Gemini 3.1 Pro vs GPT-5.2 Codex
Wins 6 of 8 areas
Coding · Reasoning · Facts · Images and charts · Math · Following instructions
Wins 1 of 8 areas
Agents
Gemini 3.1 Pro is the stronger all-rounder.GPT-5.2 Codex is better at agents.
Scores updated · 28 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.
- ReasoningHard problems that need careful thinking40Gemini 3.1 Pro4 of 4 tests
- FactsGetting facts right instead of making them up20Gemini 3.1 Pro2 of 2 tests
- CodingWriting and fixing software43Gemini 3.1 Pro4 of 7 tests
- Following instructionsDoing exactly what it is asked10Gemini 3.1 Pro1 of 2 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video10Gemini 3.1 Pro1 of 1 test
- MathCompetition and research-level math10Gemini 3.1 Pro1 of 1 test
- AgentsCarrying out multi-step tasks on its own01GPT-5.2 Codex1 of 1 test
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Agents, images and charts, math and long documents 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.
Gemini 3.1 Pro costs 11% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Gemini 3.1 Pro pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+22.5points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+16.7points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+13.8points ahead
Where GPT-5.2 Codex pulls ahead
- Real work tasks from 44 professionsGDPVal+24.7points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+7.1points ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+5.3points ahead
Every test, side by side
All 28 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3.1 Pro
- Terminal-Bench HardGemini 3.1 Pro by 16.753.837.1+16.7
- LMArena · WebDevGemini 3.1 Pro by 107 rating points14461339+107 rating
- SWE-bench VerifiedGemini 3.1 Pro by 7.880.672.8+7.8
- LiveBench · CodingGPT-5.2 Codex by 7.176.583.6+7.1
- LiveBench · Agentic CodingGPT-5.2 Codex by 5.344.149.4+5.3
- SciCodeGemini 3.1 Pro by 4.158.754.6+4.1
- SWE-bench ProGPT-5.2 Codex by 2.254.256.4+2.2
ReasoningGemini 3.1 Pro
- Humanity's Last ExamGemini 3.1 Pro by 11.34735.7+11.3
- CritPtGemini 3.1 Pro by 917.78.7+9
- LiveBench · ReasoningGemini 3.1 Pro by 6.38477.7+6.3
- GPQA DiamondGemini 3.1 Pro by 4.294.189.9+4.2
FactsGemini 3.1 Pro
- AA-Omniscience · Non-hallucinationGemini 3.1 Pro by 22.549.126.6+22.5
- AA-Omniscience · AccuracyGemini 3.1 Pro by 13.854.941.1+13.8
Images and chartsGemini 3.1 Pro
- MMMU-ProGemini 3.1 Pro by 6.182.476.3+6.1
Following instructionsGemini 3.1 Pro
- LiveBench · Instruction FollowingGemini 3.1 Pro by 12.679.166.5+12.6
- IFBenchtie77.177.6tie
Other results9 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 Agentic IndexGPT-5.2 Codex by 46.210.356.5+46.2
- AA-OmniscienceGemini 3.1 Pro by 34.131.9-2.2+34.1
- Artificial Analysis Coding IndexGemini 3.1 Pro by 25.868.843+25.8
- livebench_languageGemini 3.1 Pro by 11.785.473.7+11.7
- LiveBenchGemini 3.1 Pro by 5.679.974.3+5.6
- Terminal-Bench 2.0Gemini 3.1 Pro by 4.568.564+4.5
- τ²-Bench Telecom (AA run)Gemini 3.1 Pro by 3.595.692.1+3.5
- AA IntelligenceGemini 3.1 Pro by 1.229.728.5+1.2
- livebench_data_analysistie78.578.2tie
Questions people ask
Which is better, Gemini 3.1 Pro or GPT-5.2 Codex?
Gemini 3.1 Pro wins six of the eight areas we test: coding, reasoning, facts, images and charts, math and following instructions. GPT-5.2 Codex wins agents. They are level on long documents.
Which is better for coding?
Gemini 3.1 Pro. It wins 4 of the 7 coding tests both models report; GPT-5.2 Codex wins 3.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; GPT-5.2 Codex costs $1.75 and $14.00. That makes Gemini 3.1 Pro about 11% cheaper for the same work.
How do you compare the two?
We use the 28 benchmark tests both models have published scores on. The verdict counts the 19 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.