Gemma 4 26B A4B vs LFM2.5-1.2B-Instruct
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
Wins 0 of 6 areas
—
Gemma 4 26B A4B is the stronger all-rounder.
Scores updated · 19 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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.
- ReasoningHard problems that need careful thinking20Gemma 4 26B A4B2 of 3 tests · 1 tie
- CodingWriting and fixing software20Gemma 4 26B A4B2 of 2 tests
- AgentsCarrying out multi-step tasks on its own10Gemma 4 26B A4B1 of 1 test
- Long documentsFinding answers in very long texts10Gemma 4 26B A4B1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemma 4 26B A4B1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Agents, long documents 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
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+46.6points ahead
- Code for real scientific research problemsSciCode+37.7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+28.6points ahead
Where LFM2.5-1.2B-Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+1.3points ahead
Every test, side by side
All 19 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 37.7402.3+37.7
- Terminal-Bench HardGemma 4 26B A4B by 13.613.60+13.6
ReasoningGemma 4 26B A4B
- GPQA DiamondGemma 4 26B A4B by 46.679.232.6+46.6
- Humanity's Last ExamGemma 4 26B A4B by 12.619.36.7+12.6
- CritPttie00tie
FactsEven
- AA-Omniscience · AccuracyGemma 4 26B A4B by 12.119.17+12.1
- AA-Omniscience · Non-hallucinationLFM2.5-1.2B-Instruct by 1.313.614.9+1.3
Following instructionsGemma 4 26B A4B
- IFBenchGemma 4 26B A4B by 28.672.443.8+28.6
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.
- MATH-500 (EM)Gemma 4 26B A4B by 89.995.75.8+89.9
- MBPPGemma 4 26B A4B by 62.968.45.5+62.9
- HumanEvalGemma 4 26B A4B by 44.7505.3+44.7
- MMLU-ProGemma 4 26B A4B by 38.282.644.4+38.2
- τ²-Bench Telecom (AA run)Gemma 4 26B A4B by 32.843.610.8+32.8
- AA-OmniscienceGemma 4 26B A4B by 21.3-50.8-72.1+21.3
- AA IntelligenceGemma 4 26B A4B by 11.516.75.2+11.5
- AA Agentic IndexGemma 4 26B A4B by 7.4113.6+7.4
- IFEvalGemma 4 26B A4B by 5.89286.2+5.8
Questions people ask
Which is better, Gemma 4 26B A4B or LFM2.5-1.2B-Instruct?
Gemma 4 26B A4B wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. LFM2.5-1.2B-Instruct wins none. They are level on facts.
Which is better for coding?
Gemma 4 26B A4B. It wins 2 of the 2 coding tests both models report; LFM2.5-1.2B-Instruct wins none.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 10 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.