Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Kimi K2
60
0/8 categoriesQwen3.5-122B-A10B
71
Winner · 4/8 categoriesKimi K2· Qwen3.5-122B-A10B
Pick Qwen3.5-122B-A10B if you want the stronger benchmark profile. Kimi K2 only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.
Qwen3.5-122B-A10B is clearly ahead on the aggregate, 71 to 60. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Qwen3.5-122B-A10B's sharpest advantage is in coding, where it averages 76.3 against 58.2. The single biggest benchmark swing on the page is LiveCodeBench, 53.7% to 78.9%.
Qwen3.5-122B-A10B is the reasoning model in the pair, while Kimi K2 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Qwen3.5-122B-A10B gives you the larger context window at 262K, compared with 128K for Kimi K2.
BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.
Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.
| Benchmark | Kimi K2 | Qwen3.5-122B-A10B |
|---|---|---|
| AgenticQwen3.5-122B-A10B wins | ||
| Terminal-Bench 2.0 | 47.1% | 49.4% |
| BrowseComp | 60.2% | 63.8% |
| tau2-bench | 66.1% | 79.5% |
| OSWorld-Verified | — | 58% |
| CodingQwen3.5-122B-A10B wins | ||
| SWE-bench Verified | 65.8% | 72% |
| LiveCodeBench | 53.7% | 78.9% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 76.9% |
| Reasoning | ||
| hle | 44.9% | — |
| LongBench v2 | — | 60.2% |
| KnowledgeQwen3.5-122B-A10B wins | ||
| MMLU | 89.5% | — |
| GPQA | 75.1% | 86.6% |
| SuperGPQA | 57.2% | 67.1% |
| MMLU-Pro | 81.1% | 86.7% |
| SimpleQA | 31% | — |
| Instruction FollowingQwen3.5-122B-A10B wins | ||
| IFEval | 89.8% | 93.4% |
| Multilingual | ||
| sweMultilingual | 61.1% | — |
| MMLU-ProX | — | 82.2% |
| Mathematics | ||
| AIME 2024 | 69.6% | — |
| AIME 2025 | 49.5% | — |
| MATH-500 | 97.4% | — |
| HMMT Feb 2025 | 38.8% | — |
Qwen3.5-122B-A10B is ahead overall, 71 to 60. The biggest single separator in this matchup is LiveCodeBench, where the scores are 53.7% and 78.9%.
Qwen3.5-122B-A10B has the edge for knowledge tasks in this comparison, averaging 81.6 versus 64. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Qwen3.5-122B-A10B has the edge for coding in this comparison, averaging 76.3 versus 58.2. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
Qwen3.5-122B-A10B has the edge for agentic tasks in this comparison, averaging 56 versus 52.1. Inside this category, tau2-bench is the benchmark that creates the most daylight between them.
Qwen3.5-122B-A10B has the edge for instruction following in this comparison, averaging 93.4 versus 89.8. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.