finding
active
finding:g3-f-win-rate-72-9-in-98-canonical-gamesG3-F win rate=72.9% in 98 canonical games
Gemini 3 Flash won nearly 3/4 of its games
Source paper
extracted_from(2026) · Robert Müller · Clemens Müller
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- performance in mixed games against three code agents
- Robust performance against algorithmic baselines.
- G3-F TrueSkill μ=30.1 ± 3.3, 72.9% wins, median score 5,250 on combined-comp1 slice (n=98 canonical games)finding0.814Top LLM performance with high win rate and large score.
- Half the games won against code agents.
- G3-F achieved a win rate of 72.9% in the combined-comp1 98-game slice.
- TrackerAgent won over half of the combined-comp1 games.
- high quartet completion rate
- Gemini 3 Flash never overbid