Gemini 3 Pro vs GPT-5.1 Codex
Wins 4 of 7 areas
Coding · Reasoning · Images and charts · Long documents
Wins 0 of 7 areas
—
Gemini 3 Pro wins more areas, narrowly.GPT-5.1 Codex is cheaper.
Scores updated · 19 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 software40Gemini 3 Pro4 of 4 tests
- ReasoningHard problems that need careful thinking30Gemini 3 Pro3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video10Gemini 3 Pro1 of 1 test
- Long documentsFinding answers in very long texts10Gemini 3 Pro1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
- Following instructionsDoing exactly what it is asked00Even0 each · 1 tie
Agents, images and charts, 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.
GPT-5.1 Codex costs 20% 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 Gemini 3 Pro pulls ahead
- Code for real scientific research problemsSciCode+15.9points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+15.9points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+14points ahead
Where GPT-5.1 Codex pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+14.3points ahead
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3 Pro
- SciCodeGemini 3 Pro by 15.956.140.2+15.9
- LMArena · WebDevGemini 3 Pro by 104 rating points14401336+104 rating
- Terminal-Bench HardGemini 3 Pro by 6.941.734.8+6.9
- SWE-bench VerifiedGemini 3 Pro by 2.576.273.7+2.5
ReasoningGemini 3 Pro
- Humanity's Last ExamGemini 3 Pro by 1439.725.7+14
- GPQA DiamondGemini 3 Pro by 4.890.886+4.8
- CritPtGemini 3 Pro by 3.49.15.7+3.4
FactsEven
- AA-Omniscience · AccuracyGemini 3 Pro by 15.955.839.9+15.9
- AA-Omniscience · Non-hallucinationGPT-5.1 Codex by 14.38.522.8+14.3
Other results6 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-OmniscienceGemini 3 Pro by 21.815.3-6.5+21.8
- Artificial Analysis Coding IndexGemini 3 Pro by 9.946.536.6+9.9
- AA IntelligenceGemini 3 Pro by 4.32823.7+4.3
- τ²-Bench Telecom (AA run)Gemini 3 Pro by 4.187.183+4.1
- Terminal-Bench 2.0Gemini 3 Pro by 1.454.252.8+1.4
- AA Agentic IndexGemini 3 Pro by 1.35250.7+1.3
Questions people ask
Which is better, Gemini 3 Pro or GPT-5.1 Codex?
Gemini 3 Pro wins four of the seven areas where both have results: coding, reasoning, images and charts and long documents. GPT-5.1 Codex wins none, but costs 20% less. They are level on agents, facts and following instructions.
Which is better for coding?
Gemini 3 Pro. It wins 4 of the 4 coding tests both models report; GPT-5.1 Codex wins none.
Which is cheaper?
Gemini 3 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; GPT-5.1 Codex costs $1.25 and $10.00. That makes GPT-5.1 Codex about 20% cheaper for the same work.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 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.