Gemma 3 1B Instruct vs LFM2-8B-A1B (Non-Reasoning)
Wins 0 of 4 areas
—
Wins 3 of 4 areas
Coding · Reasoning · Following instructions
LFM2-8B-A1B (Non-Reasoning) 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 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.
- ReasoningHard problems that need careful thinking01LFM2-8B-A1B (Non-Reasoning)1 of 3 tests · 2 ties
- CodingWriting and fixing software01LFM2-8B-A1B (Non-Reasoning)1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked01LFM2-8B-A1B (Non-Reasoning)1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Following instructions rests on a single test.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where LFM2-8B-A1B (Non-Reasoning) pulls ahead
- Recent programming contest problemsLiveCodeBench v6+16.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+10.7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+6.4points ahead
Where Gemma 3 1B Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+10points ahead
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.
CodingLFM2-8B-A1B (Non-Reasoning)
- LiveCodeBench v6LFM2-8B-A1B (Non-Reasoning) by 16.74.321+16.7
- Terminal-Bench Hardtie00tie
ReasoningLFM2-8B-A1B (Non-Reasoning)
- GPQA DiamondLFM2-8B-A1B (Non-Reasoning) by 10.723.734.4+10.7
- Humanity's Last Examtie5.34.9tie
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationGemma 3 1B Instruct by 1017.77.7+10
- AA-Omniscience · AccuracyLFM2-8B-A1B (Non-Reasoning) by 4.43.88.2+4.4
Following instructionsLFM2-8B-A1B (Non-Reasoning)
- IFBenchLFM2-8B-A1B (Non-Reasoning) by 6.419.926.3+6.4
Other results14 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.
- HumanEval+LFM2-8B-A1B (Non-Reasoning) by 32.337.269.5+32.3
- MATH-500 (EM)LFM2-8B-A1B (Non-Reasoning) by 2945.274.2+29
- MGSMLFM2-8B-A1B (Non-Reasoning) by 28.843.672.4+28.8
- BFCL v3LFM2-8B-A1B (Non-Reasoning) by 28.516.645.1+28.5
- MMLULFM2-8B-A1B (Non-Reasoning) by 24.740.164.8+24.7
- MMLU-ProLFM2-8B-A1B (Non-Reasoning) by 22.714.737.4+22.7
- MMMLULFM2-8B-A1B (Non-Reasoning) by 20.934.455.3+20.9
- BFCLv4LFM2-8B-A1B (Non-Reasoning) by 18.37.225.5+18.3
- LCB v5LFM2-8B-A1B (Non-Reasoning) by 174.421.4+17
- IFEvalGemma 3 1B Instruct by 2.680.277.6+2.6
- AA-OmniscienceGemma 3 1B Instruct by 1.1-75.5-76.5+1.1
- τ²-Bench (Retail)tie6.47tie
- AA Intelligencetie4.84.9tie
- τ²-Bench Telecom (AA run)tie10.510.5tie
Questions people ask
Which is better, Gemma 3 1B Instruct or LFM2-8B-A1B (Non-Reasoning)?
LFM2-8B-A1B (Non-Reasoning) wins three of the four areas where both have results: coding, reasoning and following instructions. Gemma 3 1B Instruct wins none. They are level on facts.
Which is better for coding?
LFM2-8B-A1B (Non-Reasoning). 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 8 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 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.