Gemini 2.5 Pro vs GPT-5.1
Wins 1 of 7 areas
Facts
Wins 5 of 7 areas
Coding · Agents · Reasoning · Long documents · Following instructions
GPT-5.1 is the stronger all-rounder.Gemini 2.5 Pro is better at facts.
Scores updated · 46 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.
- ReasoningHard problems that need careful thinking05GPT-5.15 of 5 tests
- CodingWriting and fixing software14GPT-5.14 of 5 tests
- AgentsCarrying out multi-step tasks on its own03GPT-5.13 of 3 tests
- Following instructionsDoing exactly what it is asked02GPT-5.12 of 2 tests
- Long documentsFinding answers in very long texts01GPT-5.11 of 1 test
- FactsGetting facts right instead of making them up31Gemini 2.5 Pro3 of 4 tests
- Images and chartsUnderstanding pictures, charts and video11Even1 each · 1 tie
Long documents rests on a single test.
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.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where GPT-5.1 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+40.9points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+39points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+24.2points ahead
Where Gemini 2.5 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+8points ahead
- Code for real scientific research problemsSciCode+3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+1.4points ahead
Every test, side by side
All 46 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.1
- Terminal-Bench 2.1GPT-5.1 by 23.928.552.4+23.9
- Terminal-Bench HardGPT-5.1 by 1926.545.5+19
- LMArena · WebDevGPT-5.1 by 171 rating points12241395+171 rating
- SWE-bench VerifiedGPT-5.1 by 13.163.276.3+13.1
- SciCodeGemini 2.5 Pro by 346.343.3+3
AgentsGPT-5.1
- BrowseCompGPT-5.1 by 40.99.950.8+40.9
- GDPValGPT-5.1 by 16.5016.5+16.5
- τ-Bench V3 · BankingGPT-5.1 by 6.29.715.9+6.2
ReasoningGPT-5.1
- ARC-AGI-2GPT-5.1 by 12.74.917.6+12.7
- Humanity's Last ExamGPT-5.1 by 10.51828.5+10.5
- GPQA DiamondGPT-5.1 by 3.783.687.3+3.7
- CritPtGPT-5.1 by 2.32.64.9+2.3
- SimpleBenchGPT-5.1 by 1.651.653.2+1.6
FactsGemini 2.5 Pro
- AA-Omniscience · Non-hallucinationGPT-5.1 by 399.148.1+39
- SimpleQA VerifiedGemini 2.5 Pro by 85648+8
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Pro by 5.1712.1+5.1
- AA-Omniscience · AccuracyGemini 2.5 Pro by 1.43937.7+1.4
Images and chartsEven
- MMMUGPT-5.1 by 5.879.685.4+5.8
- LMArena · VisionGemini 2.5 Pro by 13 rating points12631250+13 rating
- MMMU-Protie74.975.5tie
Following instructionsGPT-5.1
- IFBenchGPT-5.1 by 24.248.772.9+24.2
- Multi-ChallengeGPT-5.1 by 9.853.663.4+9.8
Other results23 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.
- ARC-AGI-1GPT-5.1 by 35.83772.8+35.8
- HarmBenchGPT-5.1 by 32.265.497.6+32.2
- τ²-BenchGPT-5.1 by 28.75482.7+28.7
- τ²-Bench Telecom (AA run)GPT-5.1 by 27.854.181.9+27.8
- AA-OmniscienceGPT-5.1 by 21.7-16.45.4+21.7
- AA Agentic IndexGPT-5.1 by 18.13.521.6+18.1
- HMMT Feb. 2025GPT-5.1 by 15.580.896.3+15.5
- vectara_avg_summary_lengthGPT-5.1 by 148 rating points106.4254.4+148 rating
- HLE (with tools)GPT-5.1 by 14.328.442.7+14.3
- AIR-Bench 2024GPT-5.1 by 12.673.686.2+12.6
- HMMT Nov. 2025GPT-5.1 by 11.78091.7+11.7
- AIME 2025GPT-5.1 by 118394+11
- AA IntelligenceGPT-5.1 by 9.71524.7+9.7
- frontiermath_tier_4_v1GPT-5.1 by 8.34.212.5+8.3
- bbqGemini 2.5 Pro by 7.796.488.7+7.7
- vectara_factual_consistencyGemini 2.5 Pro by 5.19387.9+5.1
- simple_safety_testsGPT-5.1 by 2.89799.8+2.8
- Artificial Analysis Coding IndexGPT-5.1 by 2.746.749.4+2.7
- MMLU-ProGPT-5.1 by 18687+1
- vectara_answer_ratetie99.1100tie
- XSTesttie98.798.2tie
- matharena_visual_math_overalltie77.276.9tie
- anthropic_red_teamtie99.599.5tie
Questions people ask
Which is better, Gemini 2.5 Pro or GPT-5.1?
GPT-5.1 wins five of the seven areas where both have results: coding, agents, reasoning, long documents and following instructions. Gemini 2.5 Pro wins facts. They are level on images and charts.
Which is better for coding?
GPT-5.1. It wins 4 of the 5 coding tests both models report; Gemini 2.5 Pro wins 1.
Which is cheaper?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; GPT-5.1 costs $1.25 and $10.00. For a million tokens read plus a million written, they cost about the same.
How do you compare the two?
We use the 46 benchmark tests both models have published scores on. The verdict counts the 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 23 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.