Gemma 4 26B A4B is the stronger all-rounder.
Scores updated · 10 tests both models report · How we compare
Where each one wins
Tests won in each of the four 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.
Agents 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 Gemma 4 26B A4B pulls ahead
- Multi-step tasks using many real software toolsMCP Atlas+17.4points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+15.8points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+12.1points ahead
Where LFM3-1.7B pulls ahead
No clear win on a test scored out of 100.
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.
CodingGemma 4 26B A4B
- SciCodeGemma 4 26B A4B by 11.54028.5+11.5
- LiveCodeBench v6Gemma 4 26B A4B by 3.677.173.5+3.6
ReasoningGemma 4 26B A4B
- GPQA DiamondGemma 4 26B A4B by 15.879.263.4+15.8
- Humanity's Last ExamGemma 4 26B A4B by 12.119.37.2+12.1
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.
- BFCLv4LFM3-1.7B by 14.357.171.4+14.3
- WebArena-VerifiedLFM3-1.7B by 12.825.638.4+12.8
- IFEvalLFM3-1.7B by 4.79296.7+4.7
- HLE (with tools)Gemma 4 26B A4B by 3.317.213.9+3.3
Questions people ask
Which is better, Gemma 4 26B A4B or LFM3-1.7B?
Gemma 4 26B A4B wins three of the four areas where both have results: coding, agents and reasoning. LFM3-1.7B wins none. They are level on following instructions.
Which is better for coding?
Gemma 4 26B A4B. It wins 2 of the 2 coding tests both models report; LFM3-1.7B wins none.
How do you compare the two?
We use the 10 benchmark tests both models have published scores on. The verdict counts the 6 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.