Leaderboard / Model
Kimi K2.6
Moonshot · Open weights · Released Apr 20, 2026 · $0.95 in · $4 out per 1M tokens
n/aOverall · not enough data
Score by job
Coding
Not enough data · 2 of 5 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| SWE-bench Verified | 76.7% | kimi-k2.6 | 0.09 |
| LMArena Coding | 1486 rating | kimi-k2.6 | -0.20 |
Agents
Not enough data · 1 of 4 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| OSWorld 2.0 | 4.6% | kimi-k2.6 | -1.48 |
Reasoning
Not enough data · 1 of 4 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| GPQA Diamond | 90.8% | kimi-k2.6 | -0.31 |
Math
28 · rank 30 · 5 of 5 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| FrontierMath Tiers 1–3 | 57.2% | kimi-k2.6 | -0.74 |
| FrontierMath Tier 4 | 25.6% | kimi-k2.6 | -0.64 |
| OTIS Mock AIME | 96.1% | kimi-k2.6 | 0.13 |
| ProofBench | 16.0% | kimi-k2.6 | -1.25 |
| LMArena Math | 1473 rating | kimi-k2.6 | -0.27 |
Writing
51 · rank 31 · 2 of 2 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| LMArena Creative Writing | 1432 rating | kimi-k2.6 | -0.59 |
| LMArena Instruction Following | 1449 rating | kimi-k2.6 | -0.59 |
Design
30 · rank 33 · 1 of 1 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| LMArena WebDev | 1509 rating | kimi-k2.6 | -0.49 |