Gemma 4 E2B vs LFM2.5-24B-A2B
Wins 0 of 3 areas
—
Wins 3 of 3 areas
Coding · Reasoning · Following instructions
LFM2.5-24B-A2B is the stronger all-rounder.
Scores updated · 8 tests both models report · How we compare
Where each one wins
Tests won in each of the three 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.
Coding and following instructions rest on a single test each.
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 LFM2.5-24B-A2B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+36.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+31.1points ahead
- Code for real scientific research problemsSciCode+11.8points ahead
Where Gemma 4 E2B pulls ahead
No clear win on a test scored out of 100.
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.
ReasoningLFM2.5-24B-A2B
- GPQA DiamondLFM2.5-24B-A2B by 31.143.374.4+31.1
- Humanity's Last ExamLFM2.5-24B-A2B by 2.64.87.4+2.6
Following instructionsLFM2.5-24B-A2B
- IFBenchLFM2.5-24B-A2B by 36.73874.7+36.7
Other results4 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.
- PinchBenchLFM2.5-24B-A2B by 3944.283.2+39
- BFCLv4LFM2.5-24B-A2B by 283765+28
- IFEvalLFM2.5-24B-A2B by 13.88396.8+13.8
- τ³-Bench BankingLFM2.5-24B-A2B by 4.63.48+4.6
Questions people ask
Which is better, Gemma 4 E2B or LFM2.5-24B-A2B?
LFM2.5-24B-A2B wins all three areas where both have results: coding, reasoning and following instructions. Gemma 4 E2B wins none.
Which is better for coding?
LFM2.5-24B-A2B. It wins the one coding test both models report.
How do you compare the two?
We use the 8 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 4 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.