Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
LFM2.5-1.2B-Thinking finishes one point ahead overall, 33 to 32. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
LFM2.5-1.2B-Thinking's sharpest advantage is in agentic, where it averages 34.1 against 28.9. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 34 to 26. Ministral 3 8B does hit back in coding, 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 Ministral 3 8B 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. Ministral 3 8B gives you the larger context window at 128K, compared with 32K for LFM2.5-1.2B-Thinking.
Pick LFM2.5-1.2B-Thinking if you want the stronger benchmark profile. Ministral 3 8B only becomes the better choice if coding is the priority or you need the larger 128K context window.
LFM2.5-1.2B-Thinking
34.1
Ministral 3 8B
28.9
LFM2.5-1.2B-Thinking
8.2
Ministral 3 8B
14.2
LFM2.5-1.2B-Thinking
32.4
Ministral 3 8B
32.4
LFM2.5-1.2B-Thinking
38.4
Ministral 3 8B
36.1
LFM2.5-1.2B-Thinking
27
Ministral 3 8B
28
LFM2.5-1.2B-Thinking
72
Ministral 3 8B
69
LFM2.5-1.2B-Thinking
60.7
Ministral 3 8B
61.7
LFM2.5-1.2B-Thinking
42.3
Ministral 3 8B
43.3
LFM2.5-1.2B-Thinking is ahead overall, 33 to 32. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 34 and 26.
Ministral 3 8B has the edge for knowledge tasks in this comparison, averaging 28 versus 27. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Ministral 3 8B has the edge for coding in this comparison, averaging 14.2 versus 8.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
Ministral 3 8B has the edge for math in this comparison, averaging 43.3 versus 42.3. Inside this category, AIME 2025 is the benchmark that creates the most daylight between them.
LFM2.5-1.2B-Thinking has the edge for reasoning in this comparison, averaging 38.4 versus 36.1. Inside this category, MuSR is the benchmark that creates the most daylight between them.
LFM2.5-1.2B-Thinking has the edge for agentic tasks in this comparison, averaging 34.1 versus 28.9. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
LFM2.5-1.2B-Thinking and Ministral 3 8B are effectively tied for multimodal and grounded tasks here, both landing at 32.4 on average.
LFM2.5-1.2B-Thinking has the edge for instruction following in this comparison, averaging 72 versus 69. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Ministral 3 8B has the edge for multilingual tasks in this comparison, averaging 61.7 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.