Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
DeepSeek-R1 is clearly ahead on the aggregate, 43 to 38. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
DeepSeek-R1's sharpest advantage is in agentic, where it averages 44.5 against 33.4. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 42 to 30. LFM2-24B-A2B does hit back in multilingual, so the answer changes if that is the part of the workload you care about most.
DeepSeek-R1 is also the more expensive model on tokens at $0.55 input / $2.19 output per 1M tokens, versus $0.03 input / $0.12 output per 1M tokens for LFM2-24B-A2B. That is roughly 18.3x on output cost alone. DeepSeek-R1 is the reasoning model in the pair, while LFM2-24B-A2B 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. DeepSeek-R1 gives you the larger context window at 128K, compared with 32K for LFM2-24B-A2B.
Pick DeepSeek-R1 if you want the stronger benchmark profile. LFM2-24B-A2B only becomes the better choice if multilingual is the priority or you want the cheaper token bill.
DeepSeek-R1
44.5
LFM2-24B-A2B
33.4
DeepSeek-R1
21.5
LFM2-24B-A2B
18
DeepSeek-R1
47.5
LFM2-24B-A2B
41.7
DeepSeek-R1
50.9
LFM2-24B-A2B
46.6
DeepSeek-R1
37.9
LFM2-24B-A2B
35.6
DeepSeek-R1
69
LFM2-24B-A2B
68
DeepSeek-R1
60.4
LFM2-24B-A2B
61.4
DeepSeek-R1
52.5
LFM2-24B-A2B
50.4
DeepSeek-R1 is ahead overall, 43 to 38. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 42 and 30.
DeepSeek-R1 has the edge for knowledge tasks in this comparison, averaging 37.9 versus 35.6. Inside this category, HLE is the benchmark that creates the most daylight between them.
DeepSeek-R1 has the edge for coding in this comparison, averaging 21.5 versus 18. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
DeepSeek-R1 has the edge for math in this comparison, averaging 52.5 versus 50.4. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.
DeepSeek-R1 has the edge for reasoning in this comparison, averaging 50.9 versus 46.6. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.
DeepSeek-R1 has the edge for agentic tasks in this comparison, averaging 44.5 versus 33.4. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
DeepSeek-R1 has the edge for multimodal and grounded tasks in this comparison, averaging 47.5 versus 41.7. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.
DeepSeek-R1 has the edge for instruction following in this comparison, averaging 69 versus 68. Inside this category, IFEval is the benchmark that creates the most daylight between them.
LFM2-24B-A2B has the edge for multilingual tasks in this comparison, averaging 61.4 versus 60.4. 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.