Gemini 3.6 Flash vs GPT-5.5
Wins 3 of 8 areas
Facts · Images and charts · Following instructions
Wins 5 of 8 areas
Coding · Agents · Reasoning · Math · Long documents
GPT-5.5 is the stronger all-rounder.Gemini 3.6 Flash is cheaper and better at facts.
Scores updated · 40 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.
- MathCompetition and research-level math05GPT-5.55 of 5 tests
- ReasoningHard problems that need careful thinking04GPT-5.54 of 5 tests · 1 tie
- CodingWriting and fixing software14GPT-5.54 of 6 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own13GPT-5.53 of 4 tests
- Long documentsFinding answers in very long texts01GPT-5.51 of 1 test
- FactsGetting facts right instead of making them up21Gemini 3.6 Flash2 of 3 tests
- Images and chartsUnderstanding pictures, charts and video10Gemini 3.6 Flash1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked10Gemini 3.6 Flash1 of 1 test
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 3.6 Flash costs 87% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where GPT-5.5 pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+50.5points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+26.3points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+24.6points ahead
Where Gemini 3.6 Flash pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+33.4points ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+4.7points ahead
- Completes tasks by operating a computer desktopOSWorld-Verified+4.3points ahead
Every test, side by side
All 40 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.5
- LiveBench · Agentic CodingGPT-5.5 by 10.643.454+10.6
- Terminal-Bench 2.1GPT-5.5 by 6.877.584.3+6.8
- LiveBench · CodingGPT-5.5 by 4.377.982.2+4.3
- LMArena · WebDevGemini 3.6 Flash by 24 rating points15361512+24 rating
- SciCodeGPT-5.5 by 2.453.455.8+2.4
- SWE-bench Protie58.758.6tie
AgentsGPT-5.5
- τ-Bench V3 · BankingGPT-5.5 by 9.129.939+9.1
- Terminal-Bench 4.0GPT-5.5 by 7.57.114.6+7.5
- OSWorld-VerifiedGemini 3.6 Flash by 4.38378.7+4.3
- GDPValGPT-5.5 by 3.439.342.7+3.4
ReasoningGPT-5.5
- ARC-AGI-2GPT-5.5 by 24.660.485+24.6
- CritPtGPT-5.5 by 16.510.627.1+16.5
- Humanity's Last ExamGPT-5.5 by 540.845.8+5
- LiveBench · ReasoningGPT-5.5 by 4.585.289.7+4.5
- GPQA Diamondtie92.893.5tie
FactsGemini 3.6 Flash
- AA-Omniscience · Non-hallucinationGemini 3.6 Flash by 33.444.411+33.4
- AA-Omniscience · AccuracyGPT-5.5 by 85058+8
- SimpleQA VerifiedGemini 3.6 Flash by 3.266.263+3.2
Images and chartsGemini 3.6 Flash
- MMMU-ProGemini 3.6 Flash by 3.383.279.9+3.3
- LMArena · Visiontie12971292tie
MathGPT-5.5
- FrontierMath Tier 4GPT-5.5 by 50.521.972.5+50.5
- FrontierMath Tiers 1-3 (v2)GPT-5.5 by 26.35985.3+26.3
- LiveBench · MathematicsGPT-5.5 by 9.586.495.9+9.5
- HMMT Feb. 2026GPT-5.5 by 9.189.498.5+9.1
- AIME 2026GPT-5.5 by 3.396.7100+3.3
Following instructionsGemini 3.6 Flash
- LiveBench · Instruction FollowingGemini 3.6 Flash by 4.775.470.7+4.7
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.
- DeepSWEGPT-5.5 by 214970+21
- livebench_data_analysisGPT-5.5 by 18.66381.6+18.6
- DeepSWE 1.1GPT-5.5 by 184967+18
- GDPval-AA v2GPT-5.5 by 88 rating points14211509+88 rating
- AA Agentic IndexGPT-5.5 by 7.130.237.3+7.1
- matharena_visual_math_overallGPT-5.5 by 787.894.9+7
- GDPval-AA v2 EloGPT-5.5 by 69 rating points14221491+69 rating
- Artificial Analysis Coding IndexGPT-5.5 by 5.769.274.9+5.7
- AA IntelligenceGPT-5.5 by 4.43438.4+4.4
- ARC-AGI-1GPT-5.5 by 3.891.295+3.8
- livebench_languageGPT-5.5 by 3.583.987.4+3.5
- GDP (Surge AI)GPT-5.5 by 2.92224.9+2.9
- AA-OmniscienceGemini 3.6 Flash by 1.622.120.5+1.6
Questions people ask
Which is better, Gemini 3.6 Flash or GPT-5.5?
GPT-5.5 wins five of the eight areas we test: coding, agents, reasoning, math and long documents. Gemini 3.6 Flash wins facts, images and charts and following instructions, and costs 87% less.
Which is better for coding?
GPT-5.5. It wins 4 of the 6 coding tests both models report; Gemini 3.6 Flash wins 1, and 1 is a tie.
Which is cheaper?
Gemini 3.6 Flash costs $0.75 per million input tokens and $3.75 per million output tokens; GPT-5.5 costs $5.00 and $30.00. That makes Gemini 3.6 Flash about 87% cheaper for the same work.
How do you compare the two?
We use the 40 benchmark tests both models have published scores on. The verdict counts the 27 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.