Gemini 3.6 Flash vs Gemini 3.7 Flash
Wins 0 of 8 areas
—
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Gemini 3.7 Flash is the stronger all-rounder.
Scores updated · 43 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 3.7 Flash5 of 5 tests
- ReasoningHard problems that need careful thinking05Gemini 3.7 Flash5 of 5 tests
- AgentsCarrying out multi-step tasks on its own03Gemini 3.7 Flash3 of 3 tests
- MathCompetition and research-level math03Gemini 3.7 Flash3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02Gemini 3.7 Flash2 of 3 tests · 1 tie
- Long documentsFinding answers in very long texts02Gemini 3.7 Flash2 of 2 tests
- FactsGetting facts right instead of making them up12Gemini 3.7 Flash2 of 3 tests
- Following instructionsDoing exactly what it is asked01Gemini 3.7 Flash1 of 1 test
Following instructions 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Gemini 3.7 Flash pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+24.2points ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+14.9points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+14.6points ahead
Where Gemini 3.6 Flash pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+8.9points ahead
Every test, side by side
All 43 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3.7 Flash
- LiveBench · Agentic CodingGemini 3.7 Flash by 14.943.458.3+14.9
- Terminal-Bench 2.1Gemini 3.7 Flash by 8.377.585.8+8.3
- LMArena · WebDevGemini 3.7 Flash by 54 rating points15381592+54 rating
- SciCodeGemini 3.7 Flash by 3.853.457.2+3.8
- LiveBench · CodingGemini 3.7 Flash by 177.978.9+1
AgentsGemini 3.7 Flash
- Terminal-Bench 4.0Gemini 3.7 Flash by 6.57.113.6+6.5
- GDPValGemini 3.7 Flash by 5.339.344.6+5.3
- τ-Bench V3 · BankingGemini 3.7 Flash by 2.929.932.8+2.9
ReasoningGemini 3.7 Flash
- ARC-AGI-2Gemini 3.7 Flash by 24.260.484.6+24.2
- Humanity's Last ExamGemini 3.7 Flash by 7.140.847.9+7.1
- CritPtGemini 3.7 Flash by 3.710.614.3+3.7
- LiveBench · ReasoningGemini 3.7 Flash by 2.685.287.8+2.6
- GPQA DiamondGemini 3.7 Flash by 1.792.894.5+1.7
FactsGemini 3.7 Flash
- AA-Omniscience · Non-hallucinationGemini 3.6 Flash by 8.944.435.5+8.9
- AA-Omniscience · AccuracyGemini 3.7 Flash by 5.35055.3+5.3
- SimpleQA VerifiedGemini 3.7 Flash by 366.269.2+3
Images and chartsGemini 3.7 Flash
- MMMU-ProGemini 3.7 Flash by 2.383.285.5+2.3
- LMArena · VisionGemini 3.7 Flash by 18 rating points12971315+18 rating
- CharXiv (RQ)tie89.488.7tie
MathGemini 3.7 Flash
- FrontierMath Tier 4Gemini 3.7 Flash by 14.621.936.6+14.6
- FrontierMath Tiers 1-3 (v2)Gemini 3.7 Flash by 12.65971.6+12.6
- LiveBench · MathematicsGemini 3.7 Flash by 7.186.493.5+7.1
Long documentsGemini 3.7 Flash
- MRCR v2 8 needle 128k (average)Gemini 3.7 Flash by 5.291.897+5.2
- AA-LCRGemini 3.7 Flash by 1.78081.7+1.7
Following instructionsGemini 3.7 Flash
- LiveBench · Instruction FollowingGemini 3.7 Flash by 4.575.479.9+4.5
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.
- DeepSWE 1.1Gemini 3.7 Flash by 16.34965.3+16.3
- OSWorld 2.0Gemini 3.7 Flash by 14.133.847.9+14.1
- GDP (Surge AI)Gemini 3.7 Flash by 122234+12
- GDPval-AA v2Gemini 3.7 Flash by 104 rating points14211525+104 rating
- Terminal-bench 3.0Gemini 3.7 Flash by 9.55.414.9+9.5
- Artificial Analysis Coding IndexGemini 3.7 Flash by 6.969.276.1+6.9
- AA Agentic IndexGemini 3.7 Flash by 6.230.236.4+6.2
- GDPval-AA v2 EloGemini 3.7 Flash by 60 rating points14221482+60 rating
- AA IntelligenceGemini 3.7 Flash by 5.13439.1+5.1
- Code Arena (Elo)Gemini 3.7 Flash by 50 rating points15381588+50 rating
- livebench_data_analysisGemini 3.7 Flash by 56368+5
- AA-OmniscienceGemini 3.7 Flash by 4.422.126.5+4.4
- ARC-AGI-1Gemini 3.7 Flash by 4.391.295.5+4.3
- HLE-VerifiedGemini 3.7 Flash by 2.451.253.6+2.4
- Agent's Last Exam (Pass rate)Gemini 3.7 Flash by 2.124.226.3+2.1
- livebench_languageGemini 3.7 Flash by 1.683.985.5+1.6
- LVBenchGemini 3.7 Flash by 1.284.285.4+1.2
- CharXiv Reasoning (With tools)tie89.488.7tie
Questions people ask
Which is better, Gemini 3.6 Flash or Gemini 3.7 Flash?
Gemini 3.7 Flash wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. Gemini 3.6 Flash wins none.
Which is better for coding?
Gemini 3.7 Flash. It wins 5 of the 5 coding tests both models report; Gemini 3.6 Flash wins none.
Which is cheaper?
Gemini 3.6 Flash costs $0.75 per million input tokens and $3.75 per million output tokens; Gemini 3.7 Flash costs $0.75 and $3.75. For a million tokens read plus a million written, they cost about the same.
How do you compare the two?
We use the 43 benchmark tests both models have published scores on. The verdict counts the 25 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.