Gemma 4 31B vs GPT-5.1
Wins 1 of 7 areas
Following instructions
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents
GPT-5.1 is the stronger all-rounder.Gemma 4 31B is cheaper and better at following instructions.
Scores updated · 35 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 software15GPT-5.15 of 6 tests
- ReasoningHard problems that need careful thinking03GPT-5.13 of 3 tests
- FactsGetting facts right instead of making them up13GPT-5.13 of 4 tests
- AgentsCarrying out multi-step tasks on its own02GPT-5.12 of 2 tests
- Images and chartsUnderstanding pictures, charts and video12GPT-5.12 of 3 tests
- Long documentsFinding answers in very long texts01GPT-5.11 of 1 test
- Following instructionsDoing exactly what it is asked10Gemma 4 31B1 of 1 test
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 95% 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 GPT-5.1 pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+37.6points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+33.1points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+24.3points ahead
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.1
- SWE-bench VerifiedGPT-5.1 by 24.35276.3+24.3
- Terminal-Bench HardGPT-5.1 by 9.136.445.5+9.1
- Terminal-Bench 2.1GPT-5.1 by 943.452.4+9
- LiveCodeBench v6GPT-5.1 by 78087+7
- LMArena · WebDevGPT-5.1 by 30 rating points13651395+30 rating
- SciCodeGemma 4 31B by 2.245.543.3+2.2
AgentsGPT-5.1
- GDPValGPT-5.1 by 10.46.116.5+10.4
- τ-Bench V3 · BankingGPT-5.1 by 1.114.815.9+1.1
ReasoningGPT-5.1
- Humanity's Last ExamGPT-5.1 by 4.923.628.5+4.9
- CritPtGPT-5.1 by 3.51.44.9+3.5
- GPQA DiamondGPT-5.1 by 1.685.787.3+1.6
FactsGPT-5.1
- SimpleQA VerifiedGPT-5.1 by 37.610.448+37.6
- AA-Omniscience · Non-hallucinationGPT-5.1 by 33.11548.1+33.1
- AA-Omniscience · AccuracyGPT-5.1 by 17.72037.7+17.7
- Vectara HHEM hallucination ratelower is betterGemma 4 31B by 4.77.412.1+4.7
Images and chartsGPT-5.1
- MMMUGPT-5.1 by 580.485.4+5
- LMArena · VisionGemma 4 31B by 27 rating points12771250+27 rating
- MMMU-ProGPT-5.1 by 2.173.475.5+2.1
Following instructionsGemma 4 31B
- IFBenchGemma 4 31B by 2.775.672.9+2.7
Other results15 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.
- AA-OmniscienceGPT-5.1 by 53.3-47.95.4+53.3
- τ²-Bench Telecom (AA run)GPT-5.1 by 2259.981.9+22
- vectara_avg_summary_lengthGPT-5.1 by 178.6 rating points75.8254.4+178.6 rating
- HLE (with tools)GPT-5.1 by 16.226.542.7+16.2
- AA Agentic IndexGPT-5.1 by 14.96.721.6+14.9
- AA IntelligenceGPT-5.1 by 1014.724.7+10
- HMMT Feb. 2025GPT-5.1 by 7.688.796.3+7.6
- Artificial Analysis Coding IndexGPT-5.1 by 643.449.4+6
- τ²-BenchGPT-5.1 by 5.876.982.7+5.8
- Terminal-Bench 2.0GPT-5.1 by 4.742.947.6+4.7
- vectara_factual_consistencyGemma 4 31B by 4.792.687.9+4.7
- HMMT Nov. 2025GPT-5.1 by 4.287.591.7+4.2
- MMMLUGPT-5.1 by 2.688.491+2.6
- MMLU-ProGPT-5.1 by 1.885.287+1.8
- vectara_answer_ratetie100100tie
Questions people ask
Which is better, Gemma 4 31B or GPT-5.1?
GPT-5.1 wins six of the seven areas where both have results: coding, agents, reasoning, facts, images and charts and long documents. Gemma 4 31B wins following instructions, and costs 95% less.
Which is better for coding?
GPT-5.1. It wins 5 of the 6 coding tests both models report; Gemma 4 31B wins 1.
Which is cheaper?
Gemma 4 31B costs $0.17 per million input tokens and $0.40 per million output tokens; GPT-5.1 costs $1.25 and $10.00. That makes Gemma 4 31B about 95% cheaper for the same work.
How do you compare the two?
We use the 35 benchmark tests both models have published scores on. The verdict counts the 20 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.