Claude Opus 4.8 vs Gemini 3.6 Flash
Wins 4 of 8 areas
Coding · Agents · Reasoning · Math
Wins 3 of 8 areas
Facts · Long documents · Following instructions
Claude Opus 4.8 wins more areas, narrowly.Gemini 3.6 Flash is cheaper and better at facts.
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 software60Claude Opus 4.86 of 6 tests
- MathCompetition and research-level math50Claude Opus 4.85 of 5 tests
- ReasoningHard problems that need careful thinking40Claude Opus 4.84 of 5 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own30Claude Opus 4.83 of 4 tests · 1 tie
- FactsGetting facts right instead of making them up12Gemini 3.6 Flash2 of 3 tests
- Long documentsFinding answers in very long texts01Gemini 3.6 Flash1 of 1 test
- Following instructionsDoing exactly what it is asked01Gemini 3.6 Flash1 of 1 test
- Images and chartsUnderstanding pictures, charts and video00Even0 each · 2 ties
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 85% 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
- Extremely hard research-level math problemsFrontierMath Tier 4+34.1points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+21points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+16.3points ahead
Where Gemini 3.6 Flash pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+13.2points ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+3.4points ahead
- Reasons across sets of long documentsAA-LCR+2.3points 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.
CodingClaude Opus 4.8
- SWE-bench ProClaude Opus 4.8 by 10.569.258.7+10.5
- LiveBench · Agentic CodingClaude Opus 4.8 by 7.150.543.4+7.1
- Terminal-Bench 2.1Claude Opus 4.8 by 7.184.677.5+7.1
- LiveBench · CodingClaude Opus 4.8 by 3.981.877.9+3.9
- LMArena · WebDevClaude Opus 4.8 by 20 rating points15561536+20 rating
- SciCodeClaude Opus 4.8 by 154.453.4+1
AgentsClaude Opus 4.8
- Terminal-Bench 4.0Claude Opus 4.8 by 14.621.77.1+14.6
- GDPValClaude Opus 4.8 by 8.547.839.3+8.5
- τ-Bench V3 · BankingClaude Opus 4.8 by 4.334.229.9+4.3
- OSWorld-Verifiedtie83.483tie
ReasoningClaude Opus 4.8
- ARC-AGI-2Claude Opus 4.8 by 11.772.160.4+11.7
- CritPtClaude Opus 4.8 by 10.320.910.6+10.3
- Humanity's Last ExamClaude Opus 4.8 by 7.948.740.8+7.9
- LiveBench · ReasoningClaude Opus 4.8 by 489.285.2+4
- GPQA Diamondtie9292.8tie
FactsGemini 3.6 Flash
- AA-Omniscience · Non-hallucinationClaude Opus 4.8 by 16.360.744.4+16.3
- SimpleQA VerifiedGemini 3.6 Flash by 13.25366.2+13.2
- AA-Omniscience · AccuracyGemini 3.6 Flash by 1.248.850+1.2
Images and chartsEven
- CharXiv (RQ)tie89.989.4tie
- LMArena · Visiontie12951297tie
MathClaude Opus 4.8
- FrontierMath Tier 4Claude Opus 4.8 by 34.156.121.9+34.1
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.8 by 218059+21
- LiveBench · MathematicsClaude Opus 4.8 by 7.994.386.4+7.9
- 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 3.6 Flash
- LiveBench · Instruction FollowingGemini 3.6 Flash by 3.47275.4+3.4
Other results16 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.
- GDP (Surge AI)Claude Opus 4.8 by 62.884.822+62.8
- OSWorld 2.0Claude Opus 4.8 by 21.955.733.8+21.9
- GDPval-AA v2Claude Opus 4.8 by 172 rating points15931421+172 rating
- GDPval-AA v2 EloClaude Opus 4.8 by 171 rating points15931422+171 rating
- Terminal-bench 3.0Claude Opus 4.8 by 15.721.15.4+15.7
- AA Agentic IndexClaude Opus 4.8 by 12.442.630.2+12.4
- DeepSWE 1.1Claude Opus 4.8 by 105949+10
- DeepSWEClaude Opus 4.8 by 95849+9
- AA IntelligenceClaude Opus 4.8 by 7.841.834+7.8
- AA-OmniscienceClaude Opus 4.8 by 6.728.822.1+6.7
- matharena_visual_math_overallGemini 3.6 Flash by 6.381.687.8+6.3
- Artificial Analysis Coding IndexClaude Opus 4.8 by 5.174.369.2+5.1
- livebench_languageGemini 3.6 Flash by 4.279.783.9+4.2
- livebench_data_analysisClaude Opus 4.8 by 36663+3
- ARC-AGI-1Claude Opus 4.8 by 1.392.591.2+1.3
- CharXiv Reasoning (With tools)tie89.989.4tie
Questions people ask
Which is better, Claude Opus 4.8 or Gemini 3.6 Flash?
Claude Opus 4.8 wins four of the eight areas we test: coding, agents, reasoning and math. Gemini 3.6 Flash wins facts, long documents and following instructions, and costs 85% less. They are level on images and charts.
Which is better for coding?
Claude Opus 4.8. It wins 6 of the 6 coding tests both models report; Gemini 3.6 Flash wins none.
Which is cheaper?
Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Gemini 3.6 Flash costs $0.75 and $3.75. That makes Gemini 3.6 Flash about 85% cheaper for the same work.
How do you compare the two?
We use the 43 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 16 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.