Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Qwen3.5-122B-A10B
71
Winner · 3/8 categoriesQwen3.5-27B
70
3/8 categoriesQwen3.5-122B-A10B· Qwen3.5-27B
Pick Qwen3.5-122B-A10B if you want the stronger benchmark profile. Qwen3.5-27B only becomes the better choice if instruction following is the priority.
Qwen3.5-122B-A10B finishes one point ahead overall, 71 to 70. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
Qwen3.5-122B-A10B's sharpest advantage is in agentic, where it averages 56 against 51.6. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 49.4% to 41.6%. Qwen3.5-27B does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.
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 | Qwen3.5-122B-A10B | Qwen3.5-27B |
|---|---|---|
| AgenticQwen3.5-122B-A10B wins | ||
| Terminal-Bench 2.0 | 49.4% | 41.6% |
| BrowseComp | 63.8% | 61% |
| OSWorld-Verified | 58% | 56.2% |
| tau2-bench | 79.5% | 79% |
| CodingQwen3.5-27B wins | ||
| SWE-bench Verified | 72% | 72.4% |
| LiveCodeBench | 78.9% | 80.7% |
| Multimodal & GroundedQwen3.5-122B-A10B wins | ||
| MMMU-Pro | 76.9% | 75% |
| ReasoningQwen3.5-27B wins | ||
| LongBench v2 | 60.2% | 60.6% |
| KnowledgeQwen3.5-122B-A10B wins | ||
| MMLU-Pro | 86.7% | 86.1% |
| SuperGPQA | 67.1% | 65.6% |
| GPQA | 86.6% | 85.5% |
| Instruction FollowingQwen3.5-27B wins | ||
| IFEval | 93.4% | 95% |
| MultilingualTie | ||
| MMLU-ProX | 82.2% | 82.2% |
| Mathematics | ||
| Coming soon | ||
Qwen3.5-122B-A10B is ahead overall, 71 to 70. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 49.4% and 41.6%.
Qwen3.5-122B-A10B has the edge for knowledge tasks in this comparison, averaging 81.6 versus 80.6. Inside this category, SuperGPQA is the benchmark that creates the most daylight between them.
Qwen3.5-27B has the edge for coding in this comparison, averaging 77.6 versus 76.3. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
Qwen3.5-27B has the edge for reasoning in this comparison, averaging 60.6 versus 60.2. Inside this category, LongBench v2 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 51.6. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Qwen3.5-122B-A10B has the edge for multimodal and grounded tasks in this comparison, averaging 76.9 versus 75. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Qwen3.5-27B has the edge for instruction following in this comparison, averaging 95 versus 93.4. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Qwen3.5-122B-A10B and Qwen3.5-27B are effectively tied for multilingual tasks here, both landing at 82.2 on average.
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.