Claude Opus 4.6 vs GPT-5.1 Codex mini
Wins 5 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents
Wins 1 of 7 areas
Following instructions
Claude Opus 4.6 is the stronger all-rounder.GPT-5.1 Codex mini is cheaper and better at following instructions.
Scores updated · 18 tests both models report · How we compare
Where each one wins
Tests won in each of the seven areas where both have results. 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 software30Claude Opus 4.63 of 3 tests
- ReasoningHard problems that need careful thinking30Claude Opus 4.63 of 3 tests
- AgentsCarrying out multi-step tasks on its own10Claude Opus 4.61 of 1 test
- Images and chartsUnderstanding pictures, charts and video10Claude 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 asked01GPT-5.1 Codex mini1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Agents, images and charts, 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-5.1 Codex mini costs 93% 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 4.6 pulls ahead
- Real work tasks from 44 professionsGDPVal+28.2points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+23.8points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+21.4points ahead
Where GPT-5.1 Codex mini pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+14.8points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+11.2points ahead
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.6
- LMArena · WebDevClaude Opus 4.6 by 303 rating points15461243+303 rating
- Terminal-Bench HardClaude Opus 4.6 by 12.946.233.3+12.9
- SciCodeClaude Opus 4.6 by 9.351.942.6+9.3
ReasoningClaude Opus 4.6
- Humanity's Last ExamClaude Opus 4.6 by 21.439.918.5+21.4
- CritPtClaude Opus 4.6 by 12.612.60+12.6
- GPQA DiamondClaude Opus 4.6 by 8.389.681.3+8.3
FactsEven
- AA-Omniscience · AccuracyClaude Opus 4.6 by 23.84723.2+23.8
- AA-Omniscience · Non-hallucinationGPT-5.1 Codex mini by 11.237.248.4+11.2
Images and chartsClaude Opus 4.6
- MMMU-ProClaude Opus 4.6 by 6.475.469+6.4
Following instructionsGPT-5.1 Codex mini
- IFBenchGPT-5.1 Codex mini by 14.853.167.9+14.8
Other results6 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.
- AIME 2025Claude Opus 4.6 by 57.799.842.1+57.7
- AA-OmniscienceClaude Opus 4.6 by 30.113.7-16.4+30.1
- τ²-Bench Telecom (AA run)Claude Opus 4.6 by 29.292.162.9+29.2
- AA Agentic IndexClaude Opus 4.6 by 28.967.638.7+28.9
- Artificial Analysis Coding IndexClaude Opus 4.6 by 11.748.136.4+11.7
- AA IntelligenceClaude Opus 4.6 by 11.531.920.4+11.5
Questions people ask
Which is better, Claude Opus 4.6 or GPT-5.1 Codex mini?
Claude Opus 4.6 wins five of the seven areas where both have results: coding, agents, reasoning, images and charts and long documents. GPT-5.1 Codex mini wins following instructions, and costs 93% less. They are level on facts.
Which is better for coding?
Claude Opus 4.6. It wins 3 of the 3 coding tests both models report; GPT-5.1 Codex 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-5.1 Codex mini costs $0.25 and $2.00. That makes GPT-5.1 Codex mini about 93% cheaper for the same work.
How do you compare the two?
We use the 18 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 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.