Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Claude 3 Haiku is clearly ahead on the aggregate, 49 to 30. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude 3 Haiku's sharpest advantage is in multimodal & grounded, where it averages 68.7 against 32.4. The single biggest benchmark swing on the page is MMMU-Pro, 70 to 27. 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.
Claude 3 Haiku gives you the larger context window at 200K, compared with 32K for LFM2.5-1.2B-Instruct.
Pick Claude 3 Haiku if you want the stronger benchmark profile. LFM2.5-1.2B-Instruct only becomes the better choice if instruction following is the priority.
Claude 3 Haiku
44
LFM2.5-1.2B-Instruct
25.7
Claude 3 Haiku
19.3
LFM2.5-1.2B-Instruct
7.2
Claude 3 Haiku
68.7
LFM2.5-1.2B-Instruct
32.4
Claude 3 Haiku
59.6
LFM2.5-1.2B-Instruct
32.1
Claude 3 Haiku
42.8
LFM2.5-1.2B-Instruct
26
Claude 3 Haiku
76
LFM2.5-1.2B-Instruct
80
Claude 3 Haiku
71.1
LFM2.5-1.2B-Instruct
60.7
Claude 3 Haiku
62.2
LFM2.5-1.2B-Instruct
37
Claude 3 Haiku is ahead overall, 49 to 30. The biggest single separator in this matchup is MMMU-Pro, where the scores are 70 and 27.
Claude 3 Haiku has the edge for knowledge tasks in this comparison, averaging 42.8 versus 26. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Claude 3 Haiku has the edge for coding in this comparison, averaging 19.3 versus 7.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
Claude 3 Haiku has the edge for math in this comparison, averaging 62.2 versus 37. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
Claude 3 Haiku has the edge for reasoning in this comparison, averaging 59.6 versus 32.1. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.
Claude 3 Haiku has the edge for agentic tasks in this comparison, averaging 44 versus 25.7. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.
Claude 3 Haiku has the edge for multimodal and grounded tasks in this comparison, averaging 68.7 versus 32.4. 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 76. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Claude 3 Haiku has the edge for multilingual tasks in this comparison, averaging 71.1 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.