Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Qwen3 235B 2507 (Reasoning) is clearly ahead on the aggregate, 42 to 30. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Qwen3 235B 2507 (Reasoning)'s sharpest advantage is in agentic, where it averages 45.9 against 25.7. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 47 to 22. 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.
Qwen3 235B 2507 (Reasoning) is the reasoning model in the pair, while LFM2.5-1.2B-Instruct 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. Qwen3 235B 2507 (Reasoning) gives you the larger context window at 128K, compared with 32K for LFM2.5-1.2B-Instruct.
Pick Qwen3 235B 2507 (Reasoning) if you want the stronger benchmark profile. LFM2.5-1.2B-Instruct only becomes the better choice if instruction following is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Qwen3 235B 2507 (Reasoning)
45.9
LFM2.5-1.2B-Instruct
25.7
Qwen3 235B 2507 (Reasoning)
22.8
LFM2.5-1.2B-Instruct
7.2
Qwen3 235B 2507 (Reasoning)
42.1
LFM2.5-1.2B-Instruct
32.4
Qwen3 235B 2507 (Reasoning)
49
LFM2.5-1.2B-Instruct
32.1
Qwen3 235B 2507 (Reasoning)
34.1
LFM2.5-1.2B-Instruct
26
Qwen3 235B 2507 (Reasoning)
68
LFM2.5-1.2B-Instruct
80
Qwen3 235B 2507 (Reasoning)
58.8
LFM2.5-1.2B-Instruct
60.7
Qwen3 235B 2507 (Reasoning)
48.5
LFM2.5-1.2B-Instruct
37
Qwen3 235B 2507 (Reasoning) is ahead overall, 42 to 30. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 47 and 22.
Qwen3 235B 2507 (Reasoning) has the edge for knowledge tasks in this comparison, averaging 34.1 versus 26. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Qwen3 235B 2507 (Reasoning) has the edge for coding in this comparison, averaging 22.8 versus 7.2. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
Qwen3 235B 2507 (Reasoning) has the edge for math in this comparison, averaging 48.5 versus 37. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
Qwen3 235B 2507 (Reasoning) has the edge for reasoning in this comparison, averaging 49 versus 32.1. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
Qwen3 235B 2507 (Reasoning) has the edge for agentic tasks in this comparison, averaging 45.9 versus 25.7. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Qwen3 235B 2507 (Reasoning) has the edge for multimodal and grounded tasks in this comparison, averaging 42.1 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 68. 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.