LFM2-2.6B is the stronger all-rounder.
Scores updated · 22 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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.
- FactsGetting facts right instead of making them up02LFM2-2.6B2 of 2 tests
- ReasoningHard problems that need careful thinking01LFM2-2.6B1 of 3 tests · 2 ties
- CodingWriting and fixing software01LFM2-2.6B1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
- Following instructionsDoing exactly what it is asked00Even0 each · 1 tie
Long documents and following instructions rest on a single test each.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where LFM2-2.6B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+19.4points ahead
- Recent programming contest problemsLiveCodeBench v6+10.1points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+6.9points ahead
Where Gemma 3 1B Instruct pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingLFM2-2.6B
- LiveCodeBench v6LFM2-2.6B by 10.14.314.4+10.1
- Terminal-Bench Hardtie00.8tie
ReasoningLFM2-2.6B
- GPQA DiamondLFM2-2.6B by 6.923.730.6+6.9
- Humanity's Last Examtie5.35.5tie
- CritPttie00tie
FactsLFM2-2.6B
- AA-Omniscience · Non-hallucinationLFM2-2.6B by 19.417.737.1+19.4
- AA-Omniscience · AccuracyLFM2-2.6B by 1.63.85.4+1.6
Other results13 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.
- MGSMLFM2-2.6B by 30.743.674.3+30.7
- MMLULFM2-2.6B by 24.340.164.4+24.3
- AA-OmniscienceLFM2-2.6B by 21.3-75.5-54.1+21.3
- MMMLULFM2-2.6B by 2134.455.4+21
- HumanEval+LFM2-2.6B by 20.737.257.9+20.7
- GSM8KLFM2-2.6B by 19.662.882.4+19.6
- MATH-500 (EM)LFM2-2.6B by 18.445.263.6+18.4
- MMLU-ProLFM2-2.6B by 11.314.726+11.3
- LCB v5LFM2-2.6B by 104.414.4+10
- τ²-Bench Telecom (AA run)LFM2-2.6B by 310.513.5+3
- AA Agentic IndexLFM2-2.6B by 13.54.5+1
- IFEvaltie80.279.6tie
- AA Intelligencetie4.85.2tie
Questions people ask
Which is better, Gemma 3 1B Instruct or LFM2-2.6B?
LFM2-2.6B wins three of the five areas where both have results: coding, reasoning and facts. Gemma 3 1B Instruct wins none. They are level on long documents and following instructions.
Which is better for coding?
LFM2-2.6B. It wins 1 of the 2 coding tests both models report; Gemma 3 1B Instruct wins none, and 1 is a tie.
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. The verdict counts the 9 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.