Kimi K3.1 Pro (max): benchmark scores, price and ranking
Kimi K3.1 Pro (max) from Moonshot ranks #21 of 827 LLMs on the LLMs Tiger aggregate benchmark score (55.5), based on 4 benchmark results captured up to 2026-11-18.
- Organisation
- Moonshot
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2026-10-23 (source: epoch)
- Cheapest API price
- $0.240 in / $8.40 out per million tokens (via openrouter, observed 2026-11-18T15:47Z)
- Aggregate rank
- #21 of 827 (score 55.5)
Relative to other models, Kimi K3.1 Pro (max) is strongest on LMCA (#9 of 113) and weakest on GDP.pdf (#12 of 37).
Across the 4 benchmarks where at least ten models are scored, Kimi K3.1 Pro (max) is in the top 10% on 1 and in the top half on 4.
Its cheapest listed input price, $0.240 per million tokens, is lower than that of 67% of the 443 models with a listed price.
Kimi K3.1 Pro (max) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| LMCA | 57.6% | #9 of 113 | Epoch AI Benchmarking Hub | 2026-11-18 |
| ALE-Bench | 1,933 | #10 of 93 | Epoch AI Benchmarking Hub | 2026-11-18 |
| DTBench | 93.3% | #19 of 151 | Epoch AI Benchmarking Hub | 2026-11-18 |
| GDP.pdf | 46.6% | #12 of 37 | Epoch AI Benchmarking Hub | 2026-11-18 |
About Kimi K3.1 Pro (max)
Kimi K3.1 Pro (max) is an open-weight model that can run on your own hardware from Moonshot. It was released on 2026-10-23, according to Epoch AI. The cheapest API listing we track charges $0.240 per million input tokens and $8.40 per million output tokens, through openrouter. We hold 4 benchmark results for it across 3 areas, and 1 is in the top tenth of its board.
Where Kimi K3.1 Pro (max) stands
On our aggregate score, Kimi K3.1 Pro (max) is #21 of 827 ranked models, in the top fifty. Its score is 55.5; the scale is centred on 50, so it sits 5.5 points above the typical model. That beats 97% of the ranked field. Among the 15 ranked Moonshot models it is #1. The next one down is Kimi K3.1 Pro (Together, max) at 55.3.
Kimi K3.1 Pro (max), benchmark by benchmark
On LMCA, Kimi K3.1 Pro (max) scores 57.6% and ranks #9 of 113. Only 8 models score higher, led by Claude Sonnet 5.5 (max) at 68.3%, which is 10.7 points ahead. It covers language-model capability assessment. The board median is 29.5%, so Kimi K3.1 Pro (max) is 28.1 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-11-18.
On ALE-Bench, Kimi K3.1 Pro (max) reaches 1,933. It ranks #10 of 93, ahead of 89% of the field, and 1,019 points behind GPT-6 Astra (max) at 2,951. The results either side are GPT-5.5 (xhigh) (1,943) and Gemini 4 Hydrogen (xhigh) (1,826). It covers AtCoder heuristic-optimisation contests (performance rating). The board median is 800, so Kimi K3.1 Pro (max) is 1,133 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-11-18.
Kimi K3.1 Pro (max) manages 93.3% on DTBench, good for #19 of 151. Claude Opus 5.5 (max) leads at 98.9%, 5.6 points further up, and 87% of models sit below. The results either side are GPT-5.6 Terra (max) (93.3%) and Claude Sonnet 5 (max) (92.5%). It covers dynamic tool-use benchmark. The board median is 70.9%, so Kimi K3.1 Pro (max) is 22.4 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-11-18.
GDP.pdf puts Kimi K3.1 Pro (max) at 46.6%, #12 of 37. That beats 68% of the models tested, but 9.8 points short of Gemini 4 Carbon (high) (56.4%). The results either side are Grok 4.7 (xhigh) (48.8%) and Gemini 3.8 Flash (high) (44.2%). It covers economically valuable document tasks. The board median is 32.8%, so Kimi K3.1 Pro (max) is 13.8 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-11-18.
Strengths and weaknesses
Agents and tool use: strong, ahead of 77% of the field on average across 2 benchmarks. Its best board here is DTBench (#19 of 151) and its weakest is GDP.pdf (#12 of 37).
Price and value
The median input price across the 443 priced models is $0.482 per million tokens, so Kimi K3.1 Pro (max) costs less than the typical listing. Models that score within 1.5 points or better and cost less: DeepSeek V4.1 Flash 1017 (max) ($0.036, 55.5), Claude Haiku 5.5 (max) ($0.100, 54.3), Kimi K3 (max) ($0.192, 55.2). Similar scores cost more on Muse Spark Open (xhigh) ($1.25) and Muse Spark 1.3 (max) ($1.25).
Release history
The Moonshot model released before it was Kimi K3 (max) on 2026-07-16, which scores 55.2. The next one was Kimi K3.1 Pro (Together, max) on 2026-10-23, at 55.3.
Reading these numbers
The 4 scores on this page come from 1 source: Epoch AI Benchmarking Hub (4). No official leaderboard supplied any of them, so treat them as third-party measurements. The leaderboard also lists 3 other reasoning-effort settings of this model, which redirect here. This page shows the highest. With 4 results the aggregate rank can move a lot when one new score arrives.
Kimi K3.1 Pro (max) is also listed at 3 other reasoning-effort settings; this page shows the highest-effort row, which is the one the leaderboard keeps by default.
Models ranked nearby
- #18 GPT-5.5 (xhigh) (56.1)
- #19 GPT-5.4 (xhigh) (55.9)
- #20 DeepSeek V4.1 Flash 1017 (max) (55.5)
- #22 gemini-3.1-pro-preview-high (55.3)
- #23 Kimi K3.1 Pro (Together, max) (55.3)
- #24 Kimi K3 (max) (55.2)
More from Moonshot
- Kimi K3.1 Pro (Together, max) (#23, 55.3)
- Kimi K3 (max) (#24, 55.2)
- Kimi K2.5 (Fireworks) (#68, 52.6)
- Kimi K2.5 (#243, 50.3)
- Kimi K2 Thinking Turbo (#245, 50.3)
- Kimi K2 Thinking (Together) (#278, 49.7)
Compare it on the live leaderboard → · How the aggregate score works