Gemini 3.1 Pro vs Gemini 3.8 Flash
Wins 1 of 8 areas
Facts
Wins 5 of 8 areas
Coding · Agents · Reasoning · Images and charts · Following instructions
Gemini 3.8 Flash is the stronger all-rounder.Gemini 3.1 Pro is better at facts.
Both rank among the ten best models we track in 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.
- ReasoningHard problems that need careful thinking05Gemini 3.8 Flash5 of 7 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own04Gemini 3.8 Flash4 of 4 tests
- Images and chartsUnderstanding pictures, charts and video03Gemini 3.8 Flash3 of 3 tests
- CodingWriting and fixing software23Gemini 3.8 Flash3 of 5 tests
- Following instructionsDoing exactly what it is asked01Gemini 3.8 Flash1 of 1 test
- FactsGetting facts right instead of making them up20Gemini 3.1 Pro2 of 3 tests · 1 tie
- MathCompetition and research-level math11Even1 each · 1 tie
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
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 3.8 Flash costs 68% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Gemini 3.8 Flash pulls ahead
- Real work tasks from 44 professionsGDPVal+32.2points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+23.5points ahead
- Finds the root cause of IT system incidentsAA IT-Bench SRE+22.2points ahead
Where Gemini 3.1 Pro pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+4.8points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+4.3points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+4points 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.
CodingGemini 3.8 Flash
- LMArena · WebDevGemini 3.8 Flash by 139 rating points14471586+139 rating
- Terminal-Bench 2.1Gemini 3.8 Flash by 13.873.887.6+13.8
- LiveBench · Agentic CodingGemini 3.8 Flash by 10.144.154.2+10.1
- LiveBench · CodingGemini 3.1 Pro by 476.572.5+4
- SciCodeGemini 3.1 Pro by 2.158.756.6+2.1
AgentsGemini 3.8 Flash
- GDPValGemini 3.8 Flash by 32.214.646.8+32.2
- τ-Bench V3 · BankingGemini 3.8 Flash by 23.521.444.9+23.5
- AA IT-Bench SREGemini 3.8 Flash by 22.230.352.5+22.2
- Terminal-Bench 4.0Gemini 3.8 Flash by 15.7419.7+15.7
ReasoningGemini 3.8 Flash
- ARC-AGI-2Gemini 3.8 Flash by 12.177.189.2+12.1
- ARC-AGI-3Gemini 3.8 Flash by 100.410.4+10
- LiveBench · ReasoningGemini 3.8 Flash by 5.38489.3+5.3
- SimpleBenchGemini 3.8 Flash by 2.879.682.4+2.8
- GPQA DiamondGemini 3.8 Flash by 1.294.195.3+1.2
- Humanity's Last Examtie4747.8tie
- CritPttie17.718.3tie
FactsGemini 3.1 Pro
- AA-Omniscience · Non-hallucinationGemini 3.1 Pro by 4.349.144.8+4.3
- SimpleQA VerifiedGemini 3.1 Pro by 3.873.569.7+3.8
- AA-Omniscience · Accuracytie54.954.6tie
Images and chartsGemini 3.8 Flash
- MMMU-ProGemini 3.8 Flash by 3.282.485.6+3.2
- CharXiv (RQ)Gemini 3.8 Flash by 2.983.386.2+2.9
- LMArena · VisionGemini 3.8 Flash by 18 rating points12961314+18 rating
MathEven
- FrontierMath Tiers 1-3 (v2)Gemini 3.8 Flash by 8.759.668.4+8.7
- FrontierMath Tier 4Gemini 3.1 Pro by 4.826.821.9+4.8
- LiveBench · Mathematicstie9191.6tie
Following instructionsGemini 3.8 Flash
- LiveBench · Instruction FollowingGemini 3.8 Flash by 2.379.181.4+2.3
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.
- DeepSWE 1.1Gemini 3.8 Flash by 61.71273.7+61.7
- GDPval-AA v2Gemini 3.8 Flash by 583 rating points9621545+583 rating
- GDPval-AA v2 EloGemini 3.8 Flash by 580 rating points9651545+580 rating
- AA Agentic IndexGemini 3.8 Flash by 30.810.341.1+30.8
- livebench_data_analysisGemini 3.1 Pro by 24.578.554+24.5
- LVBenchGemini 3.8 Flash by 20.966.287.1+20.9
- GDP (Surge AI)Gemini 3.8 Flash by 18.316.735+18.3
- AA IntelligenceGemini 3.8 Flash by 11.229.740.9+11.2
- Artificial Analysis Coding IndexGemini 3.8 Flash by 7.568.876.3+7.5
- HiL-Bench (Tools-allowed)Gemini 3.8 Flash by 6.235.341.5+6.2
- livebench_languageGemini 3.8 Flash by 2.485.487.8+2.4
- AA-OmniscienceGemini 3.1 Pro by 2.331.929.6+2.3
- ARC-AGI-1tie9898.5tie
Questions people ask
Which is better, Gemini 3.1 Pro or Gemini 3.8 Flash?
Gemini 3.8 Flash wins five of the eight areas we test: coding, agents, reasoning, images and charts and following instructions. Gemini 3.1 Pro wins facts. They are level on math and long documents.
Which is better for coding?
Gemini 3.8 Flash. It wins 3 of the 5 coding tests both models report; Gemini 3.1 Pro wins 2.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Gemini 3.8 Flash costs $0.75 and $3.75. That makes Gemini 3.8 Flash about 68% 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.