Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-OSS 20B
35
1/8 categoriesLFM2.5-350M
~39
Winner · 0/8 categoriesGPT-OSS 20B· LFM2.5-350M
Pick LFM2.5-350M if you want the stronger benchmark profile. GPT-OSS 20B only becomes the better choice if knowledge is the priority or you need the larger 128K context window.
LFM2.5-350M is clearly ahead on the aggregate, 39 to 35. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-OSS 20B gives you the larger context window at 128K, compared with 32K for LFM2.5-350M.
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-OSS 20B | LFM2.5-350M |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | 35% | — |
| OSWorld-Verified | 31% | — |
| Coding | ||
| HumanEval | 23% | — |
| SWE-bench Verified | 14% | — |
| LiveCodeBench | 11% | — |
| SWE-bench Pro | 18% | — |
| React Native Evals | 64.3% | — |
| Multimodal & Grounded | ||
| MMMU-Pro | 31% | — |
| OfficeQA Pro | 42% | — |
| Reasoning | ||
| MuSR | 27% | — |
| LongBench v2 | 48% | — |
| MRCRv2 | 48% | — |
| KnowledgeGPT-OSS 20B wins | ||
| MMLU | 85.3% | — |
| GPQA | 30% | 30.6% |
| SuperGPQA | 28% | — |
| MMLU-Pro | 53% | 20.0% |
| HLE | 1% | — |
| FrontierScience | 34% | — |
| SimpleQA | 29% | — |
| Instruction Following | ||
| IFEval | — | 77.0% |
| Multilingual | ||
| MGSM | 61% | — |
| MMLU-ProX | 59% | — |
| Mathematics | ||
| AIME 2023 | 31% | — |
| AIME 2024 | 33% | — |
| AIME 2025 | 32% | — |
| HMMT Feb 2023 | 27% | — |
| HMMT Feb 2024 | 29% | — |
| HMMT Feb 2025 | 28% | — |
| BRUMO 2025 | 30% | — |
| MATH-500 | 59% | — |
LFM2.5-350M is ahead overall, 39 to 35. The biggest single separator in this matchup is MMLU-Pro, where the scores are 53% and 20.0%.
GPT-OSS 20B has the edge for knowledge tasks in this comparison, averaging 28.7 versus 23.8. 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.