finding
active
finding:g3-f-score-std-4-026-on-median-5-250G3-F score std=4,026 on median 5,250
high variance in scores due to multiplicative scoring sensitivity
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.
- High score variance driven by deck order.
- median final score, slightly higher than TrackerAgent despite lower win rate
- Gemini 3 Flash never overbid
- G3-F TrueSkill μ=30.1 ± 3.3, 72.9% wins, median score 5,250 on combined-comp1 slice (n=98 canonical games)finding0.766Top LLM performance with high win rate and large score.
- high quartet completion rate
- performance in mixed games against three code agents
- Gemini 3 Flash won nearly 3/4 of its games
- High buy-right usage among LLMs.