Moonshot AI
Kimi K2.7 Code
Release date: 6/12/2026
A long-context coding specialist optimized for repositories and autonomous editing.
Pramaana IndexAccuracy: StandardLatency: StrongCost: Leading
- Accuracy / Pramaana Index
- 62.34%± 0.99
- Latency / Pramaana Index
- 314.28s
- Cost / Test / Pramaana Index
- $0.29
- Context window
- 256k
- Max output tokens
- 64k
- Input modality
- Text · File
Hyperparameter settings
temperature: 0.2
reasoning: extended
fallbacks: disabled
Benchmark performance for Kimi K2.7 Code
| Benchmarks | Accuracy | Ranking |
|---|---|---|
| Pramaana Index | 62.34% ± 0.99 | 12 / 35 |
| Pramaana Multimodal Index | 58.26% ± 1.16 | 12 / 24 |
| Legal Research Fidelity | 56.74% ± 1.33 | 12 / 18 |
| Financial Modeling Agent | 52.45% ± 1.50 | 12 / 22 |
| Clinical Documentation Safety | 56.04% ± 1.67 | 12 / 19 |
| MATH-500 | 70.14% ± 0.48 | 12 / 112 |
| GPQA Diamond | 74.15% ± 0.65 | 12 / 121 |
| MMLU-Pro | 71.64% ± 0.82 | 12 / 119 |
| Adaptive Tutoring Dialogue | 57.94% ± 0.99 | 12 / 16 |
| SWE-bench Verified | 56.05% ± 1.16 | 6 / 69 |
| LiveCodeBench | 72.96% ± 1.33 | 7 / 127 |
| Agentic Reliability | 46.46% ± 1.50 | 12 / 12 |
| Strategic Games Arena | 54.55% ± 1.67 | 12 / 20 |
| Benefits Navigator | 57.85% ± 0.48 | 12 / 16 |