Gemma 4 26B A4B vs Gemma 4 E4B
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.Gemma 4 E4B is cheaper.
Scores updated · 38 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 software40Gemma 4 26B A4B4 of 4 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.
Gemma 4 E4B costs 77% less for the same work.
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
- US invitational high-school math exam problemsAIME 2026+45.8points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+37.1points ahead
- Math problems shown in pictures and chartsMathVista+34.2points ahead
Where Gemma 4 E4B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+55.5points ahead
Every test, side by side
All 38 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 37.1391.9+37.1
- LiveCodeBench v6Gemma 4 26B A4B by 25.177.152+25.1
- SciCodeGemma 4 26B A4B by 15.64024.4+15.6
- Terminal-Bench HardGemma 4 26B A4B by 5.313.68.3+5.3
AgentsGemma 4 26B A4B
- τ-Bench V3 · BankingGemma 4 26B A4B by 6.6125.4+6.6
- GDPValGemma 4 26B A4B by 3.43.40+3.4
ReasoningGemma 4 26B A4B
- GPQA DiamondGemma 4 26B A4B by 21.679.257.6+21.6
- Humanity's Last ExamGemma 4 26B A4B by 15.519.33.8+15.5
- CritPttie00.6tie
FactsEven
- AA-Omniscience · Non-hallucinationGemma 4 E4B by 55.513.669.1+55.5
- AA-Omniscience · AccuracyGemma 4 26B A4B by 10.519.18.6+10.5
Images and chartsGemma 4 26B A4B
Long documentsGemma 4 26B A4B
- AA-LCRGemma 4 26B A4B by 33.765.732+33.7
- MRCR v2 8 needle 128k (average)Gemma 4 26B A4B by 18.744.125.4+18.7
Following instructionsGemma 4 26B A4B
- IFBenchGemma 4 26B A4B by 28.272.444.2+28.2
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 778 rating points1718940+778 rating
- BIG-Bench Extra HardGemma 4 26B A4B by 31.764.833.1+31.7
- AA-OmniscienceGemma 4 E4B by 31.1-50.8-19.7+31.1
- Artificial Analysis Coding IndexGemma 4 26B A4B by 29.939.39.4+29.9
- MedXPertQA MMGemma 4 26B A4B by 29.458.128.7+29.4
- t2-benchGemma 4 26B A4B by 2885.557.5+28
- τ²-BenchGemma 4 26B A4B by 2668.242.2+26
- MATH-VisionGemma 4 26B A4B by 22.982.459.5+22.9
- τ²-Bench Telecom (AA run)Gemma 4 26B A4B by 22.843.620.8+22.8
- SimpleVQAGemma 4 26B A4B by 21.852.230.4+21.8
- PinchBenchGemma 4 26B A4B by 19.674.755.1+19.6
- HallusionBenchGemma 4 26B A4B by 16.366.149.8+16.3
- MMLU-ProGemma 4 26B A4B by 13.282.669.4+13.2
- τ³-Bench BankingGemma 4 26B A4B by 9.9144.1+9.9
- MMMLUGemma 4 26B A4B by 9.786.376.6+9.7
- AA Agentic IndexGemma 4 26B A4B by 9.2111.8+9.2
- RealWorldQAGemma 4 26B A4B by 7.972.264.3+7.9
- AA IntelligenceGemma 4 26B A4B by 7.816.78.9+7.8
- IFEvalGemma 4 26B A4B by 3.591.487.9+3.5
- Claw-Eval Avgtie58.858tie
- OmniDocBench 1.5 (average edit distance, lower is better)lower is bettertie0.10.2tie
Questions people ask
Which is better, Gemma 4 26B A4B or Gemma 4 E4B?
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 E4B wins none, but costs 77% less. They are level on facts.
Which is better for coding?
Gemma 4 26B A4B. It wins 4 of the 4 coding tests both models report; Gemma 4 E4B wins none.
Which is cheaper?
Gemma 4 26B A4B costs $0.13 per million input tokens and $0.40 per million output tokens; Gemma 4 E4B costs $0.02 and $0.10. That makes Gemma 4 E4B about 77% cheaper for the same work.
How do you compare the two?
We use the 38 benchmark tests both models have published scores on. The verdict counts the 17 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.