Gemma 4 E2B vs LFM2.5-8B-A1B
Wins 1 of 7 areas
Long documents
Wins 3 of 7 areas
Reasoning · Math · Following instructions
LFM2.5-8B-A1B wins more areas, narrowly.Gemma 4 E2B is better at long documents.
Scores updated · 23 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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 thinking02LFM2.5-8B-A1B2 of 3 tests · 1 tie
- MathCompetition and research-level math01LFM2.5-8B-A1B1 of 1 test
- Following instructionsDoing exactly what it is asked01LFM2.5-8B-A1B1 of 1 test
- Long documentsFinding answers in very long texts10Gemma 4 E2B1 of 1 test
- CodingWriting and fixing software11Even1 each
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
Agents, math, 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 LFM2.5-8B-A1B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+17.6points ahead
- US invitational high-school math exam problemsAIME 2026+12.5points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+8points ahead
Where Gemma 4 E2B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+14.5points ahead
- Code for real scientific research problemsSciCode+13.1points ahead
Every test, side by side
All 23 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- SciCodeGemma 4 E2B by 13.120.97.8+13.1
- Terminal-Bench HardLFM2.5-8B-A1B by 1.534.5+1.5
ReasoningLFM2.5-8B-A1B
- GPQA DiamondLFM2.5-8B-A1B by 843.351.3+8
- Humanity's Last ExamLFM2.5-8B-A1B by 2.14.86.9+2.1
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationGemma 4 E2B by 14.567.653.1+14.5
- AA-Omniscience · AccuracyLFM2.5-8B-A1B by 2.76.69.3+2.7
Following instructionsLFM2.5-8B-A1B
- IFBenchLFM2.5-8B-A1B by 17.63855.6+17.6
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.
- Tau² TelecomLFM2.5-8B-A1B by 65.722.488.1+65.7
- MATH500 (Pass@1)Gemma 4 E2B by 55.7648.3+55.7
- τ²-Bench (Retail)LFM2.5-8B-A1B by 20.818.939.8+20.8
- BFCLv4LFM2.5-8B-A1B by 16.533.249.7+16.5
- AIME25 no toolsLFM2.5-8B-A1B by 16.226.342.5+16.2
- AA-OmniscienceGemma 4 E2B by 9.6-23.6-33.2+9.6
- IFEvalLFM2.5-8B-A1B by 8.88391.8+8.8
- BFCL v3LFM2.5-8B-A1B by 8.456.464.8+8.4
- τ²-Bench Telecom (AA run)Gemma 4 E2B by 4.720.816.1+4.7
- AA Agentic IndexLFM2.5-8B-A1B by 3.91.55.4+3.9
- Artificial Analysis Coding IndexGemma 4 E2B by 1.67.25.6+1.6
- AA Intelligencetie7.87.2tie
Questions people ask
Which is better, Gemma 4 E2B or LFM2.5-8B-A1B?
LFM2.5-8B-A1B wins three of the seven areas where both have results: reasoning, math and following instructions. Gemma 4 E2B wins long documents. They are level on coding, agents and facts.
Which is better for coding?
Neither. They win 1 coding test each of the 2 both models report.
How do you compare the two?
We use the 23 benchmark tests both models have published scores on. The verdict counts the 11 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.