Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Mistral 8x7B v0.2 has the cleaner overall profile here, landing at 32 versus 30. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Mistral 8x7B v0.2's sharpest advantage is in coding, where it averages 13.3 against 7.2. The single biggest benchmark swing on the page is IFEval, 67 to 80. LFM2.5-1.2B-Instruct does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.
Pick Mistral 8x7B v0.2 if you want the stronger benchmark profile. LFM2.5-1.2B-Instruct only becomes the better choice if instruction following is the priority.
Mistral 8x7B v0.2
27.9
LFM2.5-1.2B-Instruct
25.7
Mistral 8x7B v0.2
13.3
LFM2.5-1.2B-Instruct
7.2
Mistral 8x7B v0.2
32.3
LFM2.5-1.2B-Instruct
32.4
Mistral 8x7B v0.2
35.2
LFM2.5-1.2B-Instruct
32.1
Mistral 8x7B v0.2
28.9
LFM2.5-1.2B-Instruct
26
Mistral 8x7B v0.2
67
LFM2.5-1.2B-Instruct
80
Mistral 8x7B v0.2
58.8
LFM2.5-1.2B-Instruct
60.7
Mistral 8x7B v0.2
42
LFM2.5-1.2B-Instruct
37
Mistral 8x7B v0.2 is ahead overall, 32 to 30. The biggest single separator in this matchup is IFEval, where the scores are 67 and 80.
Mistral 8x7B v0.2 has the edge for knowledge tasks in this comparison, averaging 28.9 versus 26. Inside this category, FrontierScience is the benchmark that creates the most daylight between them.
Mistral 8x7B v0.2 has the edge for coding in this comparison, averaging 13.3 versus 7.2. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
Mistral 8x7B v0.2 has the edge for math in this comparison, averaging 42 versus 37. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
Mistral 8x7B v0.2 has the edge for reasoning in this comparison, averaging 35.2 versus 32.1. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
Mistral 8x7B v0.2 has the edge for agentic tasks in this comparison, averaging 27.9 versus 25.7. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.
LFM2.5-1.2B-Instruct has the edge for multimodal and grounded tasks in this comparison, averaging 32.4 versus 32.3. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
LFM2.5-1.2B-Instruct has the edge for instruction following in this comparison, averaging 80 versus 67. Inside this category, IFEval is the benchmark that creates the most daylight between them.
LFM2.5-1.2B-Instruct has the edge for multilingual tasks in this comparison, averaging 60.7 versus 58.8. 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.