Updated daily at 05:00 UTC
- Released
- 27 Jan 2026
- Status
- Legacy
- Context
- 262.1K
- Max output
- —
- Input per 1M tokens
- —
- Output per 1M tokens
- —
- Open weights
- Yes
- License
- modified-mit
- Parameters
- 1000B, 32B active
- Knowledge cutoff
- —
- Reasoning
- Yes
- Modalities
- text, image, video → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
| Category | Score | Rank | Coverage |
|---|---|---|---|
| Knowledge & reasoning | 36.2 | Not ranked | 1 of 4 |
| Factuality & hallucination | 34.3 | 44 | 1 of 1 |
| Human preference | 55.8 | 13 | 3 of 5 |
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Humanity's Last Exam (HLE) | Accuracy | 50.2% | Self-reported | — | — | Model Card via Hugging Face Community Evals |
| MMLU-Pro | Accuracy | 87.1% | Self-reported | — | — | Model Card via Hugging Face Community Evals |
| SimpleBench | Score (AVG@5) | 46.8% | Third party | — | — | SimpleBench Leaderboard via Epoch AI |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 87.6% | Self-reported | — | — | Model Card via Hugging Face Community Evals |
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| SWE-bench Verified | % resolved | 73.8% | Independent | — | 17 Feb 2026 | Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 43.2% | Third party | — | — | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI |
| WeirdML (v2) | Average accuracy | 45.6% | Third party | — | — | https://htihle.github.io/weirdml.html via Epoch AI |
Computer & browser use
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| OSWorld-Verified | % tasks completed | 63.3% | Third party | — | — | OS World Website via Epoch AI |
Long context
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| CL-bench | Tasks solved | 19.3% | Source not stated | — | — | Epoch AI via Epoch AI |
| CL-bench Life | Tasks solved | 13.2% | Source not stated | — | — | Epoch AI via Epoch AI |
| Fiction.LiveBench | % correct at 16K tokens (Epoch's column) | 86.1% | Third party | — | — | Fiction.live leaderboard via Epoch AI |
Factuality & hallucination
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| SimpleQA Verified | Accuracy (% correct) | 34.3% | Independent | — | 27 Aug 2026 | Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Code Arena: WebDev (arena.ai) | Arena score (Elo scale) | 1436 | Independent | thinking | 25 Sep 2026 | Arena |
| Code Arena: WebDev (arena.ai) | Votes | 20171 | Independent | thinking | 25 Sep 2026 | Arena |
| Document Arena (arena.ai) | Arena score (Elo scale) | 1436 | Independent | thinking | 13 Sep 2026 | Arena |
| Document Arena (arena.ai) | Votes | 21569 | Independent | thinking | 13 Sep 2026 | Arena |
| Text Arena (arena.ai) | Arena score (Elo scale) | 1450 | Independent | thinking | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 74638 | Independent | thinking | 25 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Arena score (Elo scale) | 1252 | Independent | thinking | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Votes | 28367 | Independent | thinking | 28 Sep 2026 | Arena |
Other Kimi K versions
- Kimi K316 Jul 2026
- Kimi K2.7 Code12 Jun 2026
- Kimi K2.620 Apr 2026
- Kimi K2 Thinking6 Nov 2025
- Kimi K211 Jul 2025
- Kimi Thinking PreviewMay 2025
- kimi-latestFeb 2025