Gemma 4 31B 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 31B is the stronger all-rounder.Gemma 4 E4B is cheaper.
Scores updated · 36 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 31B4 of 4 tests
- AgentsCarrying out multi-step tasks on its own20Gemma 4 31B2 of 3 tests · 1 tie
- ReasoningHard problems that need careful thinking20Gemma 4 31B2 of 3 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video20Gemma 4 31B2 of 2 tests
- Long documentsFinding answers in very long texts20Gemma 4 31B2 of 2 tests
- MathCompetition and research-level math10Gemma 4 31B1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemma 4 31B1 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 79% 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 31B pulls ahead
- US invitational high-school math exam problemsAIME 2026+46.7points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+41.5points ahead
- Finds one of eight look-alike replies in a long chatMRCR v2 8 needle 128k (average)+41points ahead
Where Gemma 4 E4B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+54.1points ahead
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemma 4 31B
- Terminal-Bench 2.1Gemma 4 31B by 41.543.41.9+41.5
- Terminal-Bench HardGemma 4 31B by 28.136.48.3+28.1
- LiveCodeBench v6Gemma 4 31B by 288052+28
- SciCodeGemma 4 31B by 21.145.524.4+21.1
AgentsGemma 4 31B
- τ-Bench V3 · BankingGemma 4 31B by 9.414.85.4+9.4
- GDPValGemma 4 31B by 6.16.10+6.1
- Terminal-Bench 4.0tie00tie
ReasoningGemma 4 31B
- GPQA DiamondGemma 4 31B by 28.185.757.6+28.1
- Humanity's Last ExamGemma 4 31B by 19.823.63.8+19.8
- CritPttie1.40.6tie
FactsEven
- AA-Omniscience · Non-hallucinationGemma 4 E4B by 54.11569.1+54.1
- AA-Omniscience · AccuracyGemma 4 31B by 11.4208.6+11.4
Images and chartsGemma 4 31B
Long documentsGemma 4 31B
- MRCR v2 8 needle 128k (average)Gemma 4 31B by 4166.425.4+41
- AA-LCRGemma 4 31B by 37.769.732+37.7
Following instructionsGemma 4 31B
- IFBenchGemma 4 31B by 31.475.644.2+31.4
Other results18 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 31B by 1210 rating points2150940+1210 rating
- BIG-Bench Extra HardGemma 4 31B by 41.374.433.1+41.3
- τ²-Bench Telecom (AA run)Gemma 4 31B by 39.159.920.8+39.1
- τ²-BenchGemma 4 31B by 34.776.942.2+34.7
- Artificial Analysis Coding IndexGemma 4 31B by 3443.49.4+34
- MedXPertQA MMGemma 4 31B by 32.661.328.7+32.6
- t2-benchGemma 4 31B by 28.986.457.5+28.9
- AA-OmniscienceGemma 4 E4B by 28.2-47.9-19.7+28.2
- MATH-VisionGemma 4 31B by 26.185.659.5+26.1
- SimpleVQAGemma 4 31B by 22.552.930.4+22.5
- HallusionBenchGemma 4 31B by 17.667.449.8+17.6
- MMLU-ProGemma 4 31B by 15.885.269.4+15.8
- MMMLUGemma 4 31B by 11.888.476.6+11.8
- Claw-Eval AvgGemma 4 E4B by 9.548.558+9.5
- RealWorldQAGemma 4 31B by 872.364.3+8
- AA IntelligenceGemma 4 31B by 5.814.78.9+5.8
- AA Agentic IndexGemma 4 31B by 4.96.71.8+4.9
- OmniDocBench 1.5 (average edit distance, lower is better)lower is bettertie0.10.2tie
Questions people ask
Which is better, Gemma 4 31B or Gemma 4 E4B?
Gemma 4 31B 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 79% less. They are level on facts.
Which is better for coding?
Gemma 4 31B. It wins 4 of the 4 coding tests both models report; Gemma 4 E4B wins none.
Which is cheaper?
Gemma 4 31B costs $0.17 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 79% cheaper for the same work.
How do you compare the two?
We use the 36 benchmark tests both models have published scores on. The verdict counts the 18 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 18 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.