Benchmark menu

Model detail

GPT-5.6 Sol

A static, shareable model page that remains complete without JavaScript.

Model detail

GPT-5.6 Sol

Provider: OpenAI · Public slug: gpt-5-6-sol

Compare in Charts View game entrants Leaderboard

Rank: 3
Rank movement: Baseline
Score: 54.5
Last measured: 2026-07-13
Coverage: Complete coverage

Reasoning scores

XHigh: 72.4
Medium: 53.9
None: 37.2

Generation health

XHigh100%0%0%n 8Medium78%11%11%n 9None89%0%11%n 9 Complete coverage

Cost summary

Mean standard list-price equivalent: $3.55
Median unique-cell cost: $0.44
Unique-cell range: $0.09–$12.92
Coverage: 24 unique cells / 26 observed runs
Observed-run total: $85.66
Evidence basis: Standard list-price estimate
Mean output: 108k tok
Output range: 1.8k–429k tok
Token samples: 26

Cost means equal-weight unique model/game/reasoning cells. Provider-account billed spend is reported separately on Charts.

Run setup

Overall Models: combines public reasoning variants
Standard GameBench code-generation prompt