Gemma 4 31B vs GPT-4o
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Wins 1 of 7 areas
Facts
Gemma 4 31B is the stronger all-rounder.GPT-4o is better at facts.
Scores updated · 34 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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 software40Gemma 4 31B4 of 4 tests
- Images and chartsUnderstanding pictures, charts and video40Gemma 4 31B4 of 4 tests
- ReasoningHard problems that need careful thinking30Gemma 4 31B3 of 3 tests
- AgentsCarrying out multi-step tasks on its own10Gemma 4 31B1 of 1 test
- Long documentsFinding answers in very long texts10Gemma 4 31B1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemma 4 31B1 of 1 test
- FactsGetting facts right instead of making them up13GPT-4o3 of 4 tests
Agents, 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.
Gemma 4 31B costs 97% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Gemma 4 31B pulls ahead
- Recent programming contest problemsLiveCodeBench v6+49.1points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+39.6points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+33.1points ahead
Where GPT-4o pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+47.1points ahead
- Short factual questions, answered correctlySimpleQA Verified+15.6points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+3.7points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemma 4 31B
- LiveCodeBench v6Gemma 4 31B by 49.18030.9+49.1
- Terminal-Bench HardGemma 4 31B by 28.136.48.3+28.1
- SWE-bench VerifiedGemma 4 31B by 18.85233.2+18.8
- SciCodeGemma 4 31B by 12.245.533.3+12.2
ReasoningGemma 4 31B
- GPQA DiamondGemma 4 31B by 33.185.752.6+33.1
- Humanity's Last ExamGemma 4 31B by 21.823.61.8+21.8
- CritPtGemma 4 31B by 1.41.40+1.4
FactsGPT-4o
- AA-Omniscience · Non-hallucinationGPT-4o by 47.11562.1+47.1
- SimpleQA VerifiedGPT-4o by 15.610.426+15.6
- AA-Omniscience · AccuracyGPT-4o by 3.72023.7+3.7
- Vectara HHEM hallucination ratelower is betterGemma 4 31B by 2.27.49.6+2.2
Images and chartsGemma 4 31B
- MathVistaGemma 4 31B by 17.979.361.4+17.9
- MMMU-ProGemma 4 31B by 17.173.456.3+17.1
- CharXiv (RQ)Gemma 4 31B by 9.167.958.8+9.1
- MMMUGemma 4 31B by 8.280.472.2+8.2
Following instructionsGemma 4 31B
- IFBenchGemma 4 31B by 39.675.636+39.6
Other results16 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.
- MATH-VisionGemma 4 31B by 55.285.630.4+55.2
- AA-OmniscienceGPT-4o by 37.4-47.9-10.5+37.4
- τ²-Bench Telecom (AA run)Gemma 4 31B by 3159.928.9+31
- SuperGPQAGemma 4 31B by 23.365.742.4+23.3
- Artificial Analysis Coding IndexGemma 4 31B by 19.243.424.2+19.2
- vectara_avg_summary_lengthGPT-4o by 10.875.886.6+10.8
- MMLU-ProGemma 4 31B by 10.585.274.7+10.5
- AA IntelligenceGemma 4 31B by 7.414.77.3+7.4
- MMMLUGemma 4 31B by 788.481.4+7
- C-EvalGemma 4 31B by 6.682.676+6.6
- vectara_answer_rateGemma 4 31B by 6.210093.8+6.2
- MMLU-ReduxGemma 4 31B by 5.793.788+5.7
- AI2DGPT-4o by 5.28994.2+5.2
- RealWorldQAGPT-4o by 3.172.375.4+3.1
- vectara_factual_consistencyGemma 4 31B by 2.292.690.4+2.2
- AA Agentic IndexGPT-4o by 1.76.78.4+1.7
Questions people ask
Which is better, Gemma 4 31B or GPT-4o?
Gemma 4 31B wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. GPT-4o wins facts.
Which is better for coding?
Gemma 4 31B. It wins 4 of the 4 coding tests both models report; GPT-4o wins none.
Which is cheaper?
Gemma 4 31B costs $0.17 per million input tokens and $0.40 per million output tokens; GPT-4o costs $5.00 and $15.00. That makes Gemma 4 31B about 97% cheaper for the same work.
How do you compare the two?
We use the 34 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 16 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.