# MoonshotAI Kimi K2.7 Code

As of October 21, 2026, MoonshotAI Kimi K2.7 Code ranks #50 of 123 models overall with 56.7 ±11.5 on the LLMBenchmark Index. Kimi K2.7 Code ranks #41 of 133 in web design, its strongest category. MoonshotAI Kimi K2.7 Code costs $0.95 per million input tokens and $4.00 per million output tokens. Kimi K2.7 Code was released on June 12, 2026.

Page: https://llmbenchmark.ai/models/kimi-k2-7-code
Data from October 21, 2026. Every figure below names the board it was read from and the day.

- Maker: Moonshot AI
- Released: June 12, 2026
- Price per million input tokens: $0.95
- Price per million output tokens: $4.00
- Context window: 262K tokens
- Overall rank: 50 of 123, by the LLMBenchmark Index
- LLMBenchmark Index: 56.7 ±11.5 (90% margin, from 4 of 7 inputs)
- Artificial Analysis Intelligence Index: 25.8
- Vibe Coding Index: 53.4 (from 4 of 6 coding benchmarks)

Benchmark results (51 of 195):

- LMArena WebDev: 1474 Elo (source: LMArena WebDev, read October 21, 2026)
- AA Intelligence Index: 25.8 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- AA Coding Index: 60.8 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- AA Agentic Index: 21.0 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- Design Arena: websites: 1264 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: UI components: 1259 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: game dev: 1220 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: data viz: 1227 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: 3D: 1241 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: all code categories: 1253 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: SVG: 1176 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: ASCII art: 1196 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: agents building web apps: 1176 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: agents building full-stack apps: 1175 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: agents building mobile apps: 1143 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: agents building Android apps: 1137 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: agents building Godot games: 1147 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: agents building games: 1131 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: HTML slides: 1201 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: PowerPoint slides: 1154 Elo (source: Design Arena, read October 21, 2026)
- LiveCodeBench (Vals AI): 82.0% (source: Vals AI boards, read October 21, 2026)
- SWE-bench Verified (Vals AI): 78.2% (source: Vals AI boards, read October 21, 2026)
- Vibe Code Bench (Vals AI): 47.2% (source: Vals AI boards, read October 21, 2026)
- Code migration (Vals AI): 25.4% (source: Vals AI boards, read October 21, 2026)
- ProgramBench (Vals AI): 0.0% (source: Vals AI boards, read October 21, 2026)
- Terminal-Bench 2.1 (Vals AI): 67.0% (source: Vals AI boards, read October 21, 2026)
- SkillsBench (Vals AI): 50.0% (source: Vals AI boards, read October 21, 2026)
- GPQA Diamond (Artificial Analysis run): 89.6% (source: Artificial Analysis, read October 21, 2026)
- Humanity's Last Exam (Artificial Analysis run): 35.0% (source: Artificial Analysis, read October 21, 2026)
- SciCode: 47.8% (source: Artificial Analysis, read October 21, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 44.7% (source: Artificial Analysis, read October 21, 2026)
- IFBench: 63.1% (source: Artificial Analysis, read October 21, 2026)
- Long context reasoning (AA-LCR): 79.3% (source: Artificial Analysis, read October 21, 2026)
- τ²-Bench Telecom: 90.1% (source: Artificial Analysis, read October 21, 2026)
- FrontierCode: 30.1% (source: Epoch AI benchmarking hub, read October 21, 2026)
- WeirdML: 54.1% (source: Epoch AI benchmarking hub, read October 21, 2026)
- APEX-Agents: 37.6% (source: Epoch AI benchmarking hub, read October 21, 2026)
- GPQA Diamond (Epoch AI run): 87.9% (source: Epoch AI benchmarking hub, read October 21, 2026)
- SimpleBench: 57.9% (source: Epoch AI benchmarking hub, read October 21, 2026)
- Chess puzzles: 14.0% (source: Epoch AI benchmarking hub, read October 21, 2026)
- OTIS Mock AIME: 95.6% (source: Epoch AI benchmarking hub, read October 21, 2026)
- FrontierMath, tiers 1 to 3: 54.0% (source: Epoch AI benchmarking hub, read October 21, 2026)
- FrontierMath, tier 4: 12.2% (source: Epoch AI benchmarking hub, read October 21, 2026)
- SimpleQA Verified: 36.5% (source: Epoch AI benchmarking hub, read October 21, 2026)
- Surface Evolver Bench: 48.8% (source: Epoch AI benchmarking hub, read October 21, 2026)
- ALE-Bench: 886.2 (source: ALE-Bench (Sakana AI), read October 21, 2026)
- Vending-Bench 2: $5,083 (source: Epoch AI benchmarking hub, read October 21, 2026)
- Epoch Capabilities Index: 150.1 (source: Epoch AI benchmarking hub, read October 21, 2026)
- LMArena WebDev: React: 1475 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena WebDev: HTML: 1451 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena WebDev: from an image: 1513 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)