Model comparison
Kimi K2 (Jul 2025) vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 41.2 on the Noometry Index.
Last verified . 22 shared benchmarks.
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 2 categories and Qwen3.6 Plus in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 37.3.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- Qwen3.6 Plus accepts more context: 1M tokens versus 262K.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| Kimi K2 (Jul 2025) | Qwen3.6 Plus | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 41.2 | 47.5 |
| Released | 2025-07-12 | 2026-03-31 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 262K | 66K |
| Input $ / M tokens | $0.57 | $0.50 |
| Output $ / M tokens | $2.30 | $3 |
| Results tracked | 42 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.4 (#102), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Plus |
|---|---|---|
| LMArena Coding | 1399 | 1467 |
| ALE-Bench | 597.5 | 670.15 |
| SWE-bench Verified | — | 57.9% |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| LMArena WebDev | — | 1461 |
| SciCode | — | 40.7% |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
Agentic & Tool Use Not comparable
Kimi K2 (Jul 2025): 32.4 (#64), Qwen3.6 Plus: —
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Plus |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
| Vending-Bench 2 | — | 5,115 |
Reasoning Qwen3.6 Plus leads
Kimi K2 (Jul 2025): 23.3 (#179), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Plus |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1449 |
| Epoch Capabilities Index | 146.01 | 147.65 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| NYT Connections (extended) | — | 60.3% |
| CritPt | — | 2.9% |
| Chess Puzzles | — | 17% |
| Thematic Generalization | — | 59.5% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 81.9% |
| LMCA | — | 33.1% |
| ForecastBench | 60.2 | — |
Math Qwen3.6 Plus leads
Kimi K2 (Jul 2025): 42.7 (#83), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Plus |
|---|---|---|
| LMArena Math | 1397 | 1450 |
| FrontierMath (Feb 2025 set) | 21.4% | 26.2% |
| FrontierMath Tier 4 (v1) | 0% | 8.3% |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| Omni-MATH | 65.4% | — |
Knowledge Qwen3.6 Plus leads
Kimi K2 (Jul 2025): 37.3 (#157), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Plus |
|---|---|---|
| LMArena Expert | 1365 | 1454 |
| GPQA Diamond | — | 88.4% |
| SimpleQA Verified | — | 44.1% |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
Multilingual Qwen3.6 Plus leads
Kimi K2 (Jul 2025): 49.6 (#130), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1372 | 1424 |
| LMArena Chinese | 1415 | 1477 |
| LMArena French | 1379 | 1455 |
| LMArena German | 1387 | 1452 |
| LMArena Japanese | 1349 | 1389 |
| LMArena Korean | 1325 | 1379 |
| LMArena Russian | 1385 | 1434 |
| LMArena Spanish | 1386 | 1432 |
Instruction Following Qwen3.6 Plus leads
Kimi K2 (Jul 2025): 71.1 (#156), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1348 | 1425 |
| IFEval | 85% | — |
Long Context Qwen3.6 Plus leads
Kimi K2 (Jul 2025): 41.2 (#145), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Plus |
|---|---|---|
| CL-bench | 17.6% | 20.3% |
| LMArena Longer Query | 1353 | 1439 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Too close to call
Kimi K2 (Jul 2025): 62.3 (#78), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1380 | 1437 |
| LMArena Creative Writing | 1350 | 1404 |
| LMArena Multi-Turn | 1371 | 1438 |
| 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 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 41.2 on the Noometry Index.
Which is cheaper, Kimi K2 (Jul 2025) or Qwen3.6 Plus?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is Kimi K2 (Jul 2025) or Qwen3.6 Plus better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 262K.
How many benchmarks do Kimi K2 (Jul 2025) and Qwen3.6 Plus share?
22 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Qwen3.6 Plus has 37.