InternVL3_5-2B vs LFM2.5-VL-1.6B
Wins 1 of 2 areas
Images and charts
Wins 1 of 2 areas
Following instructions
The two are evenly matched.InternVL3_5-2B is better at images and charts; LFM2.5-VL-1.6B at following instructions.
Scores updated · 14 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.
Following instructions rests on a single test.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where InternVL3_5-2B pulls ahead
Every test, side by side
All 14 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsInternVL3_5-2B
Following instructionsLFM2.5-VL-1.6B
- IFBenchLFM2.5-VL-1.6B by 8.724.433.1+8.7
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.
- VLM Judge ScoreInternVL3_5-2B by 21.787.766+21.7
- HallusionBenchLFM2.5-VL-1.6B by 12.547.660.1+12.5
- MMMU (val) (Pass@1)InternVL3_5-2B by 11.45240.6+11.4
- ChartQA TestInternVL3_5-2B by 7.881.773.9+7.8
- MM-IFEvalLFM2.5-VL-1.6B by 5.247.152.3+5.2
- MMMBInternVL3_5-2B by 4.676.371.7+4.6
- OCRBench v2_enInternVL3_5-2B by 445.541.5+4
- RealWorldQALFM2.5-VL-1.6B by 3.261.664.8+3.2
- DocVQA-valtie88.487.7tie
Questions people ask
Which is better, InternVL3_5-2B or LFM2.5-VL-1.6B?
InternVL3_5-2B and LFM2.5-VL-1.6B each win one of the two areas where both have results. InternVL3_5-2B wins images and charts; LFM2.5-VL-1.6B wins following instructions.
How do you compare the two?
We use the 14 benchmark tests both models have published scores on. The verdict counts the 5 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.