The two are evenly matched.Granite 4.0 H Tiny is better at following instructions; LFM2-350M at reasoning.
Scores updated · 11 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 Granite 4.0 H Tiny pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+2points ahead
Where LFM2-350M pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+1points ahead
Every test, side by side
All 11 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Following instructionsGranite 4.0 H Tiny
- IFBenchGranite 4.0 H Tiny by 218.416.4+2
Other results9 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.
- GSM8KGranite 4.0 H Tiny by 52.582.630.1+52.5
- MGSMGranite 4.0 H Tiny by 44.273.729.5+44.2
- BFCL v3Granite 4.0 H Tiny by 33.956.922.9+33.9
- MMLUGranite 4.0 H Tiny by 23.466.843.4+23.4
- MMMLUGranite 4.0 H Tiny by 18.156.138+18.1
- BFCLv4Granite 4.0 H Tiny by 16.228.512.3+16.2
- IFEvalGranite 4.0 H Tiny by 1681.165.1+16
- τ²-Bench (Retail)Granite 4.0 H Tiny by 12.818.45.6+12.8
- MMLU-ProGranite 4.0 H Tiny by 12.73219.3+12.7
Questions people ask
Which is better, Granite 4.0 H Tiny or LFM2-350M?
Granite 4.0 H Tiny and LFM2-350M each win one of the two areas where both have results. Granite 4.0 H Tiny wins following instructions; LFM2-350M wins reasoning.
How do you compare the two?
We use the 11 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 9 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.