LFM2.5-1.2B-Thinking vs Qwen3 1.7B (instruct)
Wins 1 of 2 areas
Following instructions
Wins 1 of 2 areas
Reasoning
The two are evenly matched.LFM2.5-1.2B-Thinking is better at following instructions; Qwen3 1.7B (instruct) at reasoning.
Scores updated · 8 tests both models report · How we compare
Where each one wins
Tests won in each of the two 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.
Reasoning and following instructions rest on a single test each.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where LFM2.5-1.2B-Thinking pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+20.5points ahead
Where Qwen3 1.7B (instruct) pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+1points ahead
Every test, side by side
All 8 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningQwen3 1.7B (instruct)
- GPQA DiamondQwen3 1.7B (instruct) by 133.934.9+1
Following instructionsLFM2.5-1.2B-Thinking
- IFBenchLFM2.5-1.2B-Thinking by 20.541.821.3+20.5
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.
- GSM8KLFM2.5-1.2B-Thinking by 51.985.633.7+51.9
- AIME25 no toolsLFM2.5-1.2B-Thinking by 22.431.79.3+22.4
- MATH-500 (EM)LFM2.5-1.2B-Thinking by 17.68870.4+17.6
- IFEvalLFM2.5-1.2B-Thinking by 14.788.473.7+14.7
- BFCL v3LFM2.5-1.2B-Thinking by 10.75746.3+10.7
- MMLU-ProLFM2.5-1.2B-Thinking by 6.849.642.9+6.8
Questions people ask
Which is better, LFM2.5-1.2B-Thinking or Qwen3 1.7B (instruct)?
LFM2.5-1.2B-Thinking and Qwen3 1.7B (instruct) each win one of the two areas where both have results. LFM2.5-1.2B-Thinking wins following instructions; Qwen3 1.7B (instruct) wins reasoning.
How do you compare the two?
We use the 8 benchmark tests both models have published scores on. The verdict counts the 2 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.