Updated daily at 05:00 UTC
- Released
- 12 Jun 2026
- Status
- Current
- Context
- 262.1K
- Max output
- —
- Input per 1M tokens
- $0.95
- Output per 1M tokens
- $4.00
- 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 | 33.2 | 48 | 2 of 4 |
| Coding & software engineering | 30.3 | Not ranked | 2 of 5 |
| Factuality & hallucination | 36.5 | 41 | 1 of 1 |
| Human preference | 60.3 | Not ranked | 1 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 |
|---|---|---|---|---|---|---|
| Chess Puzzles | Puzzles solved | 21.0% | Independent | — | 7 Aug 2026 | Epoch AI |
| SimpleBench | Score (AVG@5) | 57.9% | Third party | — | — | https://lmcouncil.ai/benchmarks via Epoch AI |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 87.9% | Independent | — | 7 Aug 2026 | Epoch AI |
| Surface Evolver Bench | Mean score (partial credit) | 48.8% | Third party | — | — | https://yhenon.github.io/surface-evolver-llm-eval/ via Epoch AI |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| FrontierMath Tier 4 | Accuracy | 12.2% | Independent | — | 13 Jun 2026 | Epoch AI |
| FrontierMath Tiers 1-3 | Accuracy | 54.0% | Independent | — | 13 Jun 2026 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 95.6% | Independent | — | 7 Aug 2026 | Epoch AI |
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| DeepSWE | Pass@1 | 30.5% | Third party | — | — | https://deepswe.datacurve.ai/ via Epoch AI |
| FrontierCode | Main score (Mean@5) | 30.1% | Third party | — | — | https://cognition.com/frontiercode via Epoch AI |
| WeirdML (v2) | Average accuracy | 54.1% | Third party | — | — | https://htihle.github.io/weirdml.html via Epoch AI |
Professional knowledge work
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| APEX-Agents | Pass@1 (all rubric criteria met) | 37.6% | Source not stated | — | — | Epoch AI via Epoch AI |
Factuality & hallucination
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| SimpleQA Verified | Accuracy (% correct) | 36.5% | Independent | — | 27 Aug 2026 | Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Code Arena: WebDev (arena.ai) | Arena score (Elo scale) | 1473 | Independent | — | 25 Sep 2026 | Arena |
| Code Arena: WebDev (arena.ai) | Votes | 5004 | Independent | — | 25 Sep 2026 | Arena |
Other Kimi K versions
- Kimi K316 Jul 2026
- Kimi K2.620 Apr 2026
- Kimi K2.527 Jan 2026
- Kimi K2 Thinking6 Nov 2025
- Kimi K211 Jul 2025
- Kimi Thinking PreviewMay 2025
- kimi-latestFeb 2025