Kimi K2 0711
Moonshot AI · released Jul 11, 2025
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
Specification
- Context window
- 131K
- Max output
- 100K
- Knowledge cutoff
- Dec 31, 2024
- Parameters
- 1026.5B
- Licence
- other
- Serving providers
- 1
- Moderated
- No
- Uptime
- 99.9%
Intelligence
19.7
59th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
21 t/s
Median across providers
Latency
942ms
Time to first token
Cost per task
$0.09
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
- MMLU-Pro82.4%
- GPQA Diamond76.6%
- τ²-bench (Telecom)61.1%
- AIME 202557.0%
- LiveCodeBench55.6%
- AA-LCR (long context)53.0%
- IFBench41.5%
- SciCode34.5%
- Terminal-Bench Hard15.9%
- Humanity's Last Exam7.4%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| MMLU-Pro | 82.4% |
| GPQA Diamond | 76.6% |
| τ²-bench (Telecom) | 61.1% |
| AIME 2025 | 57.0% |
| LiveCodeBench | 55.6% |
| AA-LCR (long context) | 53.0% |
| IFBench | 41.5% |
| SciCode | 34.5% |
| Terminal-Bench Hard | 15.9% |
| Humanity's Last Exam | 7.4% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- R1DeepSeek20.4
- North Mini Code (free)Cohere20.2
- GPT-5 NanoOpenAI20.1
- Kimi K2 0711Moonshot AI19.7
- GLM 4.5Z.ai19.7
- GPT-4.1OpenAI19.6
- o3 MiniOpenAI19.2
- o1-proOpenAI19.1
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| R1 | 20.4 |
| North Mini Code (free) | 20.2 |
| GPT-5 Nano | 20.1 |
| Kimi K2 0711 | 19.7 |
| GLM 4.5 | 19.7 |
| GPT-4.1 | 19.6 |
| o3 Mini | 19.2 |
| o1-pro | 19.1 |
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
- $0.57
- Output / 1M tokens
- $2.3
- Cached input / 1M
- Not offered
- Blended 3:1
- $1
One task, estimated
$0.09
- Input tokens
- 50,000
- Output tokens
- 25,000
- Profile
- Standard
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
- 1,135
- Win rate
- 48.8%
- Strongest at
- Websites
- Tournaments
- 713
Elo by category
Dot position on a 1,125–1,150 scale · Elo has no meaningful zero
- 1,135
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| Websites | 1135 | 48.8% |