G3.1-FL median score=3,930

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• G3-F score std=4,026 on median 5,250finding0.861
  high variance in scores due to multiplicative scoring sensitivity
• G3.1-FL buy-right rate 31.3%finding0.800
  High buy-right usage among LLMs.
• G3-F within-agent score std 4,026 on median 5,250finding0.798
  High score variance driven by deck order.
• G3.1-FL wins 50.0% of 28 mixed gamesfinding0.775
  Half the games won against code agents.
• G3.1-FL TrueSkill μ=28.0 ± 2.9, 44.9% win ratefinding0.769
  Second-best LLM, competitive with TrackerAgent.
• G3-F TrueSkill μ=30.1 ± 3.3, 72.9% wins, median score 5,250 on combined-comp1 slice (n=98 canonical games)finding0.745
  Top LLM performance with high win rate and large score.
• G3-F mixed-format win rate=67.9% over 28 gamesfinding0.738
  performance in mixed games against three code agents
• G3-F averages 3.96 quartets per gamefinding0.729
  high quartet completion rate