LFM2-8B-A1B (Non-Reasoning) vs Llama 3.2 3B Instruct
Wins 2 of 4 areas
Coding · Reasoning
Wins 0 of 4 areas
—
LFM2-8B-A1B (Non-Reasoning) wins more areas, narrowly.
Scores updated · 19 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.
- CodingWriting and fixing software20LFM2-8B-A1B (Non-Reasoning)2 of 2 tests
- ReasoningHard problems that need careful thinking10LFM2-8B-A1B (Non-Reasoning)1 of 2 tests · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
- Following instructionsDoing exactly what it is asked00Even0 each · 1 tie
Following instructions rests on a single test.
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 LFM2-8B-A1B (Non-Reasoning) pulls ahead
- Recent programming contest problemsLiveCodeBench v6+9.5points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+8.9points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+1.9points ahead
Where Llama 3.2 3B Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+34.8points 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.
CodingLFM2-8B-A1B (Non-Reasoning)
- LiveCodeBench v6LFM2-8B-A1B (Non-Reasoning) by 9.52111.5+9.5
- SciCodeLFM2-8B-A1B (Non-Reasoning) by 1.66.85.2+1.6
ReasoningLFM2-8B-A1B (Non-Reasoning)
- GPQA DiamondLFM2-8B-A1B (Non-Reasoning) by 8.934.425.5+8.9
- Humanity's Last Examtie4.95.3tie
FactsEven
- AA-Omniscience · Non-hallucinationLlama 3.2 3B Instruct by 34.87.742.5+34.8
- AA-Omniscience · AccuracyLFM2-8B-A1B (Non-Reasoning) by 1.98.26.3+1.9
Other results12 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 45.469.524.1+45.4
- MATH-500 (EM)LFM2-8B-A1B (Non-Reasoning) by 3374.241.2+33
- AA-OmniscienceLlama 3.2 3B Instruct by 29-76.5-47.5+29
- GSMPlusLFM2-8B-A1B (Non-Reasoning) by 26.164.838.7+26.1
- MGSMLFM2-8B-A1B (Non-Reasoning) by 14.272.458.2+14.2
- τ²-Bench Telecom (AA run)Llama 3.2 3B Instruct by 10.610.521.1+10.6
- LCB v5LFM2-8B-A1B (Non-Reasoning) by 9.921.411.5+9.9
- MMMLULFM2-8B-A1B (Non-Reasoning) by 7.455.347.9+7.4
- MMLULFM2-8B-A1B (Non-Reasoning) by 4.464.860.4+4.4
- MMLU-ProLFM2-8B-A1B (Non-Reasoning) by 2.437.435+2.4
- AA Intelligencetie4.95.7tie
- IFEvaltie77.677.4tie
Questions people ask
Which is better, LFM2-8B-A1B (Non-Reasoning) or Llama 3.2 3B Instruct?
LFM2-8B-A1B (Non-Reasoning) wins two of the four areas where both have results: coding and reasoning. Llama 3.2 3B Instruct wins none. They are level on facts and following instructions.
Which is better for coding?
LFM2-8B-A1B (Non-Reasoning). It wins 2 of the 2 coding tests both models report; Llama 3.2 3B 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 7 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.