Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
LFM2.5-350M
~39
0/8 categoriesLlama 3 70B
45
Winner · 1/8 categoriesLFM2.5-350M· Llama 3 70B
Pick Llama 3 70B if you want the stronger benchmark profile. LFM2.5-350M only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
Llama 3 70B is clearly ahead on the aggregate, 45 to 39. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Llama 3 70B's sharpest advantage is in knowledge, where it averages 55.6 against 23.8. The single biggest benchmark swing on the page is MMLU-Pro, 20.0% to 55%.
Llama 3 70B 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 | LFM2.5-350M | Llama 3 70B |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 37% |
| OSWorld-Verified | — | 41% |
| Coding | ||
| HumanEval | — | 50% |
| SWE-bench Verified | — | 9% |
| LiveCodeBench | — | 19% |
| SWE-bench Pro | — | 14% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 50% |
| Reasoning | ||
| MuSR | — | 54% |
| BBH | — | 74% |
| LongBench v2 | — | 61% |
| MRCRv2 | — | 61% |
| KnowledgeLlama 3 70B wins | ||
| GPQA | 30.6% | 58% |
| MMLU-Pro | 20.0% | 55% |
| MMLU | — | 58% |
| SuperGPQA | — | 56% |
| FrontierScience | — | 54% |
| SimpleQA | — | 56% |
| Instruction FollowingTie | ||
| IFEval | 77.0% | 77% |
| Multilingual | ||
| MGSM | — | 72% |
| MMLU-ProX | — | 65% |
| Mathematics | ||
| AIME 2023 | — | 58% |
| AIME 2024 | — | 60% |
| AIME 2025 | — | 59% |
| HMMT Feb 2023 | — | 54% |
| HMMT Feb 2024 | — | 56% |
| HMMT Feb 2025 | — | 55% |
| BRUMO 2025 | — | 57% |
| MATH-500 | — | 71% |
Llama 3 70B is ahead overall, 45 to 39. The biggest single separator in this matchup is MMLU-Pro, where the scores are 20.0% and 55%.
Llama 3 70B has the edge for knowledge tasks in this comparison, averaging 55.6 versus 23.8. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.
LFM2.5-350M and Llama 3 70B are effectively tied for instruction following here, both landing at 77 on average.
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.