Qwen3-235B achieves only 1.1 pp harness-benefit on SkillsBench despite 4.7% base pass rate, near Qwen3-32B's 0.0% baseline

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

• Qwen3.5-9B evolver achieves highest harness-updating gain on SkillsBench (3.8 pp), exceeding Claude Opus 4.6 (2.3 pp) and Qwen3-235B (1.5 pp)finding0.862
  Case demonstrating that model scale does not predict harness-updating quality
• 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 ppfinding0.856
  Core finding demonstrating non-monotonic relationship between base capability and harness-benefit
• Qwen3-235B leads as evolver on SWE-bench with 8.2 pp harness-updating gain but ranks last on MCP with 0.6 ppfinding0.813
  Illustrates benchmark-dependent reshuffling of evolver rankings, no evolver dominates across all substrates
• Qwen3-32B achieves a skill-load rate of 0.251, while Opus 4.6, Sonnet 4.6, and Qwen3-235B achieve SLR of 0.957–0.961finding0.811
  Quantifies harness activation failure for weak-tier models vs. strong-tier models
• Haiku 4.5 achieves the largest harness-benefit on SkillsBench (15.1 pp) despite mid-tier base capability of 5.8%finding0.811
  Shows SB low-base regime is more variable than SWE; Haiku benefits far more than Qwen3-235B despite similar base rates
• Opus 4.6 achieves HFR of 0.757 while Qwen3-32B achieves HFR of only 0.142 on SkillsBenchfinding0.794
  Quantifies harness adherence failure gap between strong and weak tier models
• Qwen3-32B adherence drops from 0.52 after harness loading to 0.13 at final validation (drift of -0.39)finding0.779
  Demonstrates long-horizon instruction-following bottleneck for weak-tier models
• Qwen 35B (3B active params, score 4.38) outscores Hermes 405B (405B active params, score 1.75) by 2.5xfinding0.757
  Parameters don't predict scores; 135x more parameters yields 60% lower score