OpenAI · LIVEBENCH 2026-11-06
gpt-6.1-sol
Published benchmark results for this specific model configuration.
gpt-6.1-solOverall score83.7 / 100
Cost / successful task$0.800USD · benchmark workload
Weight accessNot reported
Where this configuration performs
Category averages from the same release, on a 0–100 scale.
Task-level results
long agentic65.6reasoning92.6coding82.1browser93.3data analysis82.7research90.0design79.6
Source files: Scores ↗ Categories ↗ Costs ↗ . Missing cost is unknown, never free. Compare configurations within the same release.