LFM2-2.6B 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 · 21 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 software02LFM2-8B-A1B (Non-Reasoning)2 of 3 tests · 1 tie
- ReasoningHard problems that need careful thinking01LFM2-8B-A1B (Non-Reasoning)1 of 3 tests · 2 ties
- 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
- Follows unfamiliar, precisely checkable instructionsIFBench+6.8points ahead
- Recent programming contest problemsLiveCodeBench v6+6.6points ahead
- Code for real scientific research problemsSciCode+4.3points ahead
Where LFM2-2.6B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+29.4points ahead
Every test, side by side
All 21 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 6.614.421+6.6
- SciCodeLFM2-8B-A1B (Non-Reasoning) by 4.32.56.8+4.3
- Terminal-Bench Hardtie0.80tie
ReasoningLFM2-8B-A1B (Non-Reasoning)
- GPQA DiamondLFM2-8B-A1B (Non-Reasoning) by 3.830.634.4+3.8
- Humanity's Last Examtie5.54.9tie
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationLFM2-2.6B by 29.437.17.7+29.4
- AA-Omniscience · AccuracyLFM2-8B-A1B (Non-Reasoning) by 2.85.48.2+2.8
Following instructionsLFM2-8B-A1B (Non-Reasoning)
- IFBenchLFM2-8B-A1B (Non-Reasoning) by 6.819.526.3+6.8
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.
- AA-OmniscienceLFM2-2.6B by 22.4-54.1-76.5+22.4
- HumanEval+LFM2-8B-A1B (Non-Reasoning) by 11.657.969.5+11.6
- MMLU-ProLFM2-8B-A1B (Non-Reasoning) by 11.42637.4+11.4
- MATH-500 (EM)LFM2-8B-A1B (Non-Reasoning) by 10.663.674.2+10.6
- LCB v5LFM2-8B-A1B (Non-Reasoning) by 714.421.4+7
- GSMPlusLFM2-8B-A1B (Non-Reasoning) by 460.864.8+4
- τ²-Bench Telecom (AA run)LFM2-2.6B by 313.510.5+3
- IFEvalLFM2-2.6B by 279.677.6+2
- MGSMLFM2-2.6B by 1.974.372.4+1.9
- MMLUtie64.464.8tie
- AA Intelligencetie5.24.9tie
- MMMLUtie55.455.3tie
Questions people ask
Which is better, LFM2-2.6B 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. LFM2-2.6B wins none. They are level on facts.
Which is better for coding?
LFM2-8B-A1B (Non-Reasoning). It wins 2 of the 3 coding tests both models report; LFM2-2.6B wins none, and 1 is a tie.
How do you compare the two?
We use the 21 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 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.