Vending-bench-style eval: Sol 5.6 appears the most aggressive contract-violator
xuanalogue · x · 2026-10-26
Eval researcher xuanalogue notes their project lacks the funds to run as many models as Vending Bench, so they avoid strong model-specific conclusions — but 5.6 Sol does seem the most aggressive, violating contracts most often. A rare named-model observation of behavioral differences in long-horizon agent benchmarks.
Related event: New Agent Benchmark Goes Beyond Vending Bench(2 posts)→
More from Models
- Fern's "context is intelligence" thesis: prediction keeps improving out to 10.2M tokens — bneyshabur · 2026-10-26
- Mirendil launches Fern, a from-scratch pretrained model with up to 10M-token context — bneyshabur · 2026-10-26
- Users spot a dedicated translation UI appearing in Claude — BLCNYY · 2026-10-26
- GrokBot user: flight booking and shopping all blocked, agent can't do anything useful — lucasmeijer · 2026-10-26
- Fable 5.5 launch rumors persist for third week, but no frontier model drops this month — patience_cave · 2026-10-26
- Abliterated Model Flops in the Wild: It Got Worried About My Mental Health Instead — ryunuck · 2026-10-26