Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 3 27B is clearly ahead on the aggregate, 38 to 33. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Gemma 3 27B's sharpest advantage is in multimodal & grounded, where it averages 41.7 against 32.4. The single biggest benchmark swing on the page is HumanEval, 37 to 17. LFM2.5-1.2B-Thinking does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.
LFM2.5-1.2B-Thinking is the reasoning model in the pair, while Gemma 3 27B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.
Pick Gemma 3 27B if you want the stronger benchmark profile. LFM2.5-1.2B-Thinking only becomes the better choice if instruction following is the priority or you want the stronger reasoning-first profile.
Gemma 3 27B
34.4
LFM2.5-1.2B-Thinking
34.1
Gemma 3 27B
16
LFM2.5-1.2B-Thinking
8.2
Gemma 3 27B
41.7
LFM2.5-1.2B-Thinking
32.4
Gemma 3 27B
45.6
LFM2.5-1.2B-Thinking
38.4
Gemma 3 27B
34.6
LFM2.5-1.2B-Thinking
27
Gemma 3 27B
67
LFM2.5-1.2B-Thinking
72
Gemma 3 27B
61.4
LFM2.5-1.2B-Thinking
60.7
Gemma 3 27B
49.4
LFM2.5-1.2B-Thinking
42.3
Gemma 3 27B is ahead overall, 38 to 33. The biggest single separator in this matchup is HumanEval, where the scores are 37 and 17.
Gemma 3 27B has the edge for knowledge tasks in this comparison, averaging 34.6 versus 27. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Gemma 3 27B has the edge for coding in this comparison, averaging 16 versus 8.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
Gemma 3 27B has the edge for math in this comparison, averaging 49.4 versus 42.3. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
Gemma 3 27B has the edge for reasoning in this comparison, averaging 45.6 versus 38.4. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.
Gemma 3 27B has the edge for agentic tasks in this comparison, averaging 34.4 versus 34.1. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Gemma 3 27B has the edge for multimodal and grounded tasks in this comparison, averaging 41.7 versus 32.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
LFM2.5-1.2B-Thinking has the edge for instruction following in this comparison, averaging 72 versus 67. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Gemma 3 27B has the edge for multilingual tasks in this comparison, averaging 61.4 versus 60.7. 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.