Benchmark Almanac

Bobby Gray

We track 3 benchmarks that Bobby Gray made or helped make.

0 in use 3 with public code 3 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
Open Tabletop GM Narrative Quality Probe v2 Models narrate twelve tabletop scenes, including player failure, deception, and changes in tone. Five judges score each scene for atmosphere, character portrayal, and game management. Creative writing Apr 2026 4.88 Not in cards
Open Tabletop GM Session Command Probe Models handle five game master commands and conversational turns, including loading a campaign and rolling dice. Pattern checks classify each response. Multi-turn conversation Apr 2026 3.00 Not in cards
Open Tabletop GM Narrative Quality Probe Models narrate six scenes from the same tabletop campaign. GPT-OSS-20B rates atmosphere, nonplayer characters, and game management on a five-point scale. Creative writing Apr 2026 4.33 Not in cards