Qwen 35B (3B active params, score 4.38) outscores Hermes 405B (405B active params, score 1.75) by 2.5x

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

• Qwen3-32B achieves a skill-load rate of 0.251, while Opus 4.6, Sonnet 4.6, and Qwen3-235B achieve SLR of 0.957–0.961finding0.805
  Quantifies harness activation failure for weak-tier models vs. strong-tier models
• Qwen3-235B has SLR of 0.961 (nearly identical to Opus 4.6) yet HFR of only 0.350, with LPR of 0.022 vs. Opus 4.6's 0.177finding0.795
  Demonstrates that harness loading is necessary but not sufficient for harness benefit; cleanest separation of activation and adherence
• Qwen-2.5-3B ASR drops from 98.6% at dim 1 to 45.1% at dim 2, recovering partially then declining to 65.3% at dim 5finding0.787
  Smaller models show non-monotonic and diminished ASR with increasing cone dimensionality
• On SWE-bench, harness-benefit peaks at Qwen3-235B (19.3 pp), while weaker Qwen3-32B gains only 4.4 pp and stronger Opus 4.6 gains only 2.6 ppfinding0.768
  Core finding demonstrating non-monotonic relationship between base capability and harness-benefit
• Qwen 2.5 7B wellbeing probe: peak Cohen's d=3.5finding0.765
  Strongest cross-family probe; explains clearer introspection in Qwen than Gemma
• Opus 4.6 achieves HFR of 0.757 while Qwen3-32B achieves HFR of only 0.142 on SkillsBenchfinding0.764
  Quantifies harness adherence failure gap between strong and weak tier models
• Qwen3.5-9Bconcept0.763
  Smallest model tested as evolver; produces harness updates comparable to Claude Opus 4.6 on SkillsBench
• Qwen3-235B achieves only 1.1 pp harness-benefit on SkillsBench despite 4.7% base pass rate, near Qwen3-32B's 0.0% baselinefinding0.757
  Shows that SB low-base regime is variable; similar starting points can yield very different harness-benefit