Model comparison
Kimi K2.6 vs Qwen2.5-Max
Kimi K2.6 is the stronger model overall, scoring 47.5 to 40.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Kimi K2.6 scores higher in 8 categories and Qwen2.5-Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 56.8 to 34.3.
- Kimi K2.6 has downloadable open weights; the other is API-only.
Side by side
| Kimi K2.6 | Qwen2.5-Max | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 47.5 | 40.1 |
| Released | 2026-04-20 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.95 | — |
| Output $ / M tokens | $4 | — |
| Results tracked | 51 | 27 |
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), Qwen2.5-Max: 41.2 (#118)
| Benchmark | Kimi K2.6 | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1488 | 1359 |
| SWE-bench Verified | 76.7% | — |
| LMArena WebDev | 1509 | — |
| SciCode | 53.5% | — |
| WeirdML | 55.9% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 1,093 | — |
Agentic & Tool Use Not comparable
Kimi K2.6: 21.8 (#128), Qwen2.5-Max: —
| Benchmark | Kimi K2.6 | Qwen2.5-Max |
|---|---|---|
| OSWorld 2.0 | 4.6% | — |
| 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), Qwen2.5-Max: 24.6 (#144)
| Benchmark | Kimi K2.6 | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1470 | 1360 |
| Epoch Capabilities Index | 151.03 | 132.54 |
| NYT Connections (extended) | 87.2% | — |
| CritPt | 8% | — |
| Chess Puzzles | 26% | — |
| EBR-Bench | 2.4% | — |
| LiveBench Reasoning | — | 51.4% |
| Mystery Game Puzzles | 18% | — |
| DTBench | 90.9% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 37.3% | — |
| LiveBench | — | 62.3% |
Math Kimi K2.6 leads
Kimi K2.6: 56.8 (#34), Qwen2.5-Max: 34.3 (#162)
| Benchmark | Kimi K2.6 | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1475 | 1369 |
| FrontierMath (Tiers 1-3) | 57.2% | — |
| FrontierMath Tier 4 | 25.6% | — |
| MathArena Final-Answer Competitions | 72.9% | — |
| OTIS Mock AIME 2024-2025 | 96.1% | — |
| ProofBench | 16% | — |
| LiveBench Math | — | 58.4% |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Kimi K2.6 leads
Kimi K2.6: 53.9 (#48), Qwen2.5-Max: 34.8 (#181)
| Benchmark | Kimi K2.6 | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1491 | 1337 |
| GPQA Diamond | 90.8% | — |
| SimpleQA Verified | 34.9% | — |
| Confabulations | — | 21.8% |
| Vectara Hallucination Rate | 10.8% | — |
Multimodal Not comparable
Kimi K2.6: 31.8 (#95), Qwen2.5-Max: —
| Benchmark | Kimi K2.6 | Qwen2.5-Max |
|---|---|---|
| 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), Qwen2.5-Max: 48.3 (#140)
| Benchmark | Kimi K2.6 | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1446 | 1352 |
| LMArena Chinese | 1521 | 1382 |
| LMArena French | 1471 | 1396 |
| LMArena German | 1449 | 1350 |
| LMArena Japanese | 1442 | 1299 |
| LMArena Korean | 1428 | 1304 |
| LMArena Russian | 1446 | 1353 |
| LMArena Spanish | 1463 | 1377 |
Instruction Following Kimi K2.6 leads
Kimi K2.6: 76.5 (#40), Qwen2.5-Max: 71.5 (#147)
| Benchmark | Kimi K2.6 | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1451 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Kimi K2.6 leads
Kimi K2.6: 44.9 (#50), Qwen2.5-Max: 41.3 (#137)
| Benchmark | Kimi K2.6 | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1468 | 1358 |
Writing & Preference Kimi K2.6 leads
Kimi K2.6: 68.7 (#25), Qwen2.5-Max: 55.6 (#141)
| Benchmark | Kimi K2.6 | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1455 | 1367 |
| LMArena Creative Writing | 1434 | 1339 |
| LMArena Multi-Turn | 1453 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 1725 | — |
| EQ-Bench 4 | 1202 | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Kimi K2.6 better than Qwen2.5-Max?
Kimi K2.6 is the stronger model overall, scoring 47.5 to 40.1 on the Noometry Index.
Is Kimi K2.6 or Qwen2.5-Max better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.5 versus 41.2 in the Noometry coding category.
How many benchmarks do Kimi K2.6 and Qwen2.5-Max share?
18 benchmarks have published results for both models. Kimi K2.6 has 51 scored results on Noometry and Qwen2.5-Max has 27.