Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Exaone 4.0 32B
~83
Winner · 1/8 categoriesQwen3.5-122B-A10B
71
0/8 categoriesExaone 4.0 32B· Qwen3.5-122B-A10B
Pick Exaone 4.0 32B if you want the stronger benchmark profile. Qwen3.5-122B-A10B only becomes the better choice if you need the larger 262K context window.
Exaone 4.0 32B is clearly ahead on the aggregate, 83 to 71. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Exaone 4.0 32B's sharpest advantage is in knowledge, where it averages 81.8 against 81.6. The single biggest benchmark swing on the page is MMLU-Pro, 81.8% to 86.7%.
Qwen3.5-122B-A10B gives you the larger context window at 262K, compared with 128K for Exaone 4.0 32B.
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 | Exaone 4.0 32B | Qwen3.5-122B-A10B |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 49.4% |
| BrowseComp | — | 63.8% |
| OSWorld-Verified | — | 58% |
| tau2-bench | — | 79.5% |
| Coding | ||
| SWE-bench Verified | — | 72% |
| LiveCodeBench | — | 78.9% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 76.9% |
| Reasoning | ||
| LongBench v2 | — | 60.2% |
| KnowledgeExaone 4.0 32B wins | ||
| MMLU-Pro | 81.8% | 86.7% |
| SuperGPQA | — | 67.1% |
| GPQA | — | 86.6% |
| Instruction Following | ||
| IFEval | — | 93.4% |
| Multilingual | ||
| MMLU-ProX | — | 82.2% |
| Mathematics | ||
| AIME 2025 | 85.3% | — |
Exaone 4.0 32B is ahead overall, 83 to 71. The biggest single separator in this matchup is MMLU-Pro, where the scores are 81.8% and 86.7%.
Exaone 4.0 32B has the edge for knowledge tasks in this comparison, averaging 81.8 versus 81.6. Inside this category, MMLU-Pro 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.