Qwen3-235B

One of the four frontier models evaluated; shows the largest robustness drop (-88%) and sigma surge (+744%)

Neighborhood — ranked by edge-count

paper

concept

Qwen3-1.7B
related_to
Smallest Qwen3 model tested; used in conscientiousness sweep example (Table 6)
Qwen3.5-9B
related_to
Smallest model tested as evolver; produces harness updates comparable to Claude Opus 4.6 on SkillsBench
Qwen3-4B
related_to
4B Qwen3 model tested in OCEAN benchmarks
Qwen3-32B
related_to
Weak-tier open-source model exhibiting both harness activation failure and adherence failure, with 25.1% skill-load rate
Qwen3-14B
related_to
14B Qwen3 model quantized to 4-bit NF4; tested in OCEAN benchmarks
Qwen3-235B-A22B
related_to
Large open-source model used as anchor agent and anchor evolver; illustrates benchmark-dependent evolver performance

cosine ≥ 0.65 · no typed edge

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

Qwen 2.5 7Bconcept0.813
Open-weights LLM used as one of three student models for character training experiments
Qwen2.5-VL-7Bconcept0.812
Base vision-language model used to instantiate ATLAS.
Qwen 3 0.6B Embeddingmethod0.788
Embedding model used to embed user messages for ridge regression analysis of persona drift causes
Qwen3-30B-A3B-Instructconcept0.762
Extended evaluation MoE model showing distributed persona localization across multiple layers
Qwen 35B (3B active params, score 4.38) outscores Hermes 405B (405B active params, score 1.75) by 2.5xfinding0.733
Parameters don't predict scores; 135x more parameters yields 60% lower score
Qwen3-235B achieves only 1.1 pp harness-benefit on SkillsBench despite 4.7% base pass rate, near Qwen3-32B's 0.0% baselinefinding0.728
Shows that SB low-base regime is variable; similar starting points can yield very different harness-benefit
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 0.177finding0.721
Demonstrates that harness loading is necessary but not sufficient for harness benefit; cleanest separation of activation and adherence
Qwen3.5-27B shows mean AS ASR of only 0.035 [0.03, 0.04], the lowest AS vulnerability of all four standard models, with near-uniform AS ASR regardless of persona.finding0.718
Vulnerability profile for Qwen3.5-27B showing near-zero AS vulnerability