# MoonshotAI Kimi K3.1 Pro

As of October 29, 2026, MoonshotAI Kimi K3.1 Pro ranks #13 of 111 models overall with 74.4 ±6.7 on the LLMBenchmark Index. Kimi K3.1 Pro ranks #6 of 134 in web design, its strongest category. MoonshotAI Kimi K3.1 Pro costs $2.00 per million input tokens and $10.00 per million output tokens. Kimi K3.1 Pro was released on October 23, 2026.

Page: https://llmbenchmark.ai/models/kimi-k3-1-pro
Data from October 29, 2026. Every figure below names the board it was read from and the day.

- Maker: Moonshot AI
- Released: October 23, 2026
- Price per million input tokens: $2.00
- Price per million output tokens: $10.00
- Context window: 1.05M tokens
- Overall rank: 13 of 111, by the LLMBenchmark Index
- LLMBenchmark Index: 74.4 ±6.7 (90% margin, from 4 of 7 inputs)
- Artificial Analysis Intelligence Index: 46.0
- Vibe Coding Index: 82.2 (from 4 of 6 coding benchmarks)

Benchmark results (35 of 206):

- LiveBench coding: 81.8% (source: LiveBench, read October 29, 2026)
- LMArena WebDev: 1695 Elo (Max) (source: LMArena WebDev, read October 29, 2026)
- Vals Index: 62.5% (source: Vals Index, read October 29, 2026)
- AA Intelligence Index: 46.0 (source: Artificial Analysis (via OpenRouter), read October 29, 2026)
- Design Arena: websites: 1325 Elo (source: Design Arena, read October 29, 2026)
- Design Arena: UI components: 1400 Elo (source: Design Arena, read October 29, 2026)
- Design Arena: game dev: 1410 Elo (source: Design Arena, read October 29, 2026)
- Design Arena: data viz: 1300 Elo (source: Design Arena, read October 29, 2026)
- Design Arena: 3D: 1451 Elo (source: Design Arena, read October 29, 2026)
- Design Arena: all code categories: 1354 Elo (source: Design Arena, read October 29, 2026)
- Design Arena: SVG: 1328 Elo (source: Design Arena, read October 29, 2026)
- LiveBench reasoning: 91.1% (source: LiveBench, read October 29, 2026)
- LiveBench data analysis: 79.1% (source: LiveBench, read October 29, 2026)
- LiveBench research: 77.9% (source: LiveBench, read October 29, 2026)
- LiveBench browser: 75.9% (source: LiveBench, read October 29, 2026)
- LiveBench long agentic: 39.1% (source: LiveBench, read October 29, 2026)
- LiveBench design: 77.8% (source: LiveBench, read October 29, 2026)
- Terminal-Bench 4 (Vals AI): 63.6% (Mini-SWE-agent) (source: Vals AI boards, read October 29, 2026)
- Vibe Code Bench (Vals AI): 84.9% (OpenHands) (source: Vals AI boards, read October 29, 2026)
- IOI (Vals AI): 81.9% (source: Vals AI boards, read October 29, 2026)
- Tax Agent Bench (Vals AI): 24.9% (source: Vals AI boards, read October 29, 2026)
- Legal Research Bench (Vals AI): 37.5% (source: Vals AI boards, read October 29, 2026)
- Harvey's Legal Agent Benchmark (Vals AI): 11.7% (source: Vals AI boards, read October 29, 2026)
- BioMysteryBench (Vals AI): 75.6% (source: Vals AI boards, read October 29, 2026)
- Terminal-Bench-Science (Vals AI): 31.4% (Mini-SWE-agent) (source: Vals AI boards, read October 29, 2026)
- Vals Science Index: 44.4% (source: Vals AI boards, read October 29, 2026)
- MysteryMechanism (Vals AI): 26.1% (source: Vals AI boards, read October 29, 2026)
- Humanity's Last Exam (Artificial Analysis run): 52.5% (source: Artificial Analysis, read October 29, 2026)
- SciCode: 60.8% (source: Artificial Analysis, read October 29, 2026)
- Long context reasoning (AA-LCR): 86.3% (source: Artificial Analysis, read October 29, 2026)
- ProofBench: 91.0% (source: Epoch AI benchmarking hub, read October 29, 2026)
- ALE-Bench: 1932.8 (Max) (source: ALE-Bench (Sakana AI), read October 29, 2026)
- LMArena WebDev: React: 1701 Elo (Max) (source: LMArena (Hugging Face dataset), read October 29, 2026)
- LMArena WebDev: HTML: 1706 Elo (Max) (source: LMArena (Hugging Face dataset), read October 29, 2026)
- MathArena: 59.6% (source: MathArena, read October 29, 2026)