Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Moonshot v1 is clearly ahead on the aggregate, 47 to 33. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Moonshot v1's sharpest advantage is in multimodal & grounded, where it averages 52.6 against 32.4. The single biggest benchmark swing on the page is HumanEval, 45 to 17.
LFM2.5-1.2B-Thinking is the reasoning model in the pair, while Moonshot v1 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. Moonshot v1 gives you the larger context window at 128K, compared with 32K for LFM2.5-1.2B-Thinking.
Pick Moonshot v1 if you want the stronger benchmark profile. LFM2.5-1.2B-Thinking only becomes the better choice if you want the stronger reasoning-first profile.
Moonshot v1
42.2
LFM2.5-1.2B-Thinking
34.1
Moonshot v1
26.4
LFM2.5-1.2B-Thinking
8.2
Moonshot v1
52.6
LFM2.5-1.2B-Thinking
32.4
Moonshot v1
55.5
LFM2.5-1.2B-Thinking
38.4
Moonshot v1
42.3
LFM2.5-1.2B-Thinking
27
Moonshot v1
77
LFM2.5-1.2B-Thinking
72
Moonshot v1
69.8
LFM2.5-1.2B-Thinking
60.7
Moonshot v1
61
LFM2.5-1.2B-Thinking
42.3
Moonshot v1 is ahead overall, 47 to 33. The biggest single separator in this matchup is HumanEval, where the scores are 45 and 17.
Moonshot v1 has the edge for knowledge tasks in this comparison, averaging 42.3 versus 27. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Moonshot v1 has the edge for coding in this comparison, averaging 26.4 versus 8.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
Moonshot v1 has the edge for math in this comparison, averaging 61 versus 42.3. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
Moonshot v1 has the edge for reasoning in this comparison, averaging 55.5 versus 38.4. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.
Moonshot v1 has the edge for agentic tasks in this comparison, averaging 42.2 versus 34.1. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.
Moonshot v1 has the edge for multimodal and grounded tasks in this comparison, averaging 52.6 versus 32.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Moonshot v1 has the edge for instruction following in this comparison, averaging 77 versus 72. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Moonshot v1 has the edge for multilingual tasks in this comparison, averaging 69.8 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.