gpt-6VIDEO
NerfBench: Opus 5.5 and GPT-6 Astra both hold launch-level capability
The latest NerfBench results show Claude Opus 5.5 at 103.8% and GPT-6 Astra at 101.1% of their launch power, and GPT-6.1 Sol has been added with a day-one baseline.
Bridgebench
@bridgebenchArchived 2026.10.02Originally posted 2026.10.02
Bridgebench @bridgebenchOriginally posted 2026.10.02
Claude Opus 5.5 and GPT 6 Astra are not nerfed. Latest NerfBench results: Claude Opus 5.5: 103.8% of launch power GPT-6 Astra: 101.1% of launch power Both are within normal variance (90% to 110%). We also just added GPT 6.1 Sol. Day one baseline is locked in. Now we watch. Which model should we add next?
x.com/bridgebench/status/2105703626681278926Archived 2026.10.02 10:05