The Inference Report

November 8, 2026

Daily rankings from SWE-rebench, a benchmark designed to fairly compare LLM capabilities on real-world software engineering tasks. Unlike other evaluations, it uses a standardized scaffolding for all models, continuously updates its dataset to prevent contamination, and runs each model five times to account for stochastic variance.

#ModelScore
1AnthropicFable 5 [high]Model64.5%± 1.41%
2GrokGrok 4.5 [high]Model63.8%± 0.60%
3AnthropicOpus 5 [high]Model63.4%± 1.35%
4Z.aiGLM-5.2 [high]Model62.9%± 1.19%
5OpenAIGPT-5.6 Sol [medium]Model62.3%± 1.83%
6JunieJunieAgent61.8%± 0.54%
7AnthropicClaude CodeAgent60.4%± 1.03%
8OpenAICodexAgent58.0%± 1.29%
9AnthropicSonnet 5 [high]Model56.8%± 0.94%
10CursorCursorAgent51.7%± 0.84%

Artificial Analysis composite index across coding, math, and reasoning benchmarks.

#ModelScoretok/s$/1M
1Gemini 4 Carbon6092$8.00
2Claude Opus 5.559.195$8.00
3GPT-6 Astra56.950$20.00
4GPT-6.1 Sol54.667$4.00
5Claude Sonnet 5.554.5136$4.00
6GPT-6.1 Terra51.3113$2.00
7Gemini 4 Argon50.490$8.00
8Muse Wonder Full50.1——
9Claude Fable 5.15061$20.00
10Kimi K3.1 Pro46.528$4.00

Output tokens per second — higher is faster. Minimum intelligence score of 40.

#Modeltok/s
1Muse Wonder144
2Claude Sonnet 5.5136
3GPT-6 Sol132
4GPT-6.1 Terra113
5Claude Opus 5.595
6Gemini 4 Carbon92
7Gemini 4 Argon90
8GPT-6.1 Sol67
9Claude Fable 5.161
10GPT-6 Astra50

Blended cost per 1M tokens (3:1 input/output) — lower is cheaper. Minimum intelligence score of 40.

#Model$/1M
1GPT-6.1 Terra$2.00
2GPT-6.1 Sol$4.00
3Claude Sonnet 5.5$4.00
4Kimi K3.1 Pro$4.00
5GPT-6 Sol$4.00
6Gemini 4 Carbon$8.00
7Claude Opus 5.5$8.00
8Gemini 4 Argon$8.00
9Muse Wonder$8.00
10Claude Opus 5$10.00