Gemma 4 26B A4B vs LFM2.5-24B-A2B
Wins 2 of 3 areas
Coding · Reasoning
Wins 1 of 3 areas
Following instructions
Gemma 4 26B A4B is the stronger all-rounder.LFM2.5-24B-A2B is better at following instructions.
Scores updated · 10 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.
Gemma 4 26B A4B costs 29% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Gemma 4 26B A4B pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+11.9points ahead
- Code for real scientific research problemsSciCode+7.3points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+4.8points ahead
Where LFM2.5-24B-A2B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+2.3points ahead
Every test, side by side
All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningGemma 4 26B A4B
- Humanity's Last ExamGemma 4 26B A4B by 11.919.37.4+11.9
- GPQA DiamondGemma 4 26B A4B by 4.879.274.4+4.8
Following instructionsLFM2.5-24B-A2B
- IFBenchLFM2.5-24B-A2B by 2.372.474.7+2.3
Other results6 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.
- BFCLv4LFM2.5-24B-A2B by 7.957.165+7.9
- PinchBenchLFM2.5-24B-A2B by 6.177.183.2+6.1
- IFEvalLFM2.5-24B-A2B by 4.89296.8+4.8
- τ³-Bench BankingLFM2.5-24B-A2B by 3.54.58+3.5
- WebArena-VerifiedLFM2.5-24B-A2B by 1.225.626.8+1.2
- MATH-500 (EM)tie95.796tie
Questions people ask
Which is better, Gemma 4 26B A4B or LFM2.5-24B-A2B?
Gemma 4 26B A4B wins two of the three areas where both have results: coding and reasoning. LFM2.5-24B-A2B wins following instructions.
Which is better for coding?
Gemma 4 26B A4B. It wins the one coding test both models report.
Which is cheaper?
Gemma 4 26B A4B costs $0.13 per million input tokens and $0.40 per million output tokens; LFM2.5-24B-A2B costs $0.05 and $0.70. That makes Gemma 4 26B A4B about 29% cheaper for the same work.
How do you compare the two?
We use the 10 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 6 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.