Kimi K2.7 Code (batch)
Moonshot AI · released Jun 12, 2026
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
Specification
- Context window
- 262K
- Max output
- —
- Knowledge cutoff
- Not stated
- Parameters
- 1026.9B
- Licence
- other
- Serving providers
- 1
- Moderated
- No
Intelligence
43.0
91th percentile
Coding
60.8
Coding Index
Agentic
30.3
Agentic Index
Output speed
40 t/s
Median across providers
Latency
1.49s
Time to first token
Cost per task
$0.18
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- τ²-bench (Telecom)90.1%
- GPQA Diamond89.6%
- AA-LCR (long context)75.0%
- IFBench63.1%
- SciCode47.5%
- Terminal-Bench Hard44.7%
- Humanity's Last Exam35.0%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| τ²-bench (Telecom) | 90.1% |
| GPQA Diamond | 89.6% |
| AA-LCR (long context) | 75.0% |
| IFBench | 63.1% |
| SciCode | 47.5% |
| Terminal-Bench Hard | 44.7% |
| Humanity's Last Exam | 35.0% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- GPT-5.2OpenAI43.3
- Kimi K2.7 Code (batch)Moonshot AI43.0
- Kimi K2.7 CodeMoonshot AI43.0
- MiMo-V2.5-ProXiaomi42.9
- InklingThinking Machines42.3
- Hy3Tencent42.2
- Nex-N2-ProNex AGI41.7
- Inkling SmallThinking Machines41.2
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| GPT-5.2 | 43.3 |
| Kimi K2.7 Code (batch) | 43.0 |
| Kimi K2.7 Code | 43.0 |
| MiMo-V2.5-Pro | 42.9 |
| Inkling | 42.3 |
| Hy3 | 42.2 |
| Nex-N2-Pro | 41.7 |
| Inkling Small | 41.2 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.475
- Output / 1M tokens
- $2
- Cached input / 1M
- $0.095
- Blended 3:1
- $0.856
One task, estimated
$0.18
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,298
- Win rate
- 52.3%
- Strongest at
- 3D scenes
- Tournaments
- 4,220
Elo by category
Dot position on a 1,200–1,300 scale · Elo has no meaningful zero
- 1,298
- 1,297
- 1,295
- 1,258
- 1,251
- 1,220
- 1,218
- 1,201
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| 3D scenes | 1298 | 52.3% |
| Websites | 1297 | 54.9% |
| UI components | 1295 | 53.7% |
| Game development | 1258 | 50.9% |
| Data visualisation | 1251 | 50.9% |
| SVG | 1220 | 48.8% |
| Full-stack apps | 1218 | 54.5% |
| Mobile apps | 1201 | 50.3% |