Claude Sonnet 4.5 vs GPT-5.1 Codex mini
Wins 4 of 7 areas
Coding · Reasoning · Facts · Long documents
Wins 2 of 7 areas
Agents · Following instructions
Claude Sonnet 4.5 wins more areas, narrowly.GPT-5.1 Codex mini is cheaper and better at agents.
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 Sonnet 4.53 of 3 tests
- ReasoningHard problems that need careful thinking20Claude Sonnet 4.52 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up20Claude Sonnet 4.52 of 2 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 4.51 of 1 test
- AgentsCarrying out multi-step tasks on its own01GPT-5.1 Codex mini1 of 1 test
- Following instructionsDoing exactly what it is asked01GPT-5.1 Codex mini1 of 1 test
- Images and chartsUnderstanding pictures, charts and video00Even0 each · 1 tie
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 88% 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 Sonnet 4.5 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+9.7points ahead
- Reasons across sets of long documentsAA-LCR+5.6points ahead
- Code for real scientific research problemsSciCode+3.1points 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 Sonnet 4.5
- LMArena · WebDevClaude Sonnet 4.5 by 151 rating points13941243+151 rating
- SciCodeClaude Sonnet 4.5 by 3.145.742.6+3.1
- Terminal-Bench HardClaude Sonnet 4.5 by 2.335.633.3+2.3
ReasoningClaude Sonnet 4.5
- GPQA DiamondClaude Sonnet 4.5 by 2.183.481.3+2.1
- CritPtClaude Sonnet 4.5 by 1.11.10+1.1
- Humanity's Last Examtie17.818.5tie
FactsClaude Sonnet 4.5
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 9.732.923.2+9.7
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 2.550.948.4+2.5
Long documentsClaude Sonnet 4.5
- AA-LCRClaude Sonnet 4.5 by 5.672.366.7+5.6
Following instructionsGPT-5.1 Codex mini
- IFBenchGPT-5.1 Codex mini by 10.657.367.9+10.6
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 Sonnet 4.5 by 44.98742.1+44.9
- AA Agentic IndexGPT-5.1 Codex mini by 21.217.538.7+21.2
- AA-OmniscienceClaude Sonnet 4.5 by 16.3-0.1-16.4+16.3
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 15.752.136.4+15.7
- τ²-Bench Telecom (AA run)Claude Sonnet 4.5 by 15.278.162.9+15.2
- AA Intelligencetie20.720.4tie
Questions people ask
Which is better, Claude Sonnet 4.5 or GPT-5.1 Codex mini?
Claude Sonnet 4.5 wins four of the seven areas where both have results: coding, reasoning, facts and long documents. GPT-5.1 Codex mini wins agents and following instructions, and costs 88% less. They are level on images and charts.
Which is better for coding?
Claude Sonnet 4.5. It wins 3 of the 3 coding tests both models report; GPT-5.1 Codex mini wins none.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-5.1 Codex mini costs $0.25 and $2.00. That makes GPT-5.1 Codex mini about 88% 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.