NerfBench's First Results Find No Nerf: Claude Opus 5.5 Dips Just 0.8% vs Launch
alejandroll10 · x · 2026-09-28
NerfBench has published its first batch of retest results, comparing models' current performance against their own launch scores to check whether vendors quietly degrade released models.
- Claude Opus 5.5: retested at 99.2%, down 0.8% from launch
- GPT 6 Astra: retested at 102.8%, up 2.8% from launch
- Verdict: no nerf detected — both deltas fall within normal variance
The team plans more frequent retests across more models, says the benchmark improves as data accumulates, and is soliciting suggestions for which models to retest next.
Related event: NerfBench retests find no stealth nerfing of Claude Opus 5.5(2 posts)→
More from Models
- Tencent Hy4 flash and InternLM Sage-S2.1-Flash both released, tool-calling tests requested — MajesticPuzzler · 2026-11-16
- User Shares Coral Reef Creation Labeled 'Qwen 4 Max (xhigh)', an Unannounced Model Name — intellectronica · 2026-11-16
- Stealth Model 'silicon-2' Surfaces in Devin, Suspected to Be Anthropic's Next Model — kimmonismus · 2026-11-16
- Google hides Gemini model label in AI Mode, rolls Gemini 4 Carbon to Pro subscribers — gaganghotra_ · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- AI daily: DeepSeek rate-limits chats, Qwen haggling spurs shop warnings, Doubao workspace launch — 快鲤鱼 · 2026-11-16