# Kimi K2.7 Code Benchmark Scores & Performance

> Kimi K2.7 Code by Moonshot AI scores 65.49/100 overall, ranking #34 out of 483 AI models.

Canonical page: https://benchlm.ai/models/kimi-k2-7-code

Last updated: September 10, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Moonshot AI |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 256K |
| Overall Score | 65.49/100 |
| Overall Rank | #34 of 483 |

## Family & Coverage

- Family: Kimi K2.7 Code
- Variant: code
- Benchmarks covered: 24 of 434
- Related earlier model: [Kimi K2.6](/models/kimi-2-6)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Kimi Claw 24/7](/benchmarks/kimiclaw247) | 46.9% |
| [MCP Atlas](/benchmarks/mcpatlas) | 76% |
| [MCP Mark Verified](/benchmarks/mcpmarkverified) | 81.1% |
| [τ²-bench results](/benchmarks/tau2-bench) | 90.1% |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 30.7% |
| [AA Agentic Index](/benchmarks/aaagenticindex) | 22.5% |
| [GDPval-AA](/benchmarks/gdpvalaa) | 1114 |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Kimi Code Bench v2](/benchmarks/kimicodebenchv2) | 62.0% |
| [ProgramBench](/benchmarks/programbench) | 53.6% |
| [MLS-Bench Lite](/benchmarks/mlsbenchlite) | 35.1% |
| [cursorBench32](/benchmarks/cursorbench32) | 49.7% |
| [AA-SciCode](/benchmarks/aascicode) | 47.8% |
| [OpenHarmony Bench](/benchmarks/openharmonybench) | 52.1% |
| [AA Coding Index](/benchmarks/aacodingindex) | 60.8% |

## Multimodal & Grounded Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Design Arena Website](/benchmarks/designarenawebsite) | 1279 |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-LCR](/benchmarks/lcr) | 79.3% |
| [CritPt](/benchmarks/critpt) | 10.0% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 26.3% |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 89.6% |
| [AA-HLE](/benchmarks/aahle) | 35.0% |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -10.2% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 39.6% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 82.4% |

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-IFBench](/benchmarks/aaifbench) | 63.1% |

## Other Moonshot AI Models

- [Kimi K3](/models/kimi-k3) - Score: 74.82
- [Kimi K2.6](/models/kimi-2-6) - Score: 65.39
- [Kimi K2.5 (Reasoning)](/models/kimi-k2-5-reasoning) - Score: 57
- [Kimi K2.5](/models/kimi-k2-5) - Score: 54.01
- [Moonshot v1](/models/moonshot-v1) - Score: 42.72
- [Kimi K2](/models/kimi-k2) - Score: 23.26
- [Kimi-Audio 7B](/models/kimi-audio-7b) - Score: not computed