Model comparison
Kimi K2 (Jul 2025) vs Qwen3.5 122B-A10B
Kimi K2 (Jul 2025) and Qwen3.5 122B-A10B score almost the same on the Noometry Index (41.2 vs 42.1), so choose on price, context window or the category you care about most.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 3 categories and Qwen3.5 122B-A10B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 122B-A10B leads 27.2 to 23.3.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 17.9% for Kimi K2 (Jul 2025) and 11.2% for Qwen3.5 122B-A10B.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $0.40 / $3.20 for Qwen3.5 122B-A10B.
Side by side
| Kimi K2 (Jul 2025) | Qwen3.5 122B-A10B | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 41.2 | 42.1 |
| Released | 2025-07-12 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 66K |
| Input $ / M tokens | $0.57 | $0.40 |
| Output $ / M tokens | $2.30 | $3.20 |
| Results tracked | 42 | 27 |
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), Qwen3.5 122B-A10B: 39.1 (#162)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Coding | 1399 | 1436 |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| LMArena WebDev | — | 1360 |
| SciCode | — | 35.6% |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| ALE-Bench | 597.5 | — |
Agentic & Tool Use Not comparable
Kimi K2 (Jul 2025): 32.4 (#64), Qwen3.5 122B-A10B: —
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.5 122B-A10B |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
Reasoning Qwen3.5 122B-A10B leads
Kimi K2 (Jul 2025): 23.3 (#179), Qwen3.5 122B-A10B: 27.2 (#123)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1421 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| NYT Connections (extended) | — | 51.7% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 51.2% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84.3% |
| LMCA | — | 32.2% |
| Epoch Capabilities Index | 146.01 | — |
| ForecastBench | 60.2 | — |
Math Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.7 (#83), Qwen3.5 122B-A10B: 39.1 (#112)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | 1397 | 1432 |
| Omni-MATH | 65.4% | — |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Qwen3.5 122B-A10B leads
Kimi K2 (Jul 2025): 37.3 (#157), Qwen3.5 122B-A10B: 38.8 (#142)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.5 122B-A10B |
|---|---|---|
| Vectara Hallucination Rate | 17.9% | 11.2% |
| LMArena Expert | 1365 | 1432 |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| GPQA (HELM) | 65.3% | — |
Multimodal Not comparable
Kimi K2 (Jul 2025): —, Qwen3.5 122B-A10B: 39.6 (#57)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual Qwen3.5 122B-A10B leads
Kimi K2 (Jul 2025): 49.6 (#130), Qwen3.5 122B-A10B: 51.6 (#107)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | 1372 | 1400 |
| LMArena Chinese | 1415 | 1462 |
| LMArena French | 1379 | 1442 |
| LMArena German | 1387 | 1426 |
| LMArena Japanese | 1349 | 1367 |
| LMArena Korean | 1325 | 1352 |
| LMArena Russian | 1385 | 1400 |
| LMArena Spanish | 1386 | 1424 |
Instruction Following Qwen3.5 122B-A10B leads
Kimi K2 (Jul 2025): 71.1 (#156), Qwen3.5 122B-A10B: 73.8 (#115)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | 1348 | 1399 |
| IFEval | 85% | — |
Long Context Qwen3.5 122B-A10B leads
Kimi K2 (Jul 2025): 41.2 (#145), Qwen3.5 122B-A10B: 43.0 (#109)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | 1353 | 1410 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 62.3 (#78), Qwen3.5 122B-A10B: 60.0 (#105)
| Benchmark | Kimi K2 (Jul 2025) | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | 1380 | 1417 |
| LMArena Creative Writing | 1350 | 1368 |
| LMArena Multi-Turn | 1371 | 1416 |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Qwen3.5 122B-A10B?
Kimi K2 (Jul 2025) and Qwen3.5 122B-A10B score almost the same on the Noometry Index (41.2 vs 42.1), so choose on price, context window or the category you care about most.
Which is cheaper, Kimi K2 (Jul 2025) or Qwen3.5 122B-A10B?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Qwen3.5 122B-A10B lists at $0.40 and $3.20.
Is Kimi K2 (Jul 2025) or Qwen3.5 122B-A10B better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Kimi K2 (Jul 2025) and Qwen3.5 122B-A10B share?
18 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Qwen3.5 122B-A10B has 27.