
Google
2026-02-19 $0.339 1.73m 0.0074 45.6 -19.1 46.5 68.8 21.4 15.3 45.6
41 Kimi K2.6
Kimi
2026-04-20 $0.365 18.2m 0.0080 45.4 -19.2 44.2 61.8 30.3 15.6 45.4
42 DeepSeek V4 Pro (Reasoning, High Effort)
DeepSeek
2026-04-24 $0.0432 7.31m 0.0010 45.4 -19.2 43.1 58.7 34.4 6.4 45.4
43 GPT-5.5 (low)
OpenAI
2026-04-23 $0.260 35s 0.0058 44.9 -19.7 43.5 60.9 30.4 14.1 44.9
44 Kimi K2.7 Code
Kimi
2026-06-12 $0.221 7.93m 0.0050 44.1 -20.5 41.9 60.8 29.6 13.5 44.1
45 MiMo-V2.5-Pro
Xiaomi
2026-04-22 $0.0340 8.68m 0.0008 43.8 -20.8 42.2 60.2 29.1 5.3 43.8
46 Hy3
Tencent
2026-07-06 $0.0357 6.80m 0.0008 43.6 -21.1 41.2 58.8 30.7 5.5 43.6
47 GPT-5.6 Terra (low)
OpenAI
2026-07-09 $0.0912 24s 0.0021 43.1 -21.6 40.5 58.1 30.6 9.6 43.1
48 DeepSeek V4 Flash (Reasoning, Max Effort)
DeepSeek
2026-04-24 $0.0691 - 0.0016 42.5 -22.1 40.3 56.2 31.1 8.4 42.5
49 GPT-5.4 mini (xhigh)
OpenAI
2026-03-17 $0.494 6.99m 0.0117 42.1 -22.6 40.0 56.1 30.2 16.9 42.1
50 GLM-5.1 (Reasoning)
Z AI
2026-04-07 $0.273 5.98m 0.0065 41.9 -22.7 40.2 55.8 29.9 14.4 41.9
51 Inkling Small
Thinking Machines
2026-07-30 $0.0733 3.42m 0.0018 41.3 -23.3 40.2 52.9 30.8 8.7 41.3
52 GPT-5.4 nano (xhigh)
OpenAI
2026-03-17 $0.150 7.46m 0.0037 40.6 -24.0 38.2 56.1 27.5 11.8 40.6
53 Qwen3.6 Plus
Alibaba
2026-04-02 $0.357 6.42m 0.0088 40.5 -24.1 39.6 54.5 27.6 15.5 40.5
54 GPT-5.6 Luna (medium)
OpenAI
2026-07-09 $0.0113 26s 0.0003 39.9 -24.7 38.1 50.7 31.0 0.5 39.9
55 Grok Build 0.1 0616
SpaceXAI
2026-06-16 $0.223 3.62m 0.0056 39.8 -24.9 39.8 51.5 28.0 13.5 39.8
56 Qwen3.6 27B (Reasoning)
Alibaba
2026-04-22 $0.293 7.64m 0.0075 39.3 -25.4 37.1 53.7 27.0 14.7 39.3
57 MiMo-V2.5
Xiaomi
2026-04-22 $0.0104 3.69m 0.0003 39.2 -25.4 37.2 56.8 23.7 0.2 39.2
58 GPT-5.5 (Non-reasoning)
OpenAI
2026-04-23 $0.206 27s 0.0053 39.2 -25.4 35.4 56.5 25.8 13.1 39.2
59 DeepSeek V4 Flash (Reasoning, High Effort)
DeepSeek
2026-04-24 $0.0505 - 0.0013 39.2 -25.4 37.5 52.0 28.2 7.0 39.2
60 Qwen3.7 Plus
Alibaba
2026-06-01 $0.226 6.68m 0.0059 38.5 -26.1 39.0 55.9 20.8 13.5 38.5
61 GPT-5.6 Terra (Non-reasoning)
OpenAI
2026-07-09 $0.103 23s 0.0027 38.5 -26.1 34.0 52.3 29.3 10.1 38.5
62 Nemotron 3 Ultra 550B A55B (Reasoning)
NVIDIA
2026-06-04 $0.413 2.61m 0.0108 38.1 -26.5 37.8 49.3 27.4 16.2 38.1
63 Claude 4.5 Sonnet (Reasoning)
Anthropic
2025-09-29 $0.462 4.99m 0.0122 37.7 -26.9 36.4 52.1 24.6 16.6 37.7
64 Gemini 3.5 Flash-Lite
Google
2026-07-21 $0.0961 36s 0.0026 37.5 -27.1 36.5 49.3 26.8 9.8 37.5
65 GPT-5.1 (high)
OpenAI
2025-11-13 $0.300 3.65m 0.0084 35.8 -28.9 36.9 49.4 21.0 14.8 35.8
66 GLM-4.7 (Reasoning)
Z AI
2025-12-22 $0.353 3.76m 0.0101 34.8 -29.9 33.7 45.3 25.4 15.5 34.8
67 Grok 4.3 (high)
SpaceXAI
2026-04-30 $0.145 1.82m 0.0042 34.6 -30.0 37.6 42.2 24.1 11.6 34.6
68 Kimi K2.5 (Reasoning)
Kimi
2026-01-27 $0.0957 3.56m 0.0028 34.6 -30.0 35.4 46.8 21.7 9.8 34.6
69 GPT-5.6 Luna (low)
OpenAI
2026-07-09 $0.00883 17s 0.0003 34.3 -30.4 33.3 44.2 25.4 0.0 34.3
70 Qwen3.5 397B A17B (Reasoning)
Alibaba
2026-02-16 $0.359 4.01m 0.0106 33.9 -30.7 33.7 48.2 19.8 15.5 33.9
71 LongCat 2.0
LongCat
2026-06-29 $0.122 7.29m 0.0036 33.5 -31.1 33.5 45.3 21.8 10.9 33.5
72 Qwen3.6 27B (Non-reasoning)
Alibaba
2026-04-22 $0.396 3.35m 0.0118 33.5 -31.2 30.5 46.6 23.3 16.0 33.5
73 Qwen3.5 122B A10B (Reasoning)
Alibaba
2026-02-24 $0.257 2.01m 0.0078 32.9 -31.7 32.3 45.7 20.7 14.1 32.9
74 GPT-5 (high)
OpenAI
2025-08-07 $0.257 3.09m 0.0079 32.7 -31.9 34.7 37.8 25.7 14.1 32.7
75 Mistral Medium 3.5
Mistral
2026-04-29 $0.460 2.85m 0.0144 31.9 -32.7 29.9 46.9 19.0 16.6 31.9
76 Qwen3.6 35B A3B (Reasoning)
Alibaba
2026-04-16 $0.194 3.45m 0.0061 31.6 -33.0 31.6 41.9 21.4 12.9 31.6
77 Ring-2.6-1T
InclusionAI
2026-05-08 $0.366 - 0.0119 30.8 -33.9 30.6 42.8 18.9 15.6 30.8
78 GLM-4.6 (Reasoning)
Z AI
2025-09-30 $0.302 5.28m 0.0098 30.7 -33.9 28.7 45.8 17.7 14.8 30.7
79 Step 3.7 Flash
StepFun
2026-05-29 $0.0906 2.24m 0.0030 30.5 -34.2 30.3 39.6 21.5 9.6 30.5
80 Claude 4.5 Haiku (Reasoning)
Anthropic
2025-10-15 $0.216 3.19m 0.0072 30.0 -34.7 29.6 43.9 16.4 13.4 30.0
81 GPT-5.6 Luna (Non-reasoning)
OpenAI
2026-07-09 $0.0118 15s 0.0004 29.3 -35.4 26.6 39.3 22.0 0.7 29.3
82 Qwen3.5 122B A10B (Non-reasoning)
Alibaba
2026-02-24 $0.193 1.01m 0.0067 28.9 -35.7 27.6 43.3 15.8 12.8 28.9
83 Grok 4.3 (Non-reasoning)
SpaceXAI
2026-04-30 $0.294 1.26m 0.0107 27.6 -37.1 24.8 35.2 22.8 14.7 27.6
84 GPT-5.5 Instant (June 2026)
OpenAI
2026-06-25 $0.537 - 0.0203 26.4 -38.2 28.9 39.4 11.0 17.3 26.4
85 Gemma 4 26B A4B (Reasoning)
Google
2026-04-02 $0.0439 - 0.0017 25.3 -39.3 25.7 39.3 11.0 6.4 25.3
86 Qwen3.5 35B A3B (Non-reasoning)
Alibaba
2026-02-24 $0.241 1.23m 0.0099 24.3 -40.4 24.0 37.0 11.8 13.8 24.3
87 NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
NVIDIA
2026-03-11 $0.231 3.00m 0.0097 23.9 -40.7 25.4 37.7 8.7 13.6 23.9
88 Qwen3.6 35B A3B (Non-reasoning)
Alibaba
2026-04-16 $0.630 1.75m 0.0265 23.8 -40.8 24.2 28.1 19.1 18.0 23.8
89 gpt-oss-120b (high)
OpenAI
2025-08-05 $0.0750 2.91m 0.0033 22.5 -42.2 23.8 30.4 13.2 8.8 22.5
90 Gemini 2.5 Pro
Google
2025-06-05 $0.215 1.42m 0.0098 22.1 -42.6 25.8 33.3 7.1 13.3 22.1
91 Qwen3 Coder Next
Alibaba
2026-02-03 $0.334 1.81m 0.0152 22.0 -42.6 21.1 36.2 8.8 15.2 22.0
92 Gemini 3.1 Flash-Lite
Google
2026-03-03 $0.0431 1.05m 0.0020 22.0 -42.7 25.0 34.7 6.2 6.3 22.0
93 Gemma 4 31B (Non-reasoning)
Google
2026-04-02 $0.0369 1.10m 0.0017 22.0 -42.7 21.8 33.2 11.0 5.7 22.0
94 Nova 2.0 Pro Preview (medium)
Amazon
2025-11-27 $0.183 1.74m 0.0088 20.9 -43.7 21.8 34.0 7.0 12.6 20.9
95 Mercury 2
Inception
2026-02-20 $0.0791 38s 0.0038 20.7 -43.9 21.4 31.1 9.6 9.0 20.7
96 Gemma 4 12B (Reasoning)
Google
2026-06-03 $0.0763 3.79m 0.0038 20.2 -44.4 21.8 31.0 7.9 8.8 20.2
97 GPT-5 mini (high)
OpenAI
2025-08-07 $0.0361 2.33m 0.0018 20.1 -44.6 25.3 15.6 19.4 5.6 20.1
98 Qwen3.5 9B (Reasoning)
Alibaba
2026-03-02 $0.243 5.94m 0.0127 19.2 -45.5 21.4 28.7 7.4 13.9 19.2
99 Nova 2.0 Pro Preview (low)
Amazon
2025-11-27 $0.227 44s 0.0131 17.3 -47.3 19.6 25.9 6.4 13.6 17.3
100 Mistral Small 4 (Reasoning)
Mistral
2026-03-16 $0.101 2.06m 0.0059 17.0 -47.7 19.6 26.6 4.7 10.0 17.0