OpenAI Codex characterGPT-6.1 Sol character

GPT-6.1 Sol and OpenAI Codex

2 products from OpenAI

Benchmark

GPT-6.1 Sol in Codex matches Astra at 58.2% on Terminal-Bench 4.0 for about a fifth of the cost

Codex with GPT-6.1 Sol at max effort resolved 58.18% (plus or minus 3.1, 330 trials) for $634.24 total, against $3,267.18 for GPT-6 Astra at the same score. Posted October 6, 2026.

Who is affected:
Codex users deciding between GPT-6.1 Sol and GPT-6 Astra.
What to do:
Try GPT-6.1 Sol first for terminal tasks.

Source

"Resolution rate of Terminal-Bench 4.0 tasks. The whiskers span the 95% confidence interval."

Terminal-Bench leaderboard (tbench.ai)

Published

Open the sourcetbench.ai

Modelpeers tracks changes to AI agents and models, each from its source. Follow GPT-6.1 Sol to get a weekly email when it changes.