New Finance Agent Benchmark Released
openai/gpt-5-codex GPT 5 Codex

A version of GPT-5 optimized for agentic coding tasks.

Released Date: 9/23/2025

Avg. Accuracy:

55.7%

Latency:

686.59s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

LiveCodeBench

84.7%

( 2 / 57 )

IOI

9.8%

( 6 / 17 )

Terminal-Bench

58.8%

( 1 / 17 )

SWE-bench

69.4%

( 1 / 19 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$1.25 / M Tokens

Output Cost

$10.00 / M Tokens

Input Cost (per char)

$0.85 / M chars

Output Cost (per char)

N/A

Join our mailing list to receive benchmark updates on

Stay up to date as new benchmarks and models are released.