Gemini 2.5 Pro vs GPT-4.1
Wins 6 of 8 areas
Coding · Reasoning · Facts · Images and charts · Math · Following instructions
Wins 1 of 8 areas
Agents
Gemini 2.5 Pro is the stronger all-rounder.GPT-4.1 is cheaper and better at agents.
Scores updated · 42 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 2.5 Pro4 of 4 tests
- Images and chartsUnderstanding pictures, charts and video40Gemini 2.5 Pro4 of 4 tests
- CodingWriting and fixing software30Gemini 2.5 Pro3 of 3 tests
- FactsGetting facts right instead of making them up31Gemini 2.5 Pro3 of 4 tests
- Following instructionsDoing exactly what it is asked20Gemini 2.5 Pro2 of 2 tests
- MathCompetition and research-level math10Gemini 2.5 Pro1 of 1 test
- AgentsCarrying out multi-step tasks on its own01GPT-4.11 of 1 test
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Agents, 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.
GPT-4.1 costs 11% 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 2.5 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+24.9points ahead
- Common-sense trick questionsSimpleBench+24.6points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+18.6points ahead
Where GPT-4.1 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 42 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 2.5 Pro
- Terminal-Bench HardGemini 2.5 Pro by 12.926.513.6+12.9
- SWE-bench VerifiedGemini 2.5 Pro by 8.663.254.6+8.6
- SciCodeGemini 2.5 Pro by 8.246.338.1+8.2
ReasoningGemini 2.5 Pro
- SimpleBenchGemini 2.5 Pro by 24.651.627+24.6
- GPQA DiamondGemini 2.5 Pro by 1783.666.6+17
- Humanity's Last ExamGemini 2.5 Pro by 13.8184.2+13.8
- CritPtGemini 2.5 Pro by 2.62.60+2.6
FactsGemini 2.5 Pro
- SimpleQA VerifiedGemini 2.5 Pro by 24.95631.1+24.9
- AA-Omniscience · AccuracyGemini 2.5 Pro by 11.33927.8+11.3
- AA-Omniscience · Non-hallucinationGemini 2.5 Pro by 2.49.16.7+2.4
- Vectara HHEM hallucination ratelower is betterGPT-4.1 by 1.475.6+1.4
Images and chartsGemini 2.5 Pro
- MMMU-ProGemini 2.5 Pro by 13.774.961.2+13.7
- MathVistaGemini 2.5 Pro by 11.783.972.2+11.7
- LMArena · VisionGemini 2.5 Pro by 53 rating points12631210+53 rating
- MMMUGemini 2.5 Pro by 4.879.674.8+4.8
Following instructionsGemini 2.5 Pro
- Multi-ChallengeGemini 2.5 Pro by 15.353.638.3+15.3
- IFBenchGemini 2.5 Pro by 5.748.743+5.7
Other results22 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.
- HMMT 2025Gemini 2.5 Pro by 36.865.728.9+36.8
- AIME 2025Gemini 2.5 Pro by 36.68346.4+36.6
- ARC-AGI-1Gemini 2.5 Pro by 31.5375.5+31.5
- HarmBenchGPT-4.1 by 26.365.491.7+26.3
- Aider-PolyglotGemini 2.5 Pro by 24.976.551.6+24.9
- Artificial Analysis Coding IndexGemini 2.5 Pro by 24.946.721.8+24.9
- AA Agentic IndexGPT-4.1 by 23.83.527.3+23.8
- AA-OmniscienceGemini 2.5 Pro by 23.3-16.4-39.6+23.3
- AIR-Bench 2024Gemini 2.5 Pro by 8.873.664.8+8.8
- τ²-Bench Telecom (AA run)Gemini 2.5 Pro by 754.147.1+7
- Terminal-BenchGPT-4.1 by 525.330.3+5
- frontiermath_tier_4_v1Gemini 2.5 Pro by 4.24.20+4.2
- bbqGemini 2.5 Pro by 3.896.492.6+3.8
- simple_safety_testsGPT-4.1 by 397100+3
- AA IntelligenceGemini 2.5 Pro by 2.31512.7+2.3
- vectara_avg_summary_lengthGemini 2.5 Pro by 14.7 rating points106.491.7+14.7 rating
- vectara_factual_consistencyGPT-4.1 by 1.49394.4+1.4
- TAU-bench (retail)GPT-4.1 by 16768+1
- vectara_answer_ratetie99.199.9tie
- XSTesttie98.797.9tie
- TAU-bench (airline)tie5049.4tie
- anthropic_red_teamtie99.599.3tie
Questions people ask
Which is better, Gemini 2.5 Pro or GPT-4.1?
Gemini 2.5 Pro wins six of the eight areas we test: coding, reasoning, facts, images and charts, math and following instructions. GPT-4.1 wins agents, and costs 11% less. They are level on long documents.
Which is better for coding?
Gemini 2.5 Pro. It wins 3 of the 3 coding tests both models report; GPT-4.1 wins none.
Which is cheaper?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; GPT-4.1 costs $2.00 and $8.00. That makes GPT-4.1 about 11% cheaper for the same work.
How do you compare the two?
We use the 42 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 22 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.