Gemma 4 E4B vs LFM2.5-8B-A1B
Wins 3 of 7 areas
Coding · Facts · Long documents
Wins 2 of 7 areas
Math · Following instructions
Gemma 4 E4B wins more areas, narrowly.LFM2.5-8B-A1B is better at math.
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.
- CodingWriting and fixing software20Gemma 4 E4B2 of 2 tests
- FactsGetting facts right instead of making them up10Gemma 4 E4B1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10Gemma 4 E4B1 of 1 test
- MathCompetition and research-level math01LFM2.5-8B-A1B1 of 1 test
- Following instructionsDoing exactly what it is asked01LFM2.5-8B-A1B1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
Agents, math, long documents and following instructions rest on a single test each.
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 three tests each model wins by the widest margin. Scores are out of 100.
Where Gemma 4 E4B pulls ahead
- Code for real scientific research problemsSciCode+16.6points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+16points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+6.3points ahead
Where LFM2.5-8B-A1B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+11.4points ahead
- US invitational high-school math exam problemsAIME 2026+7.5points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+3.1points 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.
CodingGemma 4 E4B
- SciCodeGemma 4 E4B by 16.624.47.8+16.6
- Terminal-Bench HardGemma 4 E4B by 3.88.34.5+3.8
ReasoningEven
- GPQA DiamondGemma 4 E4B by 6.357.651.3+6.3
- Humanity's Last ExamLFM2.5-8B-A1B by 3.13.86.9+3.1
- CritPttie0.60tie
FactsGemma 4 E4B
- AA-Omniscience · Non-hallucinationGemma 4 E4B by 1669.153.1+16
- AA-Omniscience · Accuracytie8.69.3tie
Following instructionsLFM2.5-8B-A1B
- IFBenchLFM2.5-8B-A1B by 11.444.255.6+11.4
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 61.326.888.1+61.3
- MATH500 (Pass@1)Gemma 4 E4B by 56.7658.3+56.7
- AA-OmniscienceGemma 4 E4B by 13.5-19.7-33.2+13.5
- BFCLv4LFM2.5-8B-A1B by 9.74049.7+9.7
- AIME25 no toolsLFM2.5-8B-A1B by 8.234.342.5+8.2
- BFCL v3LFM2.5-8B-A1B by 7.557.364.8+7.5
- τ²-Bench Telecom (AA run)Gemma 4 E4B by 4.720.816.1+4.7
- IFEvalLFM2.5-8B-A1B by 3.987.991.8+3.9
- Artificial Analysis Coding IndexGemma 4 E4B by 3.89.45.6+3.8
- AA Agentic IndexLFM2.5-8B-A1B by 3.61.85.4+3.6
- τ²-Bench (Retail)Gemma 4 E4B by 2.342.139.8+2.3
- AA IntelligenceGemma 4 E4B by 1.78.97.2+1.7
Questions people ask
Which is better, Gemma 4 E4B or LFM2.5-8B-A1B?
Gemma 4 E4B wins three of the seven areas where both have results: coding, facts and long documents. LFM2.5-8B-A1B wins math and following instructions. They are level on agents and reasoning.
Which is better for coding?
Gemma 4 E4B. It wins 2 of the 2 coding tests both models report; LFM2.5-8B-A1B wins none.
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.