Moonshot AI, open weights
Kimi K2.7 Code
Kimi K2.7 Code by Moonshot AI ranks 94th of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.3. Its strongest category is math, where it ranks 48th. API pricing starts at $0.95 per million input tokens and $4 per million output tokens, with a 262K-token context window.
Last verified
Specifications
- Noometry rank
- #94 of 354
- Index score
- 43.3
- Evidence
- Confirmed 19 results
- Provider
- Moonshot AI
- Released
- June 12, 2026
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 262K
- Max output
- 262K
- Input price
- $0.95 / M
- Output price
- $4 / M
- Blended price
- $1.71 / M
- Output speed
- Not measured
- Value
- #142 of 219
- Knowledge cutoff
- January 2025
- Input
- text, image, video
- Hugging Face
- moonshotai/Kimi-K2.7-Code
Category scores
Each category score combines every public result we have in that category.
- Coding 42.9
- Agentic & Tool Use 24.0
- Reasoning 39.0
- Math 52.9
- Knowledge 53.5
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 42.9 | #95 | 5 |
| Agentic & Tool Use | 24.0 | #122 | 2 |
| Reasoning | 39.0 | #61 | 4 |
| Math | 52.9 | #48 | 3 |
| Knowledge | 53.5 | #57 | 2 |
Strengths and weaknesses
Categories where Kimi K2.7 Code places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Agentic & Tool Use | 24.0 | −6.4 | #122 of 154, top 80% |
| Coding | 42.9 | +4.1 | #95 of 340, top 28% |
Closest competitors
The models ranked just above and below Kimi K2.7 Code. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Gemma 4 31B IT | #90 | 43.5 | $0.15 | 3 | Compare |
| Qwen3 235B-A22B | #91 | 43.5 | $1.22 | 85 | Compare |
| Gemma 4 26B A4B IT | #92 | 43.5 | $0.11 | — | Compare |
| MiMo-V2.5 | #93 | 43.4 | $0.18 | — | Compare |
| Qwen3-VL 235B-A22B | #95 | 43.2 | $1.22 | — | Compare |
| Seed 2.0 Pro | #96 | 43.2 | $1.13 | — | Compare |
| DeepSeek-V3.1-Terminus | #97 | 43.1 | $0.45 | 30 | Compare |
| Hunyuan Vision 1.5 | #98 | 43.1 | — | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| DeepSWE | 30.5% | #27 of 29, top 94% | Epoch AI | ||
| FrontierCode | 30.1% | #26 of 37, top 71% | Epoch AI | ||
| LMArena WebDev | 1473 | #53 of 113, top 47% | LMArena | 2026-10-08 | |
| SciCode | 47.5% | #50 of 121, top 42% | Epoch AI | ||
| WeirdML | 54.1% | #40 of 119, top 34% | Epoch AI | ||
| ALE-Bench | 886.23 | #53 of 105, top 51% | Epoch AI |
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| APEX-Agents | 37.6% | #39 of 49, top 80% | Epoch AI | ||
| GBAEval | 0.9% | #18 of 23, top 79% | Epoch AI | ||
| Vending-Bench 2 | 5,083 | #30 of 60, top 50% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| SimpleBench | 57.9% | #29 of 77, top 38% | Epoch AI | ||
| CritPt | 10% | #48 of 134, top 36% | Epoch AI | ||
| Chess Puzzles | 21% | #55 of 129, top 43% | Epoch AI | 2026-08-07 | |
| Surface Evolver Bench | 48.8% | #16 of 25, top 64% | Epoch AI | ||
| Epoch Capabilities Index | 149.97 | #54 of 213, top 26% | Epoch AI | 2026-06-12 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| FrontierMath (Tiers 1-3) | 54% | #44 of 81, top 55% | Epoch AI | 2026-06-13 | |
| FrontierMath Tier 4 | 12.2% | #52 of 63, top 83% | Epoch AI | 2026-06-13 | |
| OTIS Mock AIME 2024-2025 | 95.6% | #34 of 173, top 20% | Epoch AI | 2026-08-07 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 87.9% | #49 of 186, top 27% | Epoch AI | 2026-08-07 | |
| SimpleQA Verified | 36.5% | #46 of 77, top 60% | Epoch AI | 2026-08-27 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| azure | $0.95 | $4 | $0.19 | 2026-10-10 |
| deepinfra | $0.68 | $3.40 | $0.14 | 2026-10-10 |
| moonshot | $0.95 | $4 | $0.19 | 2026-10-10 |
| openrouter | $0.67 | $3.35 | $0.18 | 2026-10-10 |
Compare Kimi K2.7 Code
- Kimi K2.7 Code vs MiMo-V2.5
- Kimi K2.7 Code vs Qwen3-VL 235B-A22B
- Kimi K2.7 Code vs Gemma 4 26B A4B IT
- Kimi K2.7 Code vs Seed 2.0 Pro
- Kimi K2.7 Code vs Qwen3 235B-A22B
- Kimi K2.7 Code vs DeepSeek-V3.1-Terminus
- Kimi K2.7 Code vs GPT-6 Astra
- Kimi K2.7 Code vs Claude Fable 5.1
- Kimi K2.7 Code vs Gemini 3.8 Flash
- Kimi K2.7 Code vs Grok 4.6
- Kimi K2.7 Code vs Qwen3.8 Max
- Kimi K2.7 Code vs GLM-5.3
- Kimi K2.7 Code vs Muse Spark 1.3
- Kimi K2.7 Code vs DeepSeek V4 Pro
Other Moonshot AI models
Frequently asked questions
How good is Kimi K2.7 Code?
Kimi K2.7 Code by Moonshot AI ranks 94th of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.3. Its strongest category is math, where it ranks 48th. API pricing starts at $0.95 per million input tokens and $4 per million output tokens, with a 262K-token context window.
How much does Kimi K2.7 Code cost?
Kimi K2.7 Code costs $0.95 per million input tokens and $4 per million output tokens on Moonshot AI's own API, with cached input at $0.19.
What is Kimi K2.7 Code's context window?
Kimi K2.7 Code accepts up to 262K tokens of input and can write up to 262K tokens in one response.
Is Kimi K2.7 Code open source?
Yes. Kimi K2.7 Code's weights are downloadable from Hugging Face (moonshotai/Kimi-K2.7-Code); check the license for commercial terms.
What are Kimi K2.7 Code's strengths and weaknesses?
Relative to other ranked models, Kimi K2.7 Code places best in math, reasoning and lowest in agentic & tool use, coding.
What is Kimi K2.7 Code best at?
Its best category is math, where it ranks 48th on Noometry.