Gemini 3.5 Flash vs GPT-5
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Following instructions
Wins 1 of 8 areas
Long documents
Gemini 3.5 Flash is the stronger all-rounder.GPT-5 is better at long documents.
Scores updated · 31 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 software50Gemini 3.5 Flash5 of 5 tests
- ReasoningHard problems that need careful thinking50Gemini 3.5 Flash5 of 5 tests
- FactsGetting facts right instead of making them up30Gemini 3.5 Flash3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video30Gemini 3.5 Flash3 of 3 tests
- AgentsCarrying out multi-step tasks on its own20Gemini 3.5 Flash2 of 2 tests
- MathCompetition and research-level math20Gemini 3.5 Flash2 of 2 tests
- Following instructionsDoing exactly what it is asked10Gemini 3.5 Flash1 of 1 test
- Long documentsFinding answers in very long texts01GPT-51 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 3.5 Flash costs 7% 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 3.5 Flash pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+62.2points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+43.5points ahead
- Common-sense trick questionsSimpleBench+20points ahead
Where GPT-5 pulls ahead
- Reasons across sets of long documentsAA-LCR+4.9points ahead
Every test, side by side
All 31 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3.5 Flash
- Terminal-Bench 2.1Gemini 3.5 Flash by 43.578.735.2+43.5
- SWE-bench ProGemini 3.5 Flash by 13.355.141.8+13.3
- SciCodeGemini 3.5 Flash by 1153.942.9+11
- Terminal-Bench HardGemini 3.5 Flash by 8.340.932.6+8.3
- LMArena · WebDevGemini 3.5 Flash by 81 rating points14991418+81 rating
AgentsGemini 3.5 Flash
- GDPValGemini 3.5 Flash by 14.235.221+14.2
- τ-Bench V3 · BankingGemini 3.5 Flash by 10.132.222.1+10.1
ReasoningGemini 3.5 Flash
- ARC-AGI-2Gemini 3.5 Flash by 62.272.19.9+62.2
- SimpleBenchGemini 3.5 Flash by 2076.756.7+20
- Humanity's Last ExamGemini 3.5 Flash by 14.242.728.5+14.2
- CritPtGemini 3.5 Flash by 7.413.15.7+7.4
- GPQA DiamondGemini 3.5 Flash by 6.892.285.4+6.8
FactsGemini 3.5 Flash
- AA-Omniscience · Non-hallucinationGemini 3.5 Flash by 2037.817.8+20
- SimpleQA VerifiedGemini 3.5 Flash by 16.166.250.1+16.1
- AA-Omniscience · AccuracyGemini 3.5 Flash by 11.151.440.3+11.1
Images and chartsGemini 3.5 Flash
- LMArena · VisionGemini 3.5 Flash by 102 rating points13101208+102 rating
- MMMU-ProGemini 3.5 Flash by 10.184.374.2+10.1
- CharXiv (RQ)Gemini 3.5 Flash by 3.184.281.1+3.1
MathGemini 3.5 Flash
- FrontierMath Tiers 1-3 (v2)Gemini 3.5 Flash by 7.462.855.4+7.4
- FrontierMath Tier 4Gemini 3.5 Flash by 4.826.821.9+4.8
Following instructionsGemini 3.5 Flash
- IFBenchGemini 3.5 Flash by 3.276.373.1+3.2
Other results9 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.
- Terminal-Bench 2.0Gemini 3.5 Flash by 4176.235.2+41
- Artificial Analysis Coding IndexGemini 3.5 Flash by 32.370.137.8+32.3
- AA-OmniscienceGemini 3.5 Flash by 29.921.2-8.7+29.9
- ARC-AGI-1Gemini 3.5 Flash by 26.892.565.7+26.8
- matharena_visual_math_overallGemini 3.5 Flash by 11.189.978.8+11.1
- τ²-Bench Telecom (AA run)Gemini 3.5 Flash by 10.595.384.8+10.5
- AA IntelligenceGemini 3.5 Flash by 9.632.623+9.6
- frontiermath_tier_4_v1Gemini 3.5 Flash by 2.114.612.5+2.1
- AA Agentic Indextie27.326.5tie
Questions people ask
Which is better, Gemini 3.5 Flash or GPT-5?
Gemini 3.5 Flash wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and following instructions. GPT-5 wins long documents.
Which is better for coding?
Gemini 3.5 Flash. It wins 5 of the 5 coding tests both models report; GPT-5 wins none.
Which is cheaper?
Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens; GPT-5 costs $1.25 and $10.00. That makes Gemini 3.5 Flash about 7% cheaper for the same work.
How do you compare the two?
We use the 31 benchmark tests both models have published scores on. The verdict counts the 22 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.