Model comparison
Kimi K2.6 vs o4-mini
Kimi K2.6 is the stronger model overall, scoring 47.7 to 41.6 on the Noometry Index.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. Kimi K2.6 scores higher in 7 categories and o4-mini in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 57.0 to 40.8.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 57.2% for Kimi K2.6 and 36.1% for o4-mini.
- Kimi K2.6 is cheaper at $0.95 / $4 per million input/output tokens, against $1.10 / $4.40 for o4-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 | o4-mini | |
|---|---|---|
| Provider | Moonshot AI | OpenAI |
| Noometry Index | 47.7 | 41.6 |
| Released | 2026-04-20 | 2025-04-16 |
| 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 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Kimi K2.6: 50.7 (#43), o4-mini: 40.9 (#127)
| Benchmark | Kimi K2.6 | o4-mini |
|---|---|---|
| WeirdML | 55.9% | 52.6% |
| LMArena Coding | 1488 | 1368 |
| ALE-Bench | 1,093 | 826.17 |
| SWE-bench Verified | 76.7% | — |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| LMArena WebDev | 1509 | — |
| SciCode | 53.5% | — |
| GSO | — | 3.6% |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use o4-mini leads
Kimi K2.6: 21.9 (#137), o4-mini: 32.6 (#61)
| Benchmark | Kimi K2.6 | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| OSWorld 2.0 | 4.6% | — |
| GDPval | — | 25.3% |
| ExploitBench | 18.4% | — |
| GBAEval | 0.9% | — |
| GDP.pdf | 12% | — |
| METR Time Horizons | — | 63.9% |
| Vending-Bench 2 | 6,205 | — |
Reasoning Kimi K2.6 leads
Kimi K2.6: 40.5 (#55), o4-mini: 24.6 (#162)
| Benchmark | Kimi K2.6 | o4-mini |
|---|---|---|
| CritPt | 8% | 0.6% |
| Chess Puzzles | 26% | 26% |
| LMArena Hard Prompts | 1470 | 1351 |
| Mystery Game Puzzles | 18% | 5% |
| DTBench | 90.9% | 77.6% |
| LMCA | 37.3% | 26.5% |
| Epoch Capabilities Index | 151.05 | 145.64 |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 87.2% | — |
| ARC-AGI-1 | — | 58.7% |
| EnigmaEval | — | 9.2% |
| EBR-Bench | 2.4% | — |
| ForecastBench | — | 61.8 |
Math Kimi K2.6 leads
Kimi K2.6: 57.0 (#41), o4-mini: 40.8 (#89)
| Benchmark | Kimi K2.6 | o4-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 57.2% | 36.1% |
| FrontierMath Tier 4 | 25.6% | 4.9% |
| OTIS Mock AIME 2024-2025 | 96.1% | 81.7% |
| LMArena Math | 1475 | 1389 |
| FrontierMath (Feb 2025 set) | 39% | 24.8% |
| FrontierMath Tier 4 (v1) | 14.6% | 6.3% |
| MathArena Final-Answer Competitions | 72.9% | — |
| ProofBench | 16% | — |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
Knowledge Kimi K2.6 leads
Kimi K2.6: 54.0 (#54), o4-mini: 43.6 (#91)
| Benchmark | Kimi K2.6 | o4-mini |
|---|---|---|
| GPQA Diamond | 90.8% | 79.6% |
| SimpleQA Verified | 34.9% | 19.6% |
| Vectara Hallucination Rate | 10.8% | 18.6% |
| LMArena Expert | 1491 | 1343 |
| Humanity's Last Exam | — | 18.1% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| GPQA (HELM) | — | 73.5% |
Multimodal o4-mini leads
Kimi K2.6: 31.6 (#103), o4-mini: 40.2 (#49)
| Benchmark | Kimi K2.6 | o4-mini |
|---|---|---|
| LMArena Vision | 1283 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
| Blueprint-Bench 2 | 3.9% | — |
| Furniture Assembly | 21.7% | — |
| LMArena Document | 1451 | — |
Multilingual Kimi K2.6 leads
Kimi K2.6: 54.9 (#37), o4-mini: 47.0 (#154)
| Benchmark | Kimi K2.6 | o4-mini |
|---|---|---|
| LMArena Non-English | 1446 | 1337 |
| LMArena Chinese | 1521 | 1354 |
| LMArena French | 1471 | 1364 |
| LMArena German | 1450 | 1336 |
| LMArena Japanese | 1443 | 1308 |
| LMArena Korean | 1427 | 1312 |
| LMArena Russian | 1446 | 1334 |
| LMArena Spanish | 1464 | 1347 |
Instruction Following Kimi K2.6 leads
Kimi K2.6: 76.3 (#43), o4-mini: 75.2 (#68)
| Benchmark | Kimi K2.6 | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1451 | 1321 |
| IFEval | — | 92.8% |
Long Context Too close to call
Kimi K2.6: 44.9 (#52), o4-mini: 45.5 (#33)
| Benchmark | Kimi K2.6 | o4-mini |
|---|---|---|
| LMArena Longer Query | 1468 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Kimi K2.6 leads
Kimi K2.6: 68.5 (#26), o4-mini: 54.0 (#152)
| Benchmark | Kimi K2.6 | o4-mini |
|---|---|---|
| LMArena Text | 1455 | 1353 |
| LMArena Creative Writing | 1434 | 1294 |
| LMArena Multi-Turn | 1453 | 1350 |
| Short-Story Creative Writing | — | 75% |
| EQ-Bench Creative Writing | 1725 | — |
| WildBench | — | 85.4% |
| EQ-Bench 4 | 1202 | — |
Frequently asked questions
Is Kimi K2.6 better than o4-mini?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 41.6 on the Noometry Index.
Which is cheaper, Kimi K2.6 or o4-mini?
Kimi K2.6 is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is Kimi K2.6 or o4-mini better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 40.9 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 o4-mini share?
34 benchmarks have published results for both models. Kimi K2.6 has 51 scored results on Noometry and o4-mini has 60.