LFM2.5-24B-A2B vs Qwen3.6 35B A3B
Wins 1 of 3 areas
Following instructions
Wins 2 of 3 areas
Coding · Reasoning
Qwen3.6 35B A3B is the stronger all-rounder.LFM2.5-24B-A2B is cheaper and better at following instructions.
Scores updated · 10 tests both models report · How we compare
Where each one wins
Tests won in each of the three areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Coding and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
LFM2.5-24B-A2B costs 71% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Qwen3.6 35B A3B pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+14.8points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+9.7points ahead
- Code for real scientific research problemsSciCode+3.9points ahead
Where LFM2.5-24B-A2B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+10.3points ahead
Every test, side by side
All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningQwen3.6 35B A3B
- Humanity's Last ExamQwen3.6 35B A3B by 14.87.422.2+14.8
- GPQA DiamondQwen3.6 35B A3B by 9.774.484.1+9.7
Following instructionsLFM2.5-24B-A2B
- IFBenchLFM2.5-24B-A2B by 10.374.764.4+10.3
Other results6 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- WebArena-VerifiedQwen3.6 35B A3B by 10.826.837.6+10.8
- PinchBenchQwen3.6 35B A3B by 6.783.289.9+6.7
- IFEvalLFM2.5-24B-A2B by 3.796.893.1+3.7
- MATH-500 (EM)tie9696.7tie
- τ³-Bench Bankingtie87.6tie
- BFCLv4tie6565tie
Questions people ask
Which is better, LFM2.5-24B-A2B or Qwen3.6 35B A3B?
Qwen3.6 35B A3B wins two of the three areas where both have results: coding and reasoning. LFM2.5-24B-A2B wins following instructions, and costs 71% less.
Which is better for coding?
Qwen3.6 35B A3B. It wins the one coding test both models report.
Which is cheaper?
LFM2.5-24B-A2B costs $0.05 per million input tokens and $0.70 per million output tokens; Qwen3.6 35B A3B costs $0.38 and $2.25. That makes LFM2.5-24B-A2B about 71% cheaper for the same work.
How do you compare the two?
We use the 10 benchmark tests both models have published scores on. The verdict counts the 4 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.