Gemma 4 E2B vs LFM2.5-1.2B-Thinking
Wins 3 of 6 areas
Coding · Facts · Long documents
Wins 1 of 6 areas
Following instructions
Gemma 4 E2B wins more areas, narrowly.LFM2.5-1.2B-Thinking is better at following instructions.
Scores updated · 18 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 E2B2 of 2 tests
- FactsGetting facts right instead of making them up10Gemma 4 E2B1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10Gemma 4 E2B1 of 1 test
- Following instructionsDoing exactly what it is asked01LFM2.5-1.2B-Thinking1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
Agents, 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 Gemma 4 E2B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+62points ahead
- Code for real scientific research problemsSciCode+16.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+9.4points ahead
Where LFM2.5-1.2B-Thinking pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+3.8points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.4points ahead
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemma 4 E2B
- SciCodeGemma 4 E2B by 16.720.94.2+16.7
- Terminal-Bench HardGemma 4 E2B by 330+3
ReasoningEven
- GPQA DiamondGemma 4 E2B by 9.443.333.9+9.4
- Humanity's Last ExamLFM2.5-1.2B-Thinking by 1.44.86.2+1.4
- CritPttie00tie
FactsGemma 4 E2B
- AA-Omniscience · Non-hallucinationGemma 4 E2B by 6267.65.6+62
- AA-Omniscience · Accuracytie6.67.4tie
Following instructionsLFM2.5-1.2B-Thinking
- IFBenchLFM2.5-1.2B-Thinking by 3.83841.8+3.8
Other results8 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 56.3-23.6-80+56.3
- MMLU-ProGemma 4 E2B by 10.36049.6+10.3
- AIME25 no toolsLFM2.5-1.2B-Thinking by 5.426.331.7+5.4
- IFEvalLFM2.5-1.2B-Thinking by 5.48388.4+5.4
- AA Agentic IndexLFM2.5-1.2B-Thinking by 51.56.5+5
- AA IntelligenceGemma 4 E2B by 2.67.85.2+2.6
- τ²-Bench Telecom (AA run)Gemma 4 E2B by 1.220.819.6+1.2
- BFCL v3tie56.457tie
Questions people ask
Which is better, Gemma 4 E2B or LFM2.5-1.2B-Thinking?
Gemma 4 E2B wins three of the six areas where both have results: coding, facts and long documents. LFM2.5-1.2B-Thinking wins following instructions. They are level on agents and reasoning.
Which is better for coding?
Gemma 4 E2B. It wins 2 of the 2 coding tests both models report; LFM2.5-1.2B-Thinking wins none.
How do you compare the two?
We use the 18 benchmark tests both models have published scores on. The verdict counts the 10 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.