Gemini 2.5 Pro vs Gemini 3.1 Pro
Wins 0 of 8 areas
—
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Gemini 3.1 Pro is the stronger all-rounder.Gemini 2.5 Pro is cheaper.
Scores updated · 46 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.
- CodingWriting and fixing software05Gemini 3.1 Pro5 of 5 tests
- ReasoningHard problems that need careful thinking05Gemini 3.1 Pro5 of 5 tests
- Images and chartsUnderstanding pictures, charts and video05Gemini 3.1 Pro5 of 5 tests
- AgentsCarrying out multi-step tasks on its own04Gemini 3.1 Pro4 of 4 tests
- FactsGetting facts right instead of making them up13Gemini 3.1 Pro3 of 4 tests
- MathCompetition and research-level math02Gemini 3.1 Pro2 of 2 tests
- Following instructionsDoing exactly what it is asked02Gemini 3.1 Pro2 of 2 tests
- Long documentsFinding answers in very long texts01Gemini 3.1 Pro1 of 1 test
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.
Gemini 2.5 Pro 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 3.1 Pro pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+76points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+72.2points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+45.3points ahead
Where Gemini 2.5 Pro pulls ahead
No clear win on a test scored out of 100.
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.
CodingGemini 3.1 Pro
- Terminal-Bench 2.1Gemini 3.1 Pro by 45.328.573.8+45.3
- Terminal-Bench HardGemini 3.1 Pro by 27.326.553.8+27.3
- LMArena · WebDevGemini 3.1 Pro by 223 rating points12241447+223 rating
- SWE-bench VerifiedGemini 3.1 Pro by 17.463.280.6+17.4
- SciCodeGemini 3.1 Pro by 12.446.358.7+12.4
AgentsGemini 3.1 Pro
- BrowseCompGemini 3.1 Pro by 769.985.9+76
- GDPValGemini 3.1 Pro by 14.7014.7+14.7
- τ-Bench V3 · BankingGemini 3.1 Pro by 11.79.721.4+11.7
- Terminal-Bench 4.0Gemini 3.1 Pro by 404+4
ReasoningGemini 3.1 Pro
- ARC-AGI-2Gemini 3.1 Pro by 72.24.977.1+72.2
- Humanity's Last ExamGemini 3.1 Pro by 291847+29
- SimpleBenchGemini 3.1 Pro by 2851.679.6+28
- CritPtGemini 3.1 Pro by 15.12.617.7+15.1
- GPQA DiamondGemini 3.1 Pro by 10.583.694.1+10.5
FactsGemini 3.1 Pro
- AA-Omniscience · Non-hallucinationGemini 3.1 Pro by 409.149.1+40
- SimpleQA VerifiedGemini 3.1 Pro by 17.55673.5+17.5
- AA-Omniscience · AccuracyGemini 3.1 Pro by 15.83954.9+15.8
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Pro by 3.4710.4+3.4
Images and chartsGemini 3.1 Pro
- MMMU-ProGemini 3.1 Pro by 7.574.982.4+7.5
- MathVistaGemini 3.1 Pro by 6.383.990.2+6.3
- OCRBenchv2Gemini 3.1 Pro by 3.559.362.8+3.5
- LMArena · VisionGemini 3.1 Pro by 33 rating points12631296+33 rating
- Video-MMEGemini 3.1 Pro by 1.984.886.7+1.9
MathGemini 3.1 Pro
- FrontierMath Tiers 1-3 (v2)Gemini 3.1 Pro by 35.124.659.6+35.1
- FrontierMath Tier 4Gemini 3.1 Pro by 26.8026.8+26.8
Following instructionsGemini 3.1 Pro
- IFBenchGemini 3.1 Pro by 28.448.777.1+28.4
- Multi-ChallengeGemini 3.1 Pro by 17.853.671.4+17.8
Other results18 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-1Gemini 3.1 Pro by 613798+61
- AA-OmniscienceGemini 3.1 Pro by 48.2-16.431.9+48.2
- τ²-Bench Telecom (AA run)Gemini 3.1 Pro by 41.554.195.6+41.5
- HLE (with tools)Gemini 3.1 Pro by 2328.451.4+23
- Artificial Analysis Coding IndexGemini 3.1 Pro by 22.146.768.8+22.1
- LiveCodeBenchGemini 3.1 Pro by 17.574.291.7+17.5
- OpenAI-MRCR (1M)Gemini 3.1 Pro by 17.558.876.3+17.5
- MATH-VisionGemini 3.1 Pro by 16.573.389.8+16.5
- HMMT Nov. 2025Gemini 3.1 Pro by 14.88094.8+14.8
- AA IntelligenceGemini 3.1 Pro by 14.71529.7+14.7
- frontiermath_tier_4_v1Gemini 3.1 Pro by 12.54.216.7+12.5
- matharena_visual_math_overallGemini 3.1 Pro by 12.277.289.4+12.2
- AA Agentic IndexGemini 3.1 Pro by 6.83.510.3+6.8
- MMLU-ProGemini 3.1 Pro by 58691+5
- Global-MMLU-LiteGemini 3.1 Pro by 4.188.692.7+4.1
- vectara_factual_consistencyGemini 2.5 Pro by 3.49389.6+3.4
- vectara_answer_ratetie99.199.4tie
- vectara_avg_summary_lengthtie106.4107.7tie
Questions people ask
Which is better, Gemini 2.5 Pro or Gemini 3.1 Pro?
Gemini 3.1 Pro wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. Gemini 2.5 Pro wins none, but costs 20% less.
Which is better for coding?
Gemini 3.1 Pro. It wins 5 of the 5 coding tests both models report; Gemini 2.5 Pro wins none.
Which is cheaper?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; Gemini 3.1 Pro costs $2.00 and $12.00. That makes Gemini 2.5 Pro about 20% cheaper for the same work.
How do you compare the two?
We use the 46 benchmark tests both models have published scores on. The verdict counts the 28 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 18 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.