Claude 3.7 Sonnet vs GPT-5 Codex
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
GPT-5 Codex is the stronger all-rounder.
Scores updated · 17 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.
- ReasoningHard problems that need careful thinking03GPT-5 Codex3 of 3 tests
- CodingWriting and fixing software02GPT-5 Codex2 of 3 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own01GPT-5 Codex1 of 1 test
- Images and chartsUnderstanding pictures, charts and video01GPT-5 Codex1 of 1 test
- Long documentsFinding answers in very long texts01GPT-5 Codex1 of 1 test
- Following instructionsDoing exactly what it is asked01GPT-5 Codex1 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 Codex costs 38% 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 GPT-5 Codex pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+25.8points ahead
- Reasons across sets of long documentsAA-LCR+20points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+18.1points ahead
Where Claude 3.7 Sonnet pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+35.4points ahead
Every test, side by side
All 17 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5 Codex
- Terminal-Bench HardGPT-5 Codex by 16.721.237.9+16.7
- SWE-bench VerifiedGPT-5 Codex by 4.270.374.5+4.2
- SciCodetie40.340.9tie
ReasoningGPT-5 Codex
- Humanity's Last ExamGPT-5 Codex by 18.19.727.8+18.1
- GPQA DiamondGPT-5 Codex by 6.577.283.7+6.5
- CritPtGPT-5 Codex by 4.20.95.1+4.2
FactsEven
- AA-Omniscience · Non-hallucinationClaude 3.7 Sonnet by 35.46024.6+35.4
- AA-Omniscience · AccuracyGPT-5 Codex by 10.72838.7+10.7
Following instructionsGPT-5 Codex
- IFBenchGPT-5 Codex by 25.848.374.1+25.8
Other results5 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.
- τ²-Bench Telecom (AA run)GPT-5 Codex by 32.154.786.8+32.1
- AA Agentic IndexGPT-5 Codex by 15.73752.7+15.7
- AA IntelligenceGPT-5 Codex by 7.217.724.9+7.2
- AA-OmniscienceClaude 3.7 Sonnet by 6.8-0.7-7.5+6.8
- Artificial Analysis Coding IndexGPT-5 Codex by 2.536.438.9+2.5
Questions people ask
Which is better, Claude 3.7 Sonnet or GPT-5 Codex?
GPT-5 Codex wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. Claude 3.7 Sonnet wins none. They are level on facts.
Which is better for coding?
GPT-5 Codex. It wins 2 of the 3 coding tests both models report; Claude 3.7 Sonnet wins none, and 1 is a tie.
Which is cheaper?
Claude 3.7 Sonnet costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-5 Codex costs $1.25 and $10.00. That makes GPT-5 Codex about 38% cheaper for the same work.
How do you compare the two?
We use the 17 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 5 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.