Kimi K2.6
| Released | 2026-04-20 |
|---|---|
| Price per 1M | $0.95 in · $4.00 out |
| Overall score | 56.0 · rank 66 |
| Context window | 262,144 tokens |
| Provider | Moonshot AI |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 56.0 | 66 | 32 |
| Overall: Coding | 55.5 | 66 | 16 |
| Overall: Reasoning | 56.5 | 64 | 13 |
| Overall: Agentic work | 56.0 | 70 | 14 |
| Overall: Frontend | 52.7 | 72 | 8 |
| Coding | 56.6 | 60 | 4 |
| Agents | 55.1 | 73 | 5 |
| Reasoning | 58.3 | 62 | 5 |
| Math | 56.7 | 58 | 5 |
| Knowledge | 51.9 | 84 | 3 |
| Frontend | 49.9 | 74 | 2 |
| General | 58.4 | 40 | 6 |
| Multimodal | 58.4 | 29 | 2 |
| Value vs price | +6.7 | 56 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 56.0 ±0.9 | 31 |
| Non-reasoning | 48.7 ±12.0 | 1 |
| Thinking | 54.3 ±7.1 | 1 |
Evidence
Coding 56.6 ±2.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SciCode | 53.5% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 86.8% | Vals AI | 2026-09-01 |
| SWE-bench Verified (Epoch run) | 76.7% | Epoch AI | 2026-05-08 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
| SWE-bench Verified (Vals run) | 76.2% | Vals AI | 2026-09-01 |
Agents 55.1 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OSWorld 2.0 | 4.6% | Epoch AI | 2026-11-11 |
| Terminal-Bench 2.1 (Vals run) | 53.6% | Vals AI | 2026-10-01 |
| OSWorld-Verified | 73.1% | OSWorld-Verified | 2026-04-20 |
| Tax Agent Bench | 12.4% | Vals AI | 2026-11-09 |
| Vending-Bench 2 | $6,205 | Epoch AI | 2026-11-11 |
Reasoning 58.3 ±2.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 87.2% | Lech Mazur | 2026-11-10 |
| CritPt | 8.0% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 90.8% | Epoch AI | 2026-05-01 |
| GPQA Diamond (Vals run) | 89.1% | Vals AI | 2026-09-01 |
| Chess Puzzles | 20.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 18.0% | Epoch AI | 2026-07-17 |
Math 56.7 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 57.2% | Epoch AI | 2026-06-10 |
| FrontierMath Tier 4 | 25.6% | Epoch AI | 2026-06-10 |
| ProofBench | 16.0% | Epoch AI | 2026-11-11 |
| OTIS Mock AIME 2024-2025 | 96.1% | Epoch AI | 2026-05-02 |
| MathArena Final-Answer Competitions | 72.9% | MathArena | 2026-11-11 |
| FrontierMath Tiers 1-3 (2025 set) | 39.0% | Epoch AI | 2026-05-07 |
| FrontierMath Tier 4 (2025 set) | 14.6% | Epoch AI | 2026-05-08 |
Knowledge 51.9 ±3.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 34.9% | Epoch AI | 2026-08-10 |
| MMLU-Pro (Vals run) | 87.6% | Vals AI | 2026-09-01 |
| Legal Research Bench | 15.9% | Vals AI | 2026-11-09 |
Frontend 49.9 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 37.9% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,509 | LMArena | 2026-11-09 |
General 58.4 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,504 | Lech Mazur | 2026-10-26 |
| EQ-Bench 4 | 1,191 | EQ-Bench | 2026-10-24 |
| EQ-Bench Creative Writing v3 | 1,721 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,461 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 50.0% | Lech Mazur | 2026-10-23 |
| EQ-Bench Longform Creative Writing | 78.5% | EQ-Bench | 2026-11-11 |
Multimodal 58.4 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 86.3% | Vals AI | 2026-09-01 |
| LMArena Vision | 1,265 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| Mystery Game Puzzles | 12.0% | Epoch AI | A stronger configuration result was used |
Names matched to this model
kimi-k2-6