Model comparison
Kimi K2.6 vs o3-mini
Kimi K2.6 is the stronger model overall, scoring 47.5 to 36.7 on the Noometry Index.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. Kimi K2.6 scores higher in 8 categories and o3-mini in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 56.8 to 27.6.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 57.2% for Kimi K2.6 and 18.6% for o3-mini.
- Kimi K2.6 is cheaper at $0.95 / $4 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- Kimi K2.6 accepts more context: 262K tokens versus 200K.
- Kimi K2.6 has downloadable open weights; the other is API-only.
Side by side
| Kimi K2.6 | o3-mini | |
|---|---|---|
| Provider | Moonshot AI | OpenAI |
| Noometry Index | 47.5 | 36.7 |
| Released | 2026-04-20 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 262K | 100K |
| Input $ / M tokens | $0.95 | $1.10 |
| Output $ / M tokens | $4 | $4.40 |
| Results tracked | 51 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Kimi K2.6: 50.5 (#41), o3-mini: 41.4 (#116)
| Benchmark | Kimi K2.6 | o3-mini |
|---|---|---|
| SciCode | 53.5% | 39.8% |
| WeirdML | 55.9% | 43.7% |
| LMArena Coding | 1488 | 1378 |
| SWE-bench Verified | 76.7% | — |
| Aider Polyglot | — | 60.4% |
| LMArena WebDev | 1509 | — |
| GSO | — | 1.3% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 1,093 | — |
Agentic & Tool Use o3-mini leads
Kimi K2.6: 21.8 (#128), o3-mini: 29.3 (#79)
| Benchmark | Kimi K2.6 | o3-mini |
|---|---|---|
| OSWorld 2.0 | 4.6% | — |
| Cybench | — | 22.5% |
| ExploitBench | 18.4% | — |
| GBAEval | 0.9% | — |
| GDP.pdf | 12% | — |
| Vending-Bench 2 | 6,205 | — |
Reasoning Kimi K2.6 leads
Kimi K2.6: 39.6 (#51), o3-mini: 16.3 (#295)
| Benchmark | Kimi K2.6 | o3-mini |
|---|---|---|
| CritPt | 8% | 0.3% |
| Chess Puzzles | 26% | 17% |
| LMArena Hard Prompts | 1470 | 1366 |
| Mystery Game Puzzles | 18% | 7% |
| DTBench | 90.9% | 68.8% |
| LMCA | 37.3% | 19% |
| Epoch Capabilities Index | 151.03 | 140.35 |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| NYT Connections (extended) | 87.2% | — |
| ARC-AGI-1 | — | 34.5% |
| EBR-Bench | 2.4% | — |
| LiveBench Reasoning | — | 89.6% |
| LiveBench Data Analysis | — | 70.6% |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math Kimi K2.6 leads
Kimi K2.6: 56.8 (#34), o3-mini: 27.6 (#236)
| Benchmark | Kimi K2.6 | o3-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 57.2% | 18.6% |
| FrontierMath Tier 4 | 25.6% | 0% |
| OTIS Mock AIME 2024-2025 | 96.1% | 76.9% |
| LMArena Math | 1475 | 1396 |
| FrontierMath (Feb 2025 set) | 39% | 12.4% |
| FrontierMath Tier 4 (v1) | 14.6% | 4.2% |
| MathArena Final-Answer Competitions | 72.9% | — |
| ProofBench | 16% | — |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
Knowledge Kimi K2.6 leads
Kimi K2.6: 53.9 (#48), o3-mini: 38.3 (#135)
| Benchmark | Kimi K2.6 | o3-mini |
|---|---|---|
| GPQA Diamond | 90.8% | 77% |
| SimpleQA Verified | 34.9% | 15.3% |
| LMArena Expert | 1491 | 1364 |
| Confabulations | — | 17.9% |
| Vectara Hallucination Rate | 10.8% | — |
Multimodal Not comparable
Kimi K2.6: 31.8 (#95), o3-mini: —
| Benchmark | Kimi K2.6 | o3-mini |
|---|---|---|
| LMArena Vision | 1282 | — |
| Blueprint-Bench 2 | 3.9% | — |
| Furniture Assembly | 21.7% | — |
| LMArena Document | 1451 | — |
Multilingual Kimi K2.6 leads
Kimi K2.6: 55.1 (#35), o3-mini: 45.9 (#159)
| Benchmark | Kimi K2.6 | o3-mini |
|---|---|---|
| LMArena Non-English | 1446 | 1319 |
| LMArena Chinese | 1521 | 1379 |
| LMArena French | 1471 | 1333 |
| LMArena German | 1449 | 1303 |
| LMArena Japanese | 1442 | 1286 |
| LMArena Korean | 1428 | 1314 |
| LMArena Russian | 1446 | 1304 |
| LMArena Spanish | 1463 | 1321 |
Instruction Following Kimi K2.6 leads
Kimi K2.6: 76.5 (#40), o3-mini: 75.3 (#67)
| Benchmark | Kimi K2.6 | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1451 | 1338 |
| LiveBench Instruction Following | — | 84.4% |
Long Context Kimi K2.6 leads
Kimi K2.6: 44.9 (#50), o3-mini: 33.8 (#251)
| Benchmark | Kimi K2.6 | o3-mini |
|---|---|---|
| LMArena Longer Query | 1468 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference Kimi K2.6 leads
Kimi K2.6: 68.7 (#25), o3-mini: 50.4 (#177)
| Benchmark | Kimi K2.6 | o3-mini |
|---|---|---|
| LMArena Text | 1455 | 1337 |
| LMArena Creative Writing | 1434 | 1286 |
| LMArena Multi-Turn | 1453 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 1725 | — |
| EQ-Bench 4 | 1202 | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Kimi K2.6 better than o3-mini?
Kimi K2.6 is the stronger model overall, scoring 47.5 to 36.7 on the Noometry Index.
Which is cheaper, Kimi K2.6 or o3-mini?
Kimi K2.6 is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is Kimi K2.6 or o3-mini better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.5 versus 41.4 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.6 does, with 262K tokens against 200K.
How many benchmarks do Kimi K2.6 and o3-mini share?
32 benchmarks have published results for both models. Kimi K2.6 has 51 scored results on Noometry and o3-mini has 51.