Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Grok Code Fast 1 is clearly ahead on the aggregate, 54 to 30. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Grok Code Fast 1's sharpest advantage is in reasoning, where it averages 63.7 against 32.1. The single biggest benchmark swing on the page is HumanEval, 60 to 14. 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.
Grok Code Fast 1 gives you the larger context window at 256K, compared with 32K for LFM2.5-1.2B-Instruct.
Pick Grok Code Fast 1 if you want the stronger benchmark profile. LFM2.5-1.2B-Instruct only becomes the better choice if instruction following is the priority.
Grok Code Fast 1
55.7
LFM2.5-1.2B-Instruct
25.7
Grok Code Fast 1
32.8
LFM2.5-1.2B-Instruct
7.2
Grok Code Fast 1
50.4
LFM2.5-1.2B-Instruct
32.4
Grok Code Fast 1
63.7
LFM2.5-1.2B-Instruct
32.1
Grok Code Fast 1
48
LFM2.5-1.2B-Instruct
26
Grok Code Fast 1
79
LFM2.5-1.2B-Instruct
80
Grok Code Fast 1
73.7
LFM2.5-1.2B-Instruct
60.7
Grok Code Fast 1
67.5
LFM2.5-1.2B-Instruct
37
Grok Code Fast 1 is ahead overall, 54 to 30. The biggest single separator in this matchup is HumanEval, where the scores are 60 and 14.
Grok Code Fast 1 has the edge for knowledge tasks in this comparison, averaging 48 versus 26. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Grok Code Fast 1 has the edge for coding in this comparison, averaging 32.8 versus 7.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
Grok Code Fast 1 has the edge for math in this comparison, averaging 67.5 versus 37. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
Grok Code Fast 1 has the edge for reasoning in this comparison, averaging 63.7 versus 32.1. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.
Grok Code Fast 1 has the edge for agentic tasks in this comparison, averaging 55.7 versus 25.7. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Grok Code Fast 1 has the edge for multimodal and grounded tasks in this comparison, averaging 50.4 versus 32.4. Inside this category, OfficeQA 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 79. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Grok Code Fast 1 has the edge for multilingual tasks in this comparison, averaging 73.7 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.