Claude Opus 4.8 vs Gemini 3 Flash Preview
Wins 5 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math
Wins 2 of 8 areas
Facts · Following instructions
Claude Opus 4.8 is the stronger all-rounder.Gemini 3 Flash Preview is cheaper and better at facts.
Scores updated · 44 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 software60Claude Opus 4.86 of 6 tests
- AgentsCarrying out multi-step tasks on its own50Claude Opus 4.85 of 5 tests
- ReasoningHard problems that need careful thinking50Claude Opus 4.85 of 5 tests
- MathCompetition and research-level math40Claude Opus 4.84 of 4 tests
- Images and chartsUnderstanding pictures, charts and video20Claude Opus 4.82 of 2 tests
- FactsGetting facts right instead of making them up12Gemini 3 Flash Preview2 of 3 tests
- Following instructionsDoing exactly what it is asked01Gemini 3 Flash Preview1 of 1 test
- 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 Flash Preview costs 88% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Opus 4.8 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+53.7points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+39points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+38.5points ahead
Where Gemini 3 Flash Preview pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+15.8points ahead
- Short factual questions, answered correctlySimpleQA Verified+13.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+4.6points ahead
Every test, side by side
All 44 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.8
- Terminal-Bench 2.1Claude Opus 4.8 by 26.684.658+26.6
- Terminal-Bench HardClaude Opus 4.8 by 19.758.338.6+19.7
- SWE-bench ProClaude Opus 4.8 by 19.669.249.6+19.6
- LMArena · WebDevClaude Opus 4.8 by 117 rating points15561439+117 rating
- SWE-bench VerifiedClaude Opus 4.8 by 10.688.678+10.6
- SciCodeClaude Opus 4.8 by 3.854.450.6+3.8
AgentsClaude Opus 4.8
- MCP AtlasClaude Opus 4.8 by 24.882.257.4+24.8
- OSWorld-VerifiedClaude Opus 4.8 by 18.383.465.1+18.3
- τ-Bench V3 · BankingClaude Opus 4.8 by 13.434.220.8+13.4
- GDPValClaude Opus 4.8 by 12.647.835.2+12.6
- AA ApexAgentsClaude Opus 4.8 by 11.739.427.7+11.7
ReasoningClaude Opus 4.8
- ARC-AGI-2Claude Opus 4.8 by 38.572.133.6+38.5
- CritPtClaude Opus 4.8 by 12.320.98.6+12.3
- Humanity's Last ExamClaude Opus 4.8 by 12.148.736.6+12.1
- SimpleBenchClaude Opus 4.8 by 3.764.861.1+3.7
- GPQA DiamondClaude Opus 4.8 by 2.29289.8+2.2
FactsGemini 3 Flash Preview
- AA-Omniscience · Non-hallucinationClaude Opus 4.8 by 53.760.77+53.7
- SimpleQA VerifiedGemini 3 Flash Preview by 13.85366.8+13.8
- AA-Omniscience · AccuracyGemini 3 Flash Preview by 4.648.853.4+4.6
Images and chartsClaude Opus 4.8
- CharXiv (RQ)Claude Opus 4.8 by 9.689.980.3+9.6
- LMArena · VisionClaude Opus 4.8 by 10 rating points12951285+10 rating
MathClaude Opus 4.8
- FrontierMath Tier 4Claude Opus 4.8 by 3956.117.1+39
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.8 by 28.88051.2+28.8
- HMMT Feb. 2026Claude Opus 4.8 by 6.195.589.4+6.1
- AIME 2026Claude Opus 4.8 by 3.310096.7+3.3
Following instructionsGemini 3 Flash Preview
- IFBenchGemini 3 Flash Preview by 15.862.278+15.8
Other results17 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.
- GDPval-AA (Elo)Claude Opus 4.8 by 686 rating points18901204+686 rating
- Artificial Analysis Coding IndexClaude Opus 4.8 by 31.774.342.6+31.7
- frontiermath_tier_4_v1Claude Opus 4.8 by 27.131.34.2+27.1
- Terminal-Bench 2.0Claude Opus 4.8 by 2774.647.6+27
- ScreenSpot-Pro (No tools)Claude Opus 4.8 by 18.887.969.1+18.8
- AA-OmniscienceClaude Opus 4.8 by 18.728.810.1+18.7
- AA IntelligenceClaude Opus 4.8 by 15.541.826.3+15.5
- Blueprint-Bench 2Claude Opus 4.8 by 14.514.50+14.5
- τ²-Bench Telecom (AA run)Claude Opus 4.8 by 1494.480.4+14
- Finance Agent v2Claude Opus 4.8 by 11.353.942.5+11.3
- ToolathlonClaude Opus 4.8 by 10.559.949.4+10.5
- Legal Agent BenchmarkClaude Opus 4.8 by 10100+10
- ARC-AGI-1Claude Opus 4.8 by 7.892.584.7+7.8
- AA Agentic IndexGemini 3 Flash Preview by 7.142.649.7+7.1
- LiveBenchClaude Opus 4.8 by 4.877.272.4+4.8
- matharena_visual_math_overallGemini 3 Flash Preview by 4.281.685.8+4.2
- HMMT Nov. 2025Claude Opus 4.8 by 3.296.593.3+3.2
Questions people ask
Which is better, Claude Opus 4.8 or Gemini 3 Flash Preview?
Claude Opus 4.8 wins five of the eight areas we test: coding, agents, reasoning, images and charts and math. Gemini 3 Flash Preview wins facts and following instructions, and costs 88% less. They are level on long documents.
Which is better for coding?
Claude Opus 4.8. It wins 6 of the 6 coding tests both models report; Gemini 3 Flash Preview wins none.
Which is cheaper?
Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Gemini 3 Flash Preview costs $0.50 and $3.00. That makes Gemini 3 Flash Preview about 88% cheaper for the same work.
How do you compare the two?
We use the 44 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 17 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.