Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Granite-4.0-H-1B
~43
0/8 categoriesQwen3 235B 2507
48
Winner · 3/8 categoriesGranite-4.0-H-1B· Qwen3 235B 2507
Pick Qwen3 235B 2507 if you want the stronger benchmark profile. Granite-4.0-H-1B only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
Qwen3 235B 2507 is clearly ahead on the aggregate, 48 to 43. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Qwen3 235B 2507's sharpest advantage is in multilingual, where it averages 73.7 against 37.8. The single biggest benchmark swing on the page is MMLU-Pro, 34.0% to 83%.
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 | Granite-4.0-H-1B | Qwen3 235B 2507 |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 33% |
| BrowseComp | — | 40% |
| OSWorld-Verified | — | 30% |
| Coding | ||
| HumanEval | 74% | 31% |
| SWE-bench Verified | — | 15% |
| LiveCodeBench | — | 51.8% |
| SWE-bench Pro | — | 19% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 38% |
| OfficeQA Pro | — | 46% |
| Reasoning | ||
| BBH | 60.4% | 60% |
| MuSR | — | 35% |
| LongBench v2 | — | 52% |
| MRCRv2 | — | 52% |
| KnowledgeQwen3 235B 2507 wins | ||
| MMLU | 59.4% | 39% |
| GPQA | 29.9% | 77.5% |
| MMLU-Pro | 34.0% | 83% |
| SuperGPQA | — | 62.6% |
| FrontierScience | — | 39% |
| SimpleQA | — | 54.3% |
| Instruction FollowingQwen3 235B 2507 wins | ||
| IFEval | 77.4% | 88.7% |
| MultilingualQwen3 235B 2507 wins | ||
| MGSM | 37.8% | 63% |
| MMLU-ProX | — | 79.4% |
| Mathematics | ||
| AIME 2023 | — | 39% |
| AIME 2024 | — | 41% |
| AIME 2025 | — | 70.3% |
| HMMT Feb 2023 | — | 35% |
| HMMT Feb 2024 | — | 37% |
| HMMT Feb 2025 | — | 36% |
| BRUMO 2025 | — | 38% |
| MATH-500 | — | 57% |
Qwen3 235B 2507 is ahead overall, 48 to 43. The biggest single separator in this matchup is MMLU-Pro, where the scores are 34.0% and 83%.
Qwen3 235B 2507 has the edge for knowledge tasks in this comparison, averaging 63.8 versus 32.6. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.
Qwen3 235B 2507 has the edge for instruction following in this comparison, averaging 88.7 versus 77.4. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Qwen3 235B 2507 has the edge for multilingual tasks in this comparison, averaging 73.7 versus 37.8. Inside this category, MGSM 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.