Claude Opus 4.6 vs GPT-5 mini
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents
Wins 1 of 8 areas
Following instructions
Claude Opus 4.6 is the stronger all-rounder.GPT-5 mini is cheaper and better at following instructions.
Scores updated · 32 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 thinking40Claude Opus 4.64 of 4 tests
- CodingWriting and fixing software30Claude Opus 4.63 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20Claude Opus 4.62 of 2 tests
- MathCompetition and research-level math20Claude Opus 4.62 of 2 tests
- FactsGetting facts right instead of making them up21Claude Opus 4.62 of 4 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own10Claude Opus 4.61 of 1 test
- Long documentsFinding answers in very long texts10Claude Opus 4.61 of 1 test
- Following instructionsDoing exactly what it is asked02GPT-5 mini2 of 2 tests
Agents and long documents 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 mini costs 93% 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 4.6 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+64.4points ahead
- Real work tasks from 44 professionsGDPVal+42.4points ahead
- Short factual questions, answered correctlySimpleQA Verified+25.4points ahead
Where GPT-5 mini pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+22.3points ahead
- Keeps track of context across a multi-turn chatMulti-Challenge+21.8points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+6.4points ahead
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.6
- SWE-bench VerifiedClaude Opus 4.6 by 2180.859.8+21
- SciCodeClaude Opus 4.6 by 12.951.939+12.9
- Terminal-Bench HardClaude Opus 4.6 by 12.946.233.3+12.9
ReasoningClaude Opus 4.6
- ARC-AGI-2Claude Opus 4.6 by 64.468.84.4+64.4
- Humanity's Last ExamClaude Opus 4.6 by 18.439.921.5+18.4
- CritPtClaude Opus 4.6 by 12.612.60+12.6
- GPQA DiamondClaude Opus 4.6 by 6.889.682.8+6.8
FactsClaude Opus 4.6
- SimpleQA VerifiedClaude Opus 4.6 by 25.44721.6+25.4
- AA-Omniscience · AccuracyClaude Opus 4.6 by 224725+22
- AA-Omniscience · Non-hallucinationGPT-5 mini by 6.437.243.6+6.4
- Vectara HHEM hallucination ratelower is bettertie12.212.9tie
Images and chartsClaude Opus 4.6
- LMArena · VisionClaude Opus 4.6 by 114 rating points13161202+114 rating
- MMMU-ProClaude Opus 4.6 by 5.375.470.1+5.3
MathClaude Opus 4.6
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.6 by 19.36646.7+19.3
- FrontierMath Tier 4Claude Opus 4.6 by 14.626.812.2+14.6
Following instructionsGPT-5 mini
- IFBenchGPT-5 mini by 22.353.175.4+22.3
- Multi-ChallengeGPT-5 mini by 21.837.159+21.8
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.
- AA Agentic IndexClaude Opus 4.6 by 58.767.68.9+58.7
- ARC-AGI-1Claude Opus 4.6 by 38.79354.3+38.7
- Artificial Analysis Coding IndexClaude Opus 4.6 by 32.548.115.6+32.5
- AA-OmniscienceClaude Opus 4.6 by 3113.7-17.3+31
- τ²-Bench Telecom (AA run)Claude Opus 4.6 by 23.792.168.4+23.7
- frontiermath_tier_4_v1Claude Opus 4.6 by 16.622.96.3+16.6
- AA IntelligenceClaude Opus 4.6 by 15.131.916.8+15.1
- HMMT Nov. 2025Claude Opus 4.6 by 12.196.384.2+12.1
- AIME 2025Claude Opus 4.6 by 8.799.891.1+8.7
- matharena_visual_math_overallGPT-5 mini by 5.972.378.2+5.9
- vectara_avg_summary_lengthGPT-5 mini by 32.1 rating points137.6169.7+32.1 rating
- vectara_factual_consistencytie87.887.1tie
- vectara_answer_ratetie99.899.9tie
Questions people ask
Which is better, Claude Opus 4.6 or GPT-5 mini?
Claude Opus 4.6 wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and long documents. GPT-5 mini wins following instructions, and costs 93% less.
Which is better for coding?
Claude Opus 4.6. It wins 3 of the 3 coding tests both models report; GPT-5 mini wins none.
Which is cheaper?
Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5 mini costs $0.25 and $2.00. That makes GPT-5 mini about 93% cheaper for the same work.
How do you compare the two?
We use the 32 benchmark tests both models have published scores on. The verdict counts the 19 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.