Model comparison
Kimi K2 (Jul 2025) vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 2.9× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Max Preview leads 57.6 to 37.3.
- The biggest single-benchmark swing is SimpleBench: 26.3% for Kimi K2 (Jul 2025) and 63% for Qwen3.6 Max Preview.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| Kimi K2 (Jul 2025) | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 41.2 | 51.5 |
| Released | 2025-07-12 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 262K | 262K |
| Max output | 262K | 66K |
| Input $ / M tokens | $0.57 | $1.30 |
| Output $ / M tokens | $2.30 | $7.80 |
| Results tracked | 42 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Kimi K2 (Jul 2025): 42.4 (#102), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1399 | 1471 |
| SWE-bench Verified | — | 76.7% |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| LMArena WebDev | — | 1482 |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| ALE-Bench | 597.5 | — |
Agentic & Tool Use Not comparable
Kimi K2 (Jul 2025): 32.4 (#64), Qwen3.6 Max Preview: —
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Max Preview |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
Kimi K2 (Jul 2025): 23.3 (#179), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Max Preview |
|---|---|---|
| SimpleBench | 26.3% | 63% |
| LMArena Hard Prompts | 1384 | 1457 |
| Epoch Capabilities Index | 146.01 | 149.24 |
| Kagi LLM Benchmark | 64.4% | — |
| NYT Connections (extended) | — | 74.1% |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 87.2% |
| LMCA | — | 42.5% |
| ForecastBench | 60.2 | — |
Math Qwen3.6 Max Preview leads
Kimi K2 (Jul 2025): 42.7 (#83), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Math | 1397 | 1465 |
| FrontierMath (Feb 2025 set) | 21.4% | 23.1% |
| FrontierMath Tier 4 (v1) | 0% | 4.2% |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| Omni-MATH | 65.4% | — |
Knowledge Qwen3.6 Max Preview leads
Kimi K2 (Jul 2025): 37.3 (#157), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Expert | 1365 | 1478 |
| GPQA Diamond | — | 87.4% |
| SimpleQA Verified | — | 52% |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
Multilingual Qwen3.6 Max Preview leads
Kimi K2 (Jul 2025): 49.6 (#130), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1372 | 1437 |
| LMArena Chinese | 1415 | 1487 |
| LMArena French | 1379 | 1449 |
| LMArena Russian | 1385 | 1445 |
| LMArena Spanish | 1386 | 1454 |
| LMArena German | 1387 | — |
| LMArena Japanese | 1349 | — |
| LMArena Korean | 1325 | — |
Instruction Following Qwen3.6 Max Preview leads
Kimi K2 (Jul 2025): 71.1 (#156), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1348 | 1438 |
| IFEval | 85% | — |
Long Context Qwen3.6 Max Preview leads
Kimi K2 (Jul 2025): 41.2 (#145), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1353 | 1457 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Qwen3.6 Max Preview leads
Kimi K2 (Jul 2025): 62.3 (#78), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1380 | 1447 |
| LMArena Creative Writing | 1350 | 1435 |
| LMArena Multi-Turn | 1371 | 1456 |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 2.9× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, Kimi K2 (Jul 2025) or Qwen3.6 Max Preview?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is Kimi K2 (Jul 2025) or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Kimi K2 (Jul 2025) and Qwen3.6 Max Preview share?
18 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Qwen3.6 Max Preview has 29.