Gemma 4 26B A4B vs LFM2.5-2.6B
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
Wins 0 of 6 areas
—
Gemma 4 26B A4B is the stronger all-rounder.
Scores updated · 22 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 software30Gemma 4 26B A4B3 of 3 tests
- ReasoningHard problems that need careful thinking20Gemma 4 26B A4B2 of 3 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own20Gemma 4 26B A4B2 of 2 tests
- Long documentsFinding answers in very long texts10Gemma 4 26B A4B1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemma 4 26B A4B1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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 tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Gemma 4 26B A4B pulls ahead
- Reasons across sets of long documentsAA-LCR+60points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+34.5points ahead
- Code for real scientific research problemsSciCode+25.6points ahead
Where LFM2.5-2.6B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+70.4points ahead
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemma 4 26B A4B
- Terminal-Bench 2.1Gemma 4 26B A4B by 34.5394.5+34.5
- SciCodeGemma 4 26B A4B by 25.64014.4+25.6
- LiveCodeBench v6Gemma 4 26B A4B by 17.777.159.4+17.7
AgentsGemma 4 26B A4B
- τ-Bench V3 · BankingGemma 4 26B A4B by 4.8127.2+4.8
- GDPValGemma 4 26B A4B by 3.43.40+3.4
ReasoningGemma 4 26B A4B
- GPQA DiamondGemma 4 26B A4B by 23.479.255.8+23.4
- Humanity's Last ExamGemma 4 26B A4B by 13.119.36.2+13.1
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationLFM2.5-2.6B by 70.413.684+70.4
- AA-Omniscience · AccuracyGemma 4 26B A4B by 14.719.14.3+14.7
Following instructionsGemma 4 26B A4B
- IFBenchGemma 4 26B A4B by 13.272.459.2+13.2
Other results10 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.
- MBPPGemma 4 26B A4B by 63.768.44.7+63.7
- HumanEvalGemma 4 26B A4B by 45.5504.5+45.5
- AA-OmniscienceLFM2.5-2.6B by 39.9-50.8-10.9+39.9
- Claw Eval (pass@3)LFM2.5-2.6B by 34.92862.9+34.9
- Artificial Analysis Coding IndexGemma 4 26B A4B by 31.639.37.7+31.6
- AA Agentic IndexGemma 4 26B A4B by 8.6112.4+8.6
- AA IntelligenceGemma 4 26B A4B by 8.316.78.4+8.3
- τ³-Bench BankingGemma 4 26B A4B by 8.3145.7+8.3
- PinchBenchGemma 4 26B A4B by 6.574.768.2+6.5
- Claw-Eval AvgLFM2.5-2.6B by 4.158.862.9+4.1
Questions people ask
Which is better, Gemma 4 26B A4B or LFM2.5-2.6B?
Gemma 4 26B A4B wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. LFM2.5-2.6B wins none. They are level on facts.
Which is better for coding?
Gemma 4 26B A4B. It wins 3 of the 3 coding tests both models report; LFM2.5-2.6B wins none.
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.