Hardest composition for LLMs: two TrackerAgents (C2, C7), only G3-F still wins majority

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

• TrackerAgent outperforms six of seven tested LLMsfinding0.791
  In the 98-game slice, TrackerAgent had a higher win rate or TrueSkill than all LLMs except Gemini 3 Flash.
• Li et al. 2024: larger LLMs outperform smaller ones at distinguishing self-related from non-self-related properties on self-awareness benchmarksfinding0.762
  Prior finding showing scale-dependent self-awareness, consistent with the scale effect observed in the paper's Experiment 1
• All cases satisfying Criteria 1 and 2 (two out of three) originate from deeper transformer layers and/or the 2/3 layer of LLMs.finding0.745
  Consistent with literature that deeper layers encode semantic information and align with human brain activity.
• Two heuristic code agents (TrackerAgent and SetRaceAgent) outperform most tested LLMs.claim0.744
  Calibration that conditional logic can beat cost-efficient LLMs in this setting.
• Two heuristic code agents outperform most tested LLMs, and behavioural traces surface recurring LLM failure modes including overbidding, self-bidding, bankrupt TC initiation, and weak opponent-state adaptation.quote0.737
  Abstract sentence summarising performance and failures.
• Card-counting heuristics suffice to outperform most LLMs tested.claim0.736
  TrackerAgent's second-place ranking calibrates the benchmark and highlights LLM shortcomings.
• SetRaceAgent outperforms five of seven tested LLMsfinding0.733
  SetRaceAgent ranked above DS-v3.2, GPT5.4-N, Haiku, G2.5-FL, and EconomyAgent.
• The difficulty boundary for truth directions replicates across all four tested models (Llama-3.2-3B, Llama-3.1-8B, Gemma-2-2b, Gemma-2-9b); generalization to F3-F5 remains consistently low regardless of model size or family.finding0.726
  Establishes generalizability of the core difficulty-boundary finding across model families.