Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-4.1 nano
44
0/8 categoriesHolo3-35B-A3B
~78
Winner · 1/8 categoriesGPT-4.1 nano· Holo3-35B-A3B
Pick Holo3-35B-A3B if you want the stronger benchmark profile. GPT-4.1 nano only becomes the better choice if you want the cheaper token bill or you need the larger 1M context window.
Holo3-35B-A3B is clearly ahead on the aggregate, 78 to 44. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Holo3-35B-A3B's sharpest advantage is in agentic, where it averages 77.8 against 47.4. The single biggest benchmark swing on the page is OSWorld-Verified, 42% to 77.8%.
Holo3-35B-A3B is also the more expensive model on tokens at $0.25 input / $1.80 output per 1M tokens, versus $0.10 input / $0.40 output per 1M tokens for GPT-4.1 nano. That is roughly 4.5x on output cost alone. GPT-4.1 nano gives you the larger context window at 1M, compared with 64K for Holo3-35B-A3B.
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 | GPT-4.1 nano | Holo3-35B-A3B |
|---|---|---|
| AgenticHolo3-35B-A3B wins | ||
| Terminal-Bench 2.0 | 43% | — |
| BrowseComp | 62% | — |
| OSWorld-Verified | 42% | 77.8% |
| Coding | ||
| SWE-bench Pro | 18% | — |
| Multimodal & Grounded | ||
| MMMU-Pro | 53% | — |
| OfficeQA Pro | 67% | — |
| Reasoning | ||
| LongBench v2 | 75% | — |
| MRCRv2 | 73% | — |
| Knowledge | ||
| MMLU | 80.1% | — |
| GPQA | 50.3% | — |
| FrontierScience | 51% | — |
| Instruction Following | ||
| IFEval | 83.2% | — |
| Multilingual | ||
| MMLU-ProX | 59% | — |
| Mathematics | ||
| AIME 2024 | 9.8% | — |
Holo3-35B-A3B is ahead overall, 78 to 44. The biggest single separator in this matchup is OSWorld-Verified, where the scores are 42% and 77.8%.
Holo3-35B-A3B has the edge for agentic tasks in this comparison, averaging 77.8 versus 47.4. Inside this category, OSWorld-Verified 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.