Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Composer 2
~62
1/8 categoriesQwen3.5-35B-A3B
68
Winner · 0/8 categoriesComposer 2· Qwen3.5-35B-A3B
Pick Qwen3.5-35B-A3B if you want the stronger benchmark profile. Composer 2 only becomes the better choice if agentic is the priority.
Qwen3.5-35B-A3B is clearly ahead on the aggregate, 68 to 62. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Composer 2 is also the more expensive model on tokens at $0.50 input / $2.50 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen3.5-35B-A3B. That is roughly Infinityx on output cost alone. Qwen3.5-35B-A3B gives you the larger context window at 262K, compared with 200K for Composer 2.
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 | Composer 2 | Qwen3.5-35B-A3B |
|---|---|---|
| AgenticComposer 2 wins | ||
| Terminal-Bench 2.0 | 61.7% | 40.5% |
| BrowseComp | — | 61% |
| OSWorld-Verified | — | 54.5% |
| tau2-bench | — | 81.2% |
| Coding | ||
| SWE Multilingual | 73.7% | — |
| React Native Evals | 96.2% | — |
| SWE-bench Verified | — | 69.2% |
| LiveCodeBench | — | 74.6% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 75.1% |
| Reasoning | ||
| LongBench v2 | — | 59% |
| Knowledge | ||
| MMLU-Pro | — | 85.3% |
| SuperGPQA | — | 63.4% |
| GPQA | — | 84.2% |
| Instruction Following | ||
| IFEval | — | 91.9% |
| Multilingual | ||
| MMLU-ProX | — | 81% |
| Mathematics | ||
| Coming soon | ||
Qwen3.5-35B-A3B is ahead overall, 68 to 62. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 61.7% and 40.5%.
Composer 2 has the edge for agentic tasks in this comparison, averaging 61.7 versus 50.5. Inside this category, Terminal-Bench 2.0 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.