Qwen3 235B 2507 (Reasoning) vs LFM2.5-1.2B-Thinking

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 33. 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 coding, where it averages 22.8 against 8.2. The single biggest benchmark swing on the page is SWE-bench Pro, 29 to 7. LFM2.5-1.2B-Thinking 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) gives you the larger context window at 128K, compared with 32K for LFM2.5-1.2B-Thinking.

Quick Verdict

Pick Qwen3 235B 2507 (Reasoning) if you want the stronger benchmark profile. LFM2.5-1.2B-Thinking only becomes the better choice if instruction following is the priority.

Agentic

Qwen3 235B 2507 (Reasoning)

Qwen3 235B 2507 (Reasoning)

45.9

LFM2.5-1.2B-Thinking

34.1

47
Terminal-Bench 2.0
34
48
BrowseComp
37
43
OSWorld-Verified
32

Coding

Qwen3 235B 2507 (Reasoning)

Qwen3 235B 2507 (Reasoning)

22.8

LFM2.5-1.2B-Thinking

8.2

32
HumanEval
17
16
SWE-bench Verified
10
18
LiveCodeBench
9
29
SWE-bench Pro
7

Multimodal & Grounded

Qwen3 235B 2507 (Reasoning)

Qwen3 235B 2507 (Reasoning)

42.1

LFM2.5-1.2B-Thinking

32.4

38
MMMU-Pro
27
47
OfficeQA Pro
39

Reasoning

Qwen3 235B 2507 (Reasoning)

Qwen3 235B 2507 (Reasoning)

49

LFM2.5-1.2B-Thinking

38.4

38
SimpleQA
29
36
MuSR
31
63
BBH
67
58
LongBench v2
39
58
MRCRv2
42

Knowledge

Qwen3 235B 2507 (Reasoning)

Qwen3 235B 2507 (Reasoning)

34.1

LFM2.5-1.2B-Thinking

27

40
MMLU
27
39
GPQA
26
37
SuperGPQA
24
35
OpenBookQA
22
51
MMLU-Pro
51
6
HLE
2
42
FrontierScience
31

Instruction Following

LFM2.5-1.2B-Thinking

Qwen3 235B 2507 (Reasoning)

68

LFM2.5-1.2B-Thinking

72

68
IFEval
72

Multilingual

LFM2.5-1.2B-Thinking

Qwen3 235B 2507 (Reasoning)

58.8

LFM2.5-1.2B-Thinking

60.7

62
MGSM
62
57
MMLU-ProX
60

Mathematics

Qwen3 235B 2507 (Reasoning)

Qwen3 235B 2507 (Reasoning)

48.5

LFM2.5-1.2B-Thinking

42.3

40
AIME 2023
28
42
AIME 2024
30
41
AIME 2025
29
36
HMMT Feb 2023
24
38
HMMT Feb 2024
26
37
HMMT Feb 2025
25
39
BRUMO 2025
27
60
MATH-500
61

Frequently Asked Questions

Which is better, Qwen3 235B 2507 (Reasoning) or LFM2.5-1.2B-Thinking?

Qwen3 235B 2507 (Reasoning) is ahead overall, 42 to 33. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 29 and 7.

Which is better for knowledge tasks, Qwen3 235B 2507 (Reasoning) or LFM2.5-1.2B-Thinking?

Qwen3 235B 2507 (Reasoning) has the edge for knowledge tasks in this comparison, averaging 34.1 versus 27. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen3 235B 2507 (Reasoning) or LFM2.5-1.2B-Thinking?

Qwen3 235B 2507 (Reasoning) has the edge for coding in this comparison, averaging 22.8 versus 8.2. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, Qwen3 235B 2507 (Reasoning) or LFM2.5-1.2B-Thinking?

Qwen3 235B 2507 (Reasoning) has the edge for math in this comparison, averaging 48.5 versus 42.3. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Qwen3 235B 2507 (Reasoning) or LFM2.5-1.2B-Thinking?

Qwen3 235B 2507 (Reasoning) has the edge for reasoning in this comparison, averaging 49 versus 38.4. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3 235B 2507 (Reasoning) or LFM2.5-1.2B-Thinking?

Qwen3 235B 2507 (Reasoning) has the edge for agentic tasks in this comparison, averaging 45.9 versus 34.1. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Qwen3 235B 2507 (Reasoning) or LFM2.5-1.2B-Thinking?

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.

Which is better for instruction following, Qwen3 235B 2507 (Reasoning) or LFM2.5-1.2B-Thinking?

LFM2.5-1.2B-Thinking has the edge for instruction following in this comparison, averaging 72 versus 68. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Qwen3 235B 2507 (Reasoning) or LFM2.5-1.2B-Thinking?

LFM2.5-1.2B-Thinking 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.

Last updated: March 12, 2026

Weekly LLM Benchmark Digest

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.