Kimi K3.1 Pro
Moonshot AI
79.2#18 of 427 overall
- Input / output
- US$ 2,00 / US$ 10,00 US$ per 1M tokens
- Context
- 1.0M tokens
- Release
- 10/23/2026 release date
- Weights
- Closed
- Speed
- 30 tok/s first token in 2.67 s
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| LiveBench weight 3 | 71.3 | 71% | LiveBench |
| AA Intelligence Index weight 3 | 46.0 | 79% | Artificial Analysis |
| Arena WebDev (Elo) weight 1 | 1695 | 94% | LMArena |
| Humanity's Last Exam weight 1 | 52.5 | 98% | Artificial Analysis |
| Terminal-Bench weight 1 | 67.2 | 100% | Artificial Analysis |
| Long-context reasoning | 86.3 | 100% | Artificial Analysis |
| LiveBench long agentic | 39.1 | 65% | LiveBench |
| LiveBench reasoning | 91.1 | 77% | LiveBench |
| LiveBench coding | 81.8 | 36% | LiveBench |
| LiveBench browser | 75.9 | 71% | LiveBench |
| LiveBench data analysis | 79.1 | 68% | LiveBench |
| LiveBench research | 77.9 | 52% | LiveBench |
| LiveBench design | 77.8 | 58% | LiveBench |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Agentic | 71.5 | #11 | LiveBench long agentic, Terminal-Bench |
| Coding | 59.8 | #29 | LiveBench coding, Arena WebDev (Elo) |
| Reasoning | 75.1 | #45 | LiveBench reasoning, Humanity's Last Exam |
| Data analysis | 58.9 | #11 | LiveBench data analysis |
| Research | 67.1 | #44 | LiveBench research, Long-context reasoning |
| Design | 67.4 | #16 | LiveBench design, Arena WebDev (Elo) |
| Browser use | 60.5 | #10 | LiveBench browser |
History
RankingIA score on each collection day (hover to see the rank).
Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.