Run #905

success · fetched 2026-07-13 15:00:47 · 1.28 MB raw HTML · 572 models

Open this run in comparison view · JSON results

Top quality: GPT-5.6 Sol (max) (63.4 pts)

Cost/task vs quality?

84 models · 11 on the Pareto frontier · combined quality vs Cost per Task

117345067$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: $2.75 · Time/task: 5.30m · Quality: 63.1Claude Opus 4.8 (Adaptive Reasoning, Max Effort) · Cost/task: $1.80 · Time/task: 6.90m · Quality: 59.0GPT-5.5 (xhigh) · Cost/task: $0.992 · Time/task: 3.48m · Quality: 58.2Claude Sonnet 5 (Adaptive Reasoning, Max Effort) · Cost/task: $1.53 · Time/task: 8.64m · Quality: 57.2Claude Opus 4.7 (Adaptive Reasoning, Max Effort) · Cost/task: $1.97 · Time/task: 6.13m · Quality: 57.2GPT-5.5 (high) · Cost/task: $0.668 · Time/task: 2.20m · Quality: 56.1GPT-5.6 Terra (xhigh) · Cost/task: $0.327 · Time/task: 1.42m · Quality: 55.6GPT-5.4 (xhigh) · Cost/task: $0.887 · Time/task: 3.29m · Quality: 54.5GLM-5.2 (max) · Cost/task: $0.376 · Time/task: 3.08m · Quality: 54.3GPT-5.5 (medium) · Cost/task: $0.406 · Time/task: 1.34m · Quality: 53.2Gemini 3.5 Flash (high) · Cost/task: $0.586 · Time/task: 2.80m · Quality: 52.6Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) · Cost/task: $1.14 · Time/task: 9.64m · Quality: 50.3Qwen3.7 Max · Cost/task: $0.985 · Time/task: 1.60m · Quality: 47.5Claude Sonnet 5 (Non-reasoning, High Effort) · Cost/task: $0.375 · Time/task: 1.46m · Quality: 47.3MiniMax-M3 · Cost/task: $0.125 · Time/task: 3.55m · Quality: 46.1Gemini 3.1 Pro Preview · Cost/task: $0.291 · Time/task: 1.52m · Quality: 45.6GPT-5.5 (low) · Cost/task: $0.211 · Time/task: 36s · Quality: 44.9GPT-5.6 Terra (low) · Cost/task: $0.101 · Time/task: 20s · Quality: 43.1GPT-5.4 mini (xhigh) · Cost/task: $0.452 · Time/task: 7.70m · Quality: 42.1GLM-5.1 (Reasoning) · Cost/task: $0.247 · Time/task: 4.80m · Quality: 41.9Qwen3.6 Plus · Cost/task: $0.314 · Time/task: 6.40m · Quality: 40.5Grok Build 0.1 0616 · Cost/task: $0.212 · Time/task: 3.44m · Quality: 39.8Qwen3.6 27B (Reasoning) · Cost/task: $0.265 · Time/task: 6.74m · Quality: 39.3GPT-5.5 (Non-reasoning) · Cost/task: $0.171 · Time/task: 26s · Quality: 39.2Qwen3.7 Plus · Cost/task: $0.195 · Time/task: 6.64m · Quality: 38.5Nemotron 3 Ultra 550B A55B (Reasoning) · Cost/task: $0.234 · Time/task: 1.79m · Quality: 38.1Claude 4.5 Sonnet (Reasoning) · Cost/task: $0.413 · Time/task: 4.97m · Quality: 37.7GLM-4.7 (Reasoning) · Cost/task: $0.297 · Time/task: 2.48m · Quality: 34.8Grok 4.3 (high) · Cost/task: $0.139 · Time/task: 2.14m · Quality: 34.6Qwen3.5 397B A17B (Reasoning) · Cost/task: $0.333 · Time/task: 3.87m · Quality: 33.9Qwen3.6 27B (Non-reasoning) · Cost/task: $0.359 · Time/task: 3.26m · Quality: 33.5Qwen3.5 122B A10B (Reasoning) · Cost/task: $0.241 · Time/task: 1.78m · Quality: 32.9GPT-5 (high) · Cost/task: $0.238 · Time/task: 2.82m · Quality: 32.7Mistral Medium 3.5 · Cost/task: $1.20 · Time/task: 2.69m · Quality: 31.9Qwen3.6 35B A3B (Reasoning) · Cost/task: $0.179 · Time/task: 2.53m · Quality: 31.6Ring-2.6-1T · Cost/task: $0.345 · Time/task: 3.21m · Quality: 30.8GLM-4.6 (Reasoning) · Cost/task: $0.283 · Time/task: 6.27m · Quality: 30.7Claude 4.5 Haiku (Reasoning) · Cost/task: $0.272 · Time/task: 2.81m · Quality: 30.0Qwen3.5 122B A10B (Non-reasoning) · Cost/task: $0.177 · Time/task: 52s · Quality: 28.9Grok 4.3 (Non-reasoning) · Cost/task: $0.293 · Time/task: 1.31m · Quality: 27.6GPT-5.5 Instant (June 2026) · Cost/task: $0.711 · Time/task: - · Quality: 26.4Gemma 4 26B A4B (Reasoning) · Cost/task: $0.0294 · Time/task: - · Quality: 25.3NVIDIA Nemotron 3 Super 120B A12B (Reasoning) · Cost/task: $0.206 · Time/task: 1.68m · Quality: 23.9gpt-oss-120b (high) · Cost/task: $0.0607 · Time/task: 1.89m · Quality: 22.5Gemini 2.5 Pro · Cost/task: $0.198 · Time/task: 1.36m · Quality: 22.1Qwen3 Coder Next · Cost/task: $0.329 · Time/task: 2.35m · Quality: 22.0Gemini 3.1 Flash-Lite · Cost/task: $0.0416 · Time/task: 1.08m · Quality: 22.0Gemma 4 31B (Non-reasoning) · Cost/task: $0.0343 · Time/task: 1.37m · Quality: 22.0Nova 2.0 Pro Preview (medium) · Cost/task: $0.173 · Time/task: 1.51m · Quality: 20.9Qwen3.5 9B (Reasoning) · Cost/task: $0.164 · Time/task: 7.63m · Quality: 19.2Nova 2.0 Pro Preview (low) · Cost/task: $0.213 · Time/task: 39s · Quality: 17.3HyperNova 60B 2605 · Cost/task: $0.0180 · Time/task: 1.33m · Quality: 15.9DeepSeek R1 (Jan '25) · Cost/task: $0.247 · Time/task: - · Quality: 15.4Mistral Small 3.1 · Cost/task: $0.0410 · Time/task: 29s · Quality: 15.4Nova 2.0 Lite (high) · Cost/task: $0.245 · Time/task: 4.69m · Quality: 14.8Mistral Large 3 · Cost/task: $0.0599 · Time/task: 1.01m · Quality: 13.8Mistral Medium 3.1 · Cost/task: $0.145 · Time/task: 59s · Quality: 13.8Magistral Medium 1.2 · Cost/task: $0.747 · Time/task: 3.37m · Quality: 13.7DeepSeek V3 (Dec '24) · Cost/task: $0.0254 · Time/task: - · Quality: 12.9gpt-oss-20b (high) · Cost/task: $0.0178 · Time/task: 1.38m · Quality: 12.9DeepSeek V3 0324 · Cost/task: $0.190 · Time/task: - · Quality: 12.7Nova 2.0 Pro Preview (Non-reasoning) · Cost/task: $0.246 · Time/task: 30s · Quality: 12.7GPT-4.1 mini · Cost/task: $0.0637 · Time/task: 39s · Quality: 12.2Qwen3 Next 80B A3B (Reasoning) · Cost/task: $0.169 · Time/task: 1.82m · Quality: 12.1Llama 4 Maverick · Cost/task: $0.0316 · Time/task: 18s · Quality: 10.6NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) · Cost/task: $0.0183 · Time/task: 4.14m · Quality: 10.2Qwen3 30B A3B 2507 (Reasoning) · Cost/task: $0.0716 · Time/task: 2.63m · Quality: 9.4Ministral 3 14B · Cost/task: $0.149 · Time/task: 2.22m · Quality: 9.2Mistral Small 3.2 · Cost/task: $0.124 · Time/task: 52s · Quality: 8.4GPT-4.1 nano · Cost/task: $0.0399 · Time/task: 40s · Quality: 7.3Llama 3.3 Instruct 70B · Cost/task: $0.0798 · Time/task: 19s · Quality: 7.2Ministral 3 8B · Cost/task: $0.185 · Time/task: 2.33m · Quality: 6.6Ministral 3 3B · Cost/task: $0.126 · Time/task: 1.87m · Quality: 4.4GPT-5.6 Sol (max) · Cost/task: $1.04 · Time/task: 3.55m · Quality: 63.4 · Pareto frontierGPT-5.6 Terra (max) · Cost/task: $0.554 · Time/task: 2.20m · Quality: 59.7 · Pareto frontierGrok 4.5 (high) · Cost/task: $0.311 · Time/task: 1.98m · Quality: 57.3 · Pareto frontierMuse Spark 1.1 (xhigh) · Cost/task: $0.261 · Time/task: 2.73m · Quality: 53.2 · Pareto frontierGPT-5.6 Terra (high) · Cost/task: $0.236 · Time/task: 1.09m · Quality: 52.5 · Pareto frontierGPT-5.6 Terra (medium) · Cost/task: $0.128 · Time/task: 33s · Quality: 49.1 · Pareto frontierDeepSeek V4 Pro (Reasoning, Max Effort) · Cost/task: $0.0448 · Time/task: 8.04m · Quality: 46.7 · Pareto frontierMiMo-V2.5-Pro · Cost/task: $0.0314 · Time/task: 5.50m · Quality: 43.8 · Pareto frontierDeepSeek V4 Flash (Reasoning, Max Effort) · Cost/task: $0.0223 · Time/task: 6.55m · Quality: 42.5 · Pareto frontierMiMo-V2.5 · Cost/task: $0.00975 · Time/task: 3.09m · Quality: 39.2 · Pareto frontierLlama 4 Scout · Cost/task: $0.00851 · Time/task: 11s · Quality: 6.4 · Pareto frontier Llama 4 ScoutMiMo-V2.5DeepSeek V4 Flash…MiMo-V2.5-ProDeepSeek V4 Pro (…GPT-5.6 Terra (me…GPT-5.6 Terra (hi…Muse Spark 1.1 (x…Grok 4.5 (high)GPT-5.6 Terra (ma…GPT-5.6 Sol (max)
#?Pareto?Model?Released?Cost/task?Time/task?$/Q?Qual?ΔTop?Intel?Code?Agent?Pen?Score?
1 GPT-5.6 Sol (max)
OpenAI
2026-07-09 $1.04 3.55m 0.0164 63.4 0.0 58.9 77.4 54.0 20.2 63.4
2 Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
Anthropic
2026-06-09 $2.75 5.30m 0.0436 63.1 -0.4 59.9 76.5 52.8 24.4 63.1
3 GPT-5.6 Terra (max)
OpenAI
2026-07-09 $0.554 2.20m 0.0093 59.7 -3.8 55.0 76.7 47.4 17.4 59.7
4 Claude Opus 4.8 (Adaptive Reasoning, Max Effort)
Anthropic
2026-05-28 $1.80 6.90m 0.0304 59.0 -4.4 55.7 74.3 47.2 22.5 59.0
5 GPT-5.5 (xhigh)
OpenAI
2026-04-23 $0.992 3.48m 0.0171 58.2 -5.2 54.8 74.9 44.9 20.0 58.2
6 Grok 4.5 (high)
SpaceXAI
2026-07-08 $0.311 1.98m 0.0054 57.3 -6.1 53.8 72.4 45.7 14.9 57.3
7 Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
Anthropic
2026-06-30 $1.53 8.64m 0.0267 57.2 -6.2 53.4 71.5 46.7 21.8 57.2
8 Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
Anthropic
2026-04-16 $1.97 6.13m 0.0345 57.2 -6.3 53.5 73.6 44.4 23.0 57.2
9 GPT-5.5 (high)
OpenAI
2026-04-23 $0.668 2.20m 0.0119 56.1 -7.4 53.1 71.6 43.5 18.2 56.1
10 GPT-5.6 Terra (xhigh)
OpenAI
2026-07-09 $0.327 1.42m 0.0059 55.6 -7.8 51.6 70.6 44.7 15.1 55.6
11 GPT-5.4 (xhigh)
OpenAI
2026-03-05 $0.887 3.29m 0.0163 54.5 -8.9 51.4 71.1 41.1 19.5 54.5
12 GLM-5.2 (max)
Z AI
2026-06-16 $0.376 3.08m 0.0069 54.3 -9.1 51.1 68.8 43.1 15.8 54.3
13 GPT-5.5 (medium)
OpenAI
2026-04-23 $0.406 1.34m 0.0076 53.2 -10.2 50.4 71.5 37.8 16.1 53.2
14 Muse Spark 1.1 (xhigh)
Meta
2026-07-09 $0.261 2.73m 0.0049 53.2 -10.3 50.6 71.3 37.5 14.2 53.2
15 Gemini 3.5 Flash (high)
Google
2026-05-19 $0.586 2.80m 0.0111 52.6 -10.8 50.2 70.1 37.4 17.7 52.6
16 GPT-5.6 Terra (high)
OpenAI
2026-07-09 $0.236 1.09m 0.0045 52.5 -11.0 49.0 67.1 41.3 13.7 52.5
17 Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)
Anthropic
2026-02-17 $1.14 9.64m 0.0226 50.3 -13.1 47.2 63.0 40.8 20.6 50.3
18 GPT-5.6 Terra (medium)
OpenAI
2026-07-09 $0.128 33s 0.0026 49.1 -14.3 45.6 64.7 37.0 11.1 49.1
19 Qwen3.7 Max
Alibaba
2026-05-19 $0.985 1.60m 0.0207 47.5 -15.9 46.0 66.0 30.6 19.9 47.5
20 Claude Sonnet 5 (Non-reasoning, High Effort)
Anthropic
2026-06-30 $0.375 1.46m 0.0079 47.3 -16.2 41.7 66.4 33.7 15.7 47.3
21 DeepSeek V4 Pro (Reasoning, Max Effort)
DeepSeek
2026-04-24 $0.0448 8.04m 0.0010 46.7 -16.8 44.3 59.4 36.4 6.5 46.7
22 MiniMax-M3
MiniMax
2026-06-01 $0.125 3.55m 0.0027 46.1 -17.3 44.4 58.6 35.4 11.0 46.1
23 Gemini 3.1 Pro Preview
Google
2026-02-19 $0.291 1.52m 0.0064 45.6 -17.9 46.5 68.8 21.4 14.6 45.6
24 GPT-5.5 (low)
OpenAI
2026-04-23 $0.211 36s 0.0047 44.9 -18.5 43.5 60.9 30.4 13.2 44.9
25 MiMo-V2.5-Pro
Xiaomi
2026-04-22 $0.0314 5.50m 0.0007 43.8 -19.6 42.2 60.2 29.1 5.0 43.8
26 GPT-5.6 Terra (low)
OpenAI
2026-07-09 $0.101 20s 0.0023 43.1 -20.4 40.5 58.1 30.6 10.0 43.1
27 DeepSeek V4 Flash (Reasoning, Max Effort)
DeepSeek
2026-04-24 $0.0223 6.55m 0.0005 42.5 -20.9 40.3 56.2 31.1 3.5 42.5
28 GPT-5.4 mini (xhigh)
OpenAI
2026-03-17 $0.452 7.70m 0.0107 42.1 -21.4 40.0 56.1 30.2 16.6 42.1
29 GLM-5.1 (Reasoning)
Z AI
2026-04-07 $0.247 4.80m 0.0059 41.9 -21.5 40.2 55.8 29.9 13.9 41.9
30 Qwen3.6 Plus
Alibaba
2026-04-02 $0.314 6.40m 0.0077 40.5 -22.9 39.6 54.5 27.6 15.0 40.5
31 Grok Build 0.1 0616
SpaceXAI
- $0.212 3.44m 0.0053 39.8 -23.7 39.8 51.5 28.0 13.3 39.8
32 Qwen3.6 27B (Reasoning)
Alibaba
2026-04-22 $0.265 6.74m 0.0068 39.3 -24.2 37.1 53.7 27.0 14.2 39.3
33 MiMo-V2.5
Xiaomi
2026-04-22 $0.00975 3.09m 0.0002 39.2 -24.2 37.2 56.8 23.7 0.0 39.2
34 GPT-5.5 (Non-reasoning)
OpenAI
2026-04-23 $0.171 26s 0.0044 39.2 -24.2 35.4 56.5 25.8 12.3 39.2
35 Qwen3.7 Plus
Alibaba
2026-06-01 $0.195 6.64m 0.0051 38.5 -24.9 39.0 55.9 20.8 12.9 38.5
36 Nemotron 3 Ultra 550B A55B (Reasoning)
NVIDIA
2026-06-04 $0.234 1.79m 0.0061 38.1 -25.3 37.8 49.3 27.4 13.7 38.1
37 Claude 4.5 Sonnet (Reasoning)
Anthropic
2025-09-29 $0.413 4.97m 0.0110 37.7 -25.7 36.4 52.1 24.6 16.2 37.7
38 GLM-4.7 (Reasoning)
Z AI
2025-12-22 $0.297 2.48m 0.0086 34.8 -28.6 33.7 45.3 25.4 14.7 34.8
39 Grok 4.3 (high)
SpaceXAI
2026-04-30 $0.139 2.14m 0.0040 34.6 -28.8 37.6 42.2 24.1 11.4 34.6
40 Qwen3.5 397B A17B (Reasoning)
Alibaba
2026-02-16 $0.333 3.87m 0.0098 33.9 -29.5 33.7 48.2 19.8 15.2 33.9
41 Qwen3.6 27B (Non-reasoning)
Alibaba
2026-04-22 $0.359 3.26m 0.0107 33.5 -30.0 30.5 46.6 23.3 15.6 33.5
42 Qwen3.5 122B A10B (Reasoning)
Alibaba
2026-02-24 $0.241 1.78m 0.0073 32.9 -30.5 32.3 45.7 20.7 13.8 32.9
43 GPT-5 (high)
OpenAI
2025-08-07 $0.238 2.82m 0.0073 32.7 -30.7 34.7 37.8 25.7 13.8 32.7
44 Mistral Medium 3.5
Mistral
2026-04-29 $1.20 2.69m 0.0374 31.9 -31.5 29.9 46.9 19.0 20.8 31.9
45 Qwen3.6 35B A3B (Reasoning)
Alibaba
2026-04-16 $0.179 2.53m 0.0056 31.6 -31.8 31.6 41.9 21.4 12.5 31.6
46 Ring-2.6-1T
InclusionAI
2026-05-08 $0.345 3.21m 0.0112 30.8 -32.7 30.6 42.8 18.9 15.4 30.8
47 GLM-4.6 (Reasoning)
Z AI
2025-09-30 $0.283 6.27m 0.0092 30.7 -32.7 28.7 45.8 17.7 14.5 30.7
48 Claude 4.5 Haiku (Reasoning)
Anthropic
2025-10-15 $0.272 2.81m 0.0091 30.0 -33.5 29.6 43.9 16.4 14.3 30.0
49 Qwen3.5 122B A10B (Non-reasoning)
Alibaba
2026-02-24 $0.177 52s 0.0061 28.9 -34.5 27.6 43.3 15.8 12.5 28.9
50 Grok 4.3 (Non-reasoning)
SpaceXAI
2026-04-30 $0.293 1.31m 0.0106 27.6 -35.8 24.8 35.2 22.8 14.7 27.6
51 GPT-5.5 Instant (June 2026)
OpenAI
2026-06-25 $0.711 - 0.0269 26.4 -37.0 28.9 39.4 11.0 18.5 26.4
52 Gemma 4 26B A4B (Reasoning)
Google
2026-04-02 $0.0294 - 0.0012 25.3 -38.1 25.7 39.3 11.0 4.7 25.3
53 NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
NVIDIA
2026-03-11 $0.206 1.68m 0.0086 23.9 -39.5 25.4 37.7 8.7 13.1 23.9
54 gpt-oss-120b (high)
OpenAI
2025-08-05 $0.0607 1.89m 0.0027 22.5 -40.9 23.8 30.4 13.2 7.8 22.5
55 Gemini 2.5 Pro
Google
2025-06-05 $0.198 1.36m 0.0090 22.1 -41.4 25.8 33.3 7.1 13.0 22.1
56 Qwen3 Coder Next
Alibaba
2026-02-03 $0.329 2.35m 0.0149 22.0 -41.4 21.1 36.2 8.8 15.2 22.0
57 Gemini 3.1 Flash-Lite
Google
2026-03-03 $0.0416 1.08m 0.0019 22.0 -41.5 25.0 34.7 6.2 6.2 22.0
58 Gemma 4 31B (Non-reasoning)
Google
2026-04-02 $0.0343 1.37m 0.0016 22.0 -41.5 21.8 33.2 11.0 5.4 22.0
59 Nova 2.0 Pro Preview (medium)
Amazon
2025-11-27 $0.173 1.51m 0.0083 20.9 -42.5 21.8 34.0 7.0 12.4 20.9
60 Qwen3.5 9B (Reasoning)
Alibaba
2026-03-02 $0.164 7.63m 0.0085 19.2 -44.3 21.4 28.7 7.4 12.1 19.2
61 Nova 2.0 Pro Preview (low)
Amazon
2025-11-27 $0.213 39s 0.0123 17.3 -46.1 19.6 25.9 6.4 13.3 17.3
62 HyperNova 60B 2605
Multiverse Computing
2026-05-26 $0.0180 1.33m 0.0011 15.9 -47.5 17.8 23.2 6.7 2.5 15.9
63 DeepSeek R1 (Jan '25)
DeepSeek
2025-01-20 $0.247 - 0.0160 15.4 -48.0 18.5 24.6 3.1 13.9 15.4
64 Mistral Small 3.1
Mistral
2025-03-17 $0.0410 29s 0.0027 15.4 -48.0 14.7 26.3 5.2 6.1 15.4
65 Nova 2.0 Lite (high)
Amazon
2025-10-29 $0.245 4.69m 0.0166 14.8 -48.6 18.2 23.0 3.1 13.9 14.8
66 Mistral Large 3
Mistral
2025-12-02 $0.0599 1.01m 0.0043 13.8 -49.6 15.9 20.1 5.5 7.8 13.8
67 Mistral Medium 3.1
Mistral
2025-08-12 $0.145 59s 0.0105 13.8 -49.6 14.7 20.5 6.2 11.6 13.8
68 Magistral Medium 1.2
Mistral
2025-09-18 $0.747 3.37m 0.0546 13.7 -49.7 17.9 21.3 1.9 18.7 13.7
69 DeepSeek V3 (Dec '24)
DeepSeek
2024-12-26 $0.0254 - 0.0020 12.9 -50.5 14.2 23.0 1.6 4.0 12.9
70 gpt-oss-20b (high)
OpenAI
2025-08-05 $0.0178 1.38m 0.0014 12.9 -50.5 14.9 20.7 3.1 2.5 12.9
71 DeepSeek V3 0324
DeepSeek
2025-03-25 $0.190 - 0.0149 12.7 -50.7 15.4 21.2 1.5 12.8 12.7
72 Nova 2.0 Pro Preview (Non-reasoning)
Amazon
2025-11-27 $0.246 30s 0.0194 12.7 -50.7 14.4 20.9 2.9 13.9 12.7
73 GPT-4.1 mini
OpenAI
2025-04-14 $0.0637 39s 0.0052 12.2 -51.2 14.8 20.2 1.7 8.0 12.2
74 Qwen3 Next 80B A3B (Reasoning)
Alibaba
2025-09-11 $0.169 1.82m 0.0140 12.1 -51.4 16.7 17.4 2.1 12.3 12.1
75 Llama 4 Maverick
Meta
2025-04-05 $0.0316 18s 0.0030 10.6 -52.8 14.3 16.3 1.3 5.0 10.6
76 NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
NVIDIA
2025-12-15 $0.0183 4.14m 0.0018 10.2 -53.2 14.2 14.4 2.0 2.6 10.2
77 Qwen3 30B A3B 2507 (Reasoning)
Alibaba
2025-07-30 $0.0716 2.63m 0.0076 9.4 -54.0 14.4 12.1 1.8 8.6 9.4
78 Ministral 3 14B
Mistral
2025-12-02 $0.149 2.22m 0.0162 9.2 -54.2 11.1 14.4 2.2 11.7 9.2
79 Mistral Small 3.2
Mistral
2025-06-20 $0.124 52s 0.0148 8.4 -55.1 10.6 12.5 2.0 10.9 8.4
80 GPT-4.1 nano
OpenAI
2025-04-14 $0.0399 40s 0.0055 7.3 -56.1 9.6 11.1 1.2 6.0 7.3
81 Llama 3.3 Instruct 70B
Meta
2024-12-06 $0.0798 19s 0.0110 7.2 -56.2 9.4 11.9 0.3 9.0 7.2
82 Ministral 3 8B
Mistral
2025-12-02 $0.185 2.33m 0.0279 6.6 -56.8 9.0 9.7 1.2 12.7 6.6
83 Llama 4 Scout
Meta
2025-04-05 $0.00851 11s 0.0013 6.4 -57.0 10.0 8.2 1.1 0.0 6.4
84 Ministral 3 3B
Mistral
2025-12-02 $0.126 1.87m 0.0288 4.4 -59.0 6.8 4.8 1.6 11.0 4.4