Gemma 4 26B A4B vs Gemma 4 E2B
Wins 7 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
Gemma 4 26B A4B is the stronger all-rounder.
Scores updated · 37 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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
- Images and chartsUnderstanding pictures, charts and video20Gemma 4 26B A4B2 of 2 tests
- Long documentsFinding answers in very long texts20Gemma 4 26B A4B2 of 2 tests
- MathCompetition and research-level math10Gemma 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
Math 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
Where Gemma 4 E2B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+54points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemma 4 26B A4B
- LiveCodeBench v6Gemma 4 26B A4B by 33.177.144+33.1
- SciCodeGemma 4 26B A4B by 19.14020.9+19.1
- Terminal-Bench HardGemma 4 26B A4B by 10.613.63+10.6
AgentsGemma 4 26B A4B
- τ-Bench V3 · BankingGemma 4 26B A4B by 7.5124.5+7.5
- GDPValGemma 4 26B A4B by 3.43.40+3.4
ReasoningGemma 4 26B A4B
- GPQA DiamondGemma 4 26B A4B by 35.979.243.3+35.9
- Humanity's Last ExamGemma 4 26B A4B by 14.519.34.8+14.5
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationGemma 4 E2B by 5413.667.6+54
- AA-Omniscience · AccuracyGemma 4 26B A4B by 12.519.16.6+12.5
Images and chartsGemma 4 26B A4B
Long documentsGemma 4 26B A4B
- AA-LCRGemma 4 26B A4B by 49.465.716.3+49.4
- MRCR v2 8 needle 128k (average)Gemma 4 26B A4B by 2544.119.1+25
Following instructionsGemma 4 26B A4B
- IFBenchGemma 4 26B A4B by 34.472.438+34.4
Other results21 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.
- Codeforces ELOGemma 4 26B A4B by 1085 rating points1718633+1085 rating
- t2-benchGemma 4 26B A4B by 56.185.529.4+56.1
- τ²-BenchGemma 4 26B A4B by 43.768.224.5+43.7
- BIG-Bench Extra HardGemma 4 26B A4B by 42.964.821.9+42.9
- MedXPertQA MMGemma 4 26B A4B by 34.658.123.5+34.6
- Artificial Analysis Coding IndexGemma 4 26B A4B by 32.139.37.2+32.1
- PinchBenchGemma 4 26B A4B by 30.574.744.2+30.5
- MATH-VisionGemma 4 26B A4B by 3082.452.4+30
- AA-OmniscienceGemma 4 E2B by 27.2-50.8-23.6+27.2
- SimpleVQAGemma 4 26B A4B by 24.952.227.3+24.9
- τ²-Bench Telecom (AA run)Gemma 4 26B A4B by 22.843.620.8+22.8
- MMLU-ProGemma 4 26B A4B by 22.682.660+22.6
- MMMLUGemma 4 26B A4B by 18.986.367.4+18.9
- RealWorldQAGemma 4 26B A4B by 12.272.260+12.2
- τ³-Bench BankingGemma 4 26B A4B by 10.6143.4+10.6
- AA Agentic IndexGemma 4 26B A4B by 9.5111.5+9.5
- AA IntelligenceGemma 4 26B A4B by 8.916.77.8+8.9
- IFEvalGemma 4 26B A4B by 8.491.483+8.4
- HallusionBenchGemma 4 26B A4B by 6.366.159.8+6.3
- Claw-Eval AvgGemma 4 26B A4B by 5.758.853.1+5.7
- OmniDocBench 1.5 (average edit distance, lower is better)lower is bettertie0.10.3tie
Questions people ask
Which is better, Gemma 4 26B A4B or Gemma 4 E2B?
Gemma 4 26B A4B wins seven of the eight areas we test: coding, agents, reasoning, images and charts, math, long documents and following instructions. Gemma 4 E2B 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; Gemma 4 E2B wins none.
How do you compare the two?
We use the 37 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 21 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.