Claude Opus 4.8 vs GPT-5
Wins 6 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math
Wins 1 of 8 areas
Following instructions
Claude Opus 4.8 is the stronger all-rounder.GPT-5 is cheaper and better at following instructions.
Scores updated · 37 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 software70Claude Opus 4.87 of 7 tests
- ReasoningHard problems that need careful thinking50Claude Opus 4.85 of 5 tests
- AgentsCarrying out multi-step tasks on its own30Claude Opus 4.83 of 3 tests
- FactsGetting facts right instead of making them up30Claude Opus 4.83 of 3 tests
- MathCompetition and research-level math30Claude Opus 4.83 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20Claude Opus 4.82 of 2 tests
- Following instructionsDoing exactly what it is asked01GPT-51 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.
GPT-5 costs 63% 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 Claude Opus 4.8 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+62.2points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+49.4points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+42.9points ahead
Where GPT-5 pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+10.9points ahead
Every test, side by side
All 37 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 49.484.635.2+49.4
- SWE-bench MultilingualClaude Opus 4.8 by 29.184.455.3+29.1
- SWE-bench ProClaude Opus 4.8 by 27.469.241.8+27.4
- Terminal-Bench HardClaude Opus 4.8 by 25.758.332.6+25.7
- LMArena · WebDevClaude Opus 4.8 by 139 rating points15561417+139 rating
- SWE-bench VerifiedClaude Opus 4.8 by 13.788.674.9+13.7
- SciCodeClaude Opus 4.8 by 11.554.442.9+11.5
AgentsClaude Opus 4.8
- BrowseCompClaude Opus 4.8 by 29.484.354.9+29.4
- GDPValClaude Opus 4.8 by 26.847.821+26.8
- τ-Bench V3 · BankingClaude Opus 4.8 by 12.134.222.1+12.1
ReasoningClaude Opus 4.8
- ARC-AGI-2Claude Opus 4.8 by 62.272.19.9+62.2
- Humanity's Last ExamClaude Opus 4.8 by 20.248.728.5+20.2
- CritPtClaude Opus 4.8 by 15.220.95.7+15.2
- SimpleBenchClaude Opus 4.8 by 8.164.856.7+8.1
- GPQA DiamondClaude Opus 4.8 by 6.69285.4+6.6
FactsClaude Opus 4.8
- AA-Omniscience · Non-hallucinationClaude Opus 4.8 by 42.960.717.8+42.9
- AA-Omniscience · AccuracyClaude Opus 4.8 by 8.548.840.3+8.5
- SimpleQA VerifiedClaude Opus 4.8 by 2.95350.1+2.9
Images and chartsClaude Opus 4.8
- CharXiv (RQ)Claude Opus 4.8 by 8.889.981.1+8.8
- LMArena · VisionClaude Opus 4.8 by 87 rating points12951208+87 rating
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 24.68055.4+24.6
- IMOAnswerBenchClaude Opus 4.8 by 7.583.576+7.5
Other results12 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 2.0Claude Opus 4.8 by 39.474.635.2+39.4
- AA-OmniscienceClaude Opus 4.8 by 37.528.8-8.7+37.5
- Artificial Analysis Coding IndexClaude Opus 4.8 by 36.574.337.8+36.5
- ARC-AGI-1Claude Opus 4.8 by 26.892.565.7+26.8
- HLE (with tools)Claude Opus 4.8 by 22.757.935.2+22.7
- AA IntelligenceClaude Opus 4.8 by 18.841.823+18.8
- frontiermath_tier_4_v1Claude Opus 4.8 by 18.831.312.5+18.8
- AA Agentic IndexClaude Opus 4.8 by 16.142.626.5+16.1
- τ²-Bench Telecom (AA run)Claude Opus 4.8 by 9.694.484.8+9.6
- HealthBenchGPT-5 by 7.959.367.2+7.9
- HMMT Nov. 2025Claude Opus 4.8 by 7.396.589.2+7.3
- matharena_visual_math_overallClaude Opus 4.8 by 2.881.678.8+2.8
Questions people ask
Which is better, Claude Opus 4.8 or GPT-5?
Claude Opus 4.8 wins six of the eight areas we test: coding, agents, reasoning, facts, images and charts and math. GPT-5 wins following instructions, and costs 63% less. They are level on long documents.
Which is better for coding?
Claude Opus 4.8. It wins 7 of the 7 coding tests both models report; GPT-5 wins none.
Which is cheaper?
Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5 costs $1.25 and $10.00. That makes GPT-5 about 63% cheaper for the same work.
How do you compare the two?
We use the 37 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 12 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.