LFM3-VL-2B is the stronger all-rounder.
Scores updated · 29 tests both models report · How we compare
Where each one wins
Tests won in each of the one area 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.
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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where LFM3-VL-2B pulls ahead
Where Qwen3.5 4B pulls ahead
- Harder college exam questions with imagesMMMU-Pro+19.7points ahead
Every test, side by side
All 29 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsLFM3-VL-2B
Other results25 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.
- ScreenSpot-v2 DesktopLFM3-VL-2B by 18.394.676.3+18.3
- HallusionBenchLFM3-VL-2B by 13.965.651.7+13.9
- RealWorldQALFM3-VL-2B by 12.279.367.1+12.2
- ScreenSpot-v2 WebLFM3-VL-2B by 12.189.977.8+12.1
- ScreenSpot-v2 MobileLFM3-VL-2B by 10.892.281.4+10.8
- MM-IFEvalLFM3-VL-2B by 9.772.863.1+9.7
- Math & logical reasoningQwen3.5 4B by 9.668.878.4+9.6
- ChartQA TestLFM3-VL-2B by 8.592.784.2+8.5
- MMBenchLFM3-VL-2B by 7.786.178.4+7.7
- MMELFM3-VL-2B by 7.486.979.5+7.4
- GeneralQwen3.5 4B by 76673+7
- TextVQA-valLFM3-VL-2B by 6.787.981.2+6.7
- Multilingual MMBenchLFM3-VL-2B by 6.683.677+6.6
- InfographicVQA (val)LFM3-VL-2B by 5.986.280.3+5.9
- MMMU (val) (Pass@1)LFM3-VL-2B by 5.455.750.3+5.4
- OCRBench v2_enLFM3-VL-2B by 4.863.558.7+4.8
- SimpleVQAQwen3.5 4B by 4.436.340.7+4.4
- MMMBLFM3-VL-2B by 3.285.282+3.2
- POPELFM3-VL-2B by 2.788.786+2.7
- SEED-Bench (image)LFM3-VL-2B by 2.578.676.1+2.5
- DocVQA-valLFM3-VL-2B by 1.996.794.8+1.9
- ERQALFM3-VL-2B by 1.948.246.3+1.9
- PerceptionQwen3.5 4B by 1.575.677.1+1.5
- OCRBench v1tie86.385.6tie
- Document, OCR & Charttie83.984.3tie
Questions people ask
Which is better, LFM3-VL-2B or Qwen3.5 4B?
LFM3-VL-2B wins the one area where both have results: images and charts. Qwen3.5 4B wins none.
How do you compare the two?
We use the 29 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 25 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.