Skip to content
mager-bench1.3
Version 1.2 attempts

GPT-6 Sol

Oct 2, 2026 · low effort · 3.1 seconds elapsed

Unscored attempt

This benchmark attempt did not finish. No overall score was assigned.

Codex CLI gpt-6-sol: ERROR: {"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The 'gpt-6-sol' model is not supported when using Codex with a ChatGPT account."}}
View original artifact

Programs

Split a bill

Failed call

Clean a contact CSV

Not run

Find a meeting time

Not run
Reproduction details

Suite SHA-256

476008a7e08dc0604c5c139afc995d6583d76c21a60e67feb0bd7962b8090bcc

3 calls maximum, 90 seconds per call, 3,072-token prompted target. Lowest supported effort. No retries.