Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Llama 4 Maverick is clearly ahead on the aggregate, 43 to 33. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Llama 4 Maverick's sharpest advantage is in multimodal & grounded, where it averages 56.8 against 32.4. The single biggest benchmark swing on the page is MMMU-Pro, 59 to 27. 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 Llama 4 Maverick 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. Llama 4 Maverick gives you the larger context window at 1M, compared with 32K for LFM2.5-1.2B-Thinking.
Pick Llama 4 Maverick 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.
Llama 4 Maverick
40.9
LFM2.5-1.2B-Thinking
34.1
Llama 4 Maverick
15.7
LFM2.5-1.2B-Thinking
8.2
Llama 4 Maverick
56.8
LFM2.5-1.2B-Thinking
32.4
Llama 4 Maverick
54
LFM2.5-1.2B-Thinking
38.4
Llama 4 Maverick
36.5
LFM2.5-1.2B-Thinking
27
Llama 4 Maverick
68
LFM2.5-1.2B-Thinking
72
Llama 4 Maverick
59.8
LFM2.5-1.2B-Thinking
60.7
Llama 4 Maverick
51.3
LFM2.5-1.2B-Thinking
42.3
Llama 4 Maverick is ahead overall, 43 to 33. The biggest single separator in this matchup is MMMU-Pro, where the scores are 59 and 27.
Llama 4 Maverick has the edge for knowledge tasks in this comparison, averaging 36.5 versus 27. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Llama 4 Maverick has the edge for coding in this comparison, averaging 15.7 versus 8.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
Llama 4 Maverick has the edge for math in this comparison, averaging 51.3 versus 42.3. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
Llama 4 Maverick has the edge for reasoning in this comparison, averaging 54 versus 38.4. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
Llama 4 Maverick has the edge for agentic tasks in this comparison, averaging 40.9 versus 34.1. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.
Llama 4 Maverick has the edge for multimodal and grounded tasks in this comparison, averaging 56.8 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 68. Inside this category, IFEval is the benchmark that creates the most daylight between them.
LFM2.5-1.2B-Thinking has the edge for multilingual tasks in this comparison, averaging 60.7 versus 59.8. Inside this category, MMLU-ProX 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.