Kimi K3.1 Pro: benchmarks, price and rank
Kimi K3.1 Pro from Moonshot is 14th of 123 rated AI models on Spezia's leaderboard, strongest on BrowseComp and MMMU-Pro. It costs $2 in, $10 out per million tokens.
- 14th of 123 rated models
- Rating 1,722
- First on 3 of 13 benchmarks
- Open weights
- Released Oct 23, 2026
- 1 million tokens of context
Where it is strongest
- 1st of 56 on BrowseComp
- 1st of 51 on MMMU-Pro
- 10th of 98 on LMArena WebDev
- 1st of 5 on GDPval-AA
Where it falls behind
- 5th of 8 on ExploitGym
Price: $2 in, $10 out per million tokens.
Its headline results
The benchmarks that count most in the rating, with its place among the models measured the same way, and where each number came from.
- APEX-Agents65.5%
Long tasks written by investment banking analysts, management consultants and corporate lawyers from their own work, done across files and apps in a realistic work setup.
12th of 56. Independent result from Epoch AI.
- Terminal-Bench 4.065.7%
Hard jobs done in a real computer terminal: building and fixing software, setting up systems, and science and engineering problems.
4th of 17. The maker's own number, from Moonshot AI, via LLM Stats.
- BrowseComp92.1%
Questions whose answers are hidden deep on the web and take many searches and pages to track down.
1st of 56. The maker's own number, from Moonshot AI, via LLM Stats.
- Humanity's Last Exam51.1%
About 2,500 questions written by experts in more than a hundred fields to be as hard as they could make them, many needing a diagram or image.
17th of 74. The maker's own number, from Moonshot AI, via LLM Stats.
- GDPval-AA1,846
Work products from dozens of occupations, the kind of documents, spreadsheets and plans professionals hand in, made by the model and compared head to head with other models' work.
1st of 5. The maker's own number, from Moonshot AI, via LLM Stats.
- SimpleQA Verified62.2%
Short factual questions with one checked answer, asked without web search.
17th of 78. Independent result from Epoch AI.
- FrontierMath78.3%
Hundreds of new, unpublished math problems written by mathematicians, from hard undergraduate level up to research, with answers a computer can check.
23rd of 76. Independent result from Epoch AI.
- MMMU-Pro84.1%
College exam questions that need a picture to answer, such as charts, diagrams, maps and chemical structures, with more answer options than the original MMMU and some questions shown only as a screenshot.
1st of 51. The maker's own number, from Moonshot AI, via LLM Stats.
- CharXiv Reasoning89%
Questions about real charts from scientific papers that need reasoning across the chart, not just reading off a value.
9th of 45. The maker's own number, from Moonshot AI, via LLM Stats.
- LMArena text1,457
People put a question to two anonymous models and vote for the better answer.
34th of 107. Independent result from LMArena.
6 more results in its full profile.
Every result with its source, what it costs per task, what jumped with its release, side by side with any other model, and answers to your questions about when to use it.
Models ranked near it
How the rating works, and every benchmark it uses: the model leaderboard.