OpenAI · LIVEBENCH 2026-06-25

GPT-6.1 Sol xHigh Effort

Published benchmark results for this specific model configuration.

gpt-6.1-sol-xhigh

Overall score81.1 / 100

Cost / successful task$0.093USD · benchmark workload

Weight accessNot reported

Where this configuration performs

Category averages from the same release, on a 0–100 scale.

Reasoning91.6

Coding80.7

Agentic Coding56.8

Mathematics96.5

Data Analysis82.2

Language88.6

Instruction Following71.3

Task-level results

theory of mind86.5zebra puzzle100.0spatial98.0logic with navigation82.0code generation78.9code completion82.6javascript63.6typescript46.7python60.0AMPS Hard98.0integrals with game99.0math comp97.1olympiad91.9consecutive events91.3tablejoin55.3tablereformat100.0connections100.0plot unscrambling81.9typos84.0paraphrase71.0simplify68.2story generation70.6summarize75.5

Source files: Scores ↗ Categories ↗ Costs ↗ . Missing cost is unknown, never free. Compare configurations within the same release.