Gemini 2.5 Flash vs GPT-5.2
Wins 1 of 7 areas
Facts
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
GPT-5.2 is the stronger all-rounder.Gemini 2.5 Flash is cheaper and better at facts.
Scores updated · 29 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-5.25 of 5 tests
- CodingWriting and fixing software03GPT-5.23 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02GPT-5.22 of 2 tests
- AgentsCarrying out multi-step tasks on its own01GPT-5.21 of 1 test
- Long documentsFinding answers in very long texts01GPT-5.21 of 1 test
- Following instructionsDoing exactly what it is asked01GPT-5.21 of 1 test
- FactsGetting facts right instead of making them up21Gemini 2.5 Flash2 of 3 tests
Agents, 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.
Gemini 2.5 Flash costs 82% 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 GPT-5.2 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+50.4points ahead
- Real work tasks from 44 professionsGDPVal+38.4points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+33.4points ahead
Where Gemini 2.5 Flash pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+5.9points ahead
Every test, side by side
All 29 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.2
- Terminal-Bench HardGPT-5.2 by 33.413.647+33.4
- SciCodeGPT-5.2 by 2329.152.1+23
- SWE-bench VerifiedGPT-5.2 by 19.660.480+19.6
ReasoningGPT-5.2
- ARC-AGI-2GPT-5.2 by 50.42.552.9+50.4
- Humanity's Last ExamGPT-5.2 by 25.612.137.7+25.6
- GPQA DiamondGPT-5.2 by 11.37990.3+11.3
- CritPtGPT-5.2 by 10.51.111.6+10.5
- SimpleBenchGPT-5.2 by 4.641.245.8+4.6
FactsGemini 2.5 Flash
- AA-Omniscience · AccuracyGPT-5.2 by 18.325.944.3+18.3
- AA-Omniscience · Non-hallucinationGemini 2.5 Flash by 5.924.718.8+5.9
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Flash by 37.810.8+3
Images and chartsGPT-5.2
- MMMU-ProGPT-5.2 by 5.569.174.6+5.5
- LMArena · VisionGPT-5.2 by 11 rating points12351246+11 rating
Other results13 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-5.2 by 53.932.386.2+53.9
- τ²-Bench Telecom (AA run)GPT-5.2 by 53.231.684.8+53.2
- AA Agentic IndexGPT-5.2 by 41.418.860.2+41.4
- HMMT Feb. 2025GPT-5.2 by 35.864.2100+35.8
- AA-OmniscienceGPT-5.2 by 28.9-29.8-0.9+28.9
- AIME 2025GPT-5.2 by 2872100+28
- Artificial Analysis Coding IndexGPT-5.2 by 26.522.248.7+26.5
- AA IntelligenceGPT-5.2 by 17.313.130.4+17.3
- frontiermath_tier_4_v1GPT-5.2 by 14.64.218.8+14.6
- LiveCodeBenchGPT-5.2 by 12.876.289+12.8
- vectara_avg_summary_lengthGPT-5.2 by 84.8 rating points101.5186.3+84.8 rating
- vectara_factual_consistencyGemini 2.5 Flash by 392.289.2+3
- vectara_answer_rateGPT-5.2 by 199100+1
Questions people ask
Which is better, Gemini 2.5 Flash or GPT-5.2?
GPT-5.2 wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. Gemini 2.5 Flash wins facts, and costs 82% less.
Which is better for coding?
GPT-5.2. It wins 3 of the 3 coding tests both models report; Gemini 2.5 Flash wins none.
Which is cheaper?
Gemini 2.5 Flash costs $0.30 per million input tokens and $2.50 per million output tokens; GPT-5.2 costs $1.75 and $14.00. That makes Gemini 2.5 Flash about 82% cheaper for the same work.
How do you compare the two?
We use the 29 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.