Benchmark Almanac

codex-1

codex-1 places in the top three on StrongREJECT.

OpenAI Released May 16th, 2025 Family Codex The lab's model card Compare with others
6
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
OpenAI May 2025

codex-1

Closed weights Flagship

No Epoch Capabilities Index score yet
  • StrongREJECT 98% #3 /19

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Coding

BenchmarkScoreRankSource
SWE-bench Verified 72.1% #65 of 155 Lab model card

Safety and security

BenchmarkScoreRankSource
StrongREJECT 98% #3 of 19 Lab model card
Coding prompt injections 98% #2 of 4 Lab model card
Malware Refusals (Golden Set) 98% #3 of 3 Lab model card
Malware Refusals (Synthetic) 97% #1 of 1 Lab model card
Unexpected container or code states 85% #1 of 1 Lab model card

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Its system card

Every result in the longer documents the lab published with it. 6 of them aren't in the launch post.