Gemma 4 E2B vs LFM2-8B-A1B (Non-Reasoning)
Wins 3 of 4 areas
Coding · Reasoning · Following instructions
Wins 0 of 4 areas
—
Gemma 4 E2B 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.
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 Gemma 4 E2B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+59.9points ahead
- Recent programming contest problemsLiveCodeBench v6+23points ahead
- Code for real scientific research problemsSciCode+14.1points ahead
Where LFM2-8B-A1B (Non-Reasoning) pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+1.6points 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.
CodingGemma 4 E2B
- LiveCodeBench v6Gemma 4 E2B by 234421+23
- SciCodeGemma 4 E2B by 14.120.96.8+14.1
- Terminal-Bench HardGemma 4 E2B by 330+3
ReasoningGemma 4 E2B
- GPQA DiamondGemma 4 E2B by 8.943.334.4+8.9
- Humanity's Last Examtie4.84.9tie
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationGemma 4 E2B by 59.967.67.7+59.9
- AA-Omniscience · AccuracyLFM2-8B-A1B (Non-Reasoning) by 1.66.68.2+1.6
Following instructionsGemma 4 E2B
- IFBenchGemma 4 E2B by 11.73826.3+11.7
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-OmniscienceGemma 4 E2B by 52.9-23.6-76.5+52.9
- MMLU-ProGemma 4 E2B by 22.66037.4+22.6
- MMMLUGemma 4 E2B by 12.167.455.3+12.1
- τ²-Bench (Retail)Gemma 4 E2B by 1218.97+12
- BFCL v3Gemma 4 E2B by 11.356.445.1+11.3
- MATH500 (Pass@1)LFM2-8B-A1B (Non-Reasoning) by 10.86474.8+10.8
- τ²-Bench Telecom (AA run)Gemma 4 E2B by 10.320.810.5+10.3
- Tau² TelecomGemma 4 E2B by 8.822.413.6+8.8
- BFCLv4Gemma 4 E2B by 7.733.225.5+7.7
- AIME25 no toolsGemma 4 E2B by 6.326.320+6.3
- IFEvalGemma 4 E2B by 5.48377.6+5.4
- AA IntelligenceGemma 4 E2B by 2.97.84.9+2.9
Questions people ask
Which is better, Gemma 4 E2B or LFM2-8B-A1B (Non-Reasoning)?
Gemma 4 E2B wins three of the four areas where both have results: coding, reasoning and following instructions. LFM2-8B-A1B (Non-Reasoning) wins none. They are level on facts.
Which is better for coding?
Gemma 4 E2B. It wins 3 of the 3 coding tests both models report; LFM2-8B-A1B (Non-Reasoning) wins none.
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.