The two are evenly matched.Gemma 3 1B Instruct is better at following instructions; LFM2-350M at reasoning.
Scores updated · 12 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 Gemma 3 1B Instruct pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+3.5points ahead
Where LFM2-350M pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+3.8points ahead
Every test, side by side
All 12 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Following instructionsGemma 3 1B Instruct
- IFBenchGemma 3 1B Instruct by 3.519.916.4+3.5
Other results10 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.
- GSM8KGemma 3 1B Instruct by 32.762.830.1+32.7
- IFEvalGemma 3 1B Instruct by 15.180.265.1+15.1
- MGSMGemma 3 1B Instruct by 14.143.629.5+14.1
- BFCL v3LFM2-350M by 6.416.622.9+6.4
- BFCLv4LFM2-350M by 5.17.212.3+5.1
- MMLU-ProLFM2-350M by 4.614.719.3+4.6
- MMMLULFM2-350M by 3.634.438+3.6
- MMLULFM2-350M by 3.340.143.4+3.3
- τ²-BenchLFM2-350M by 1.49.410.8+1.4
- τ²-Bench (Retail)tie6.45.6tie
Questions people ask
Which is better, Gemma 3 1B Instruct or LFM2-350M?
Gemma 3 1B Instruct and LFM2-350M each win one of the two areas where both have results. Gemma 3 1B Instruct wins following instructions; LFM2-350M wins reasoning.
How do you compare the two?
We use the 12 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 10 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.