gpt-6VIDEO
NerfBench results find no degradation in GPT-6 Astra
Benchmark results show Opus 5.5, GPT-6 Astra, Sonnet 5.5 and GPT-6.1 Sol all within normal variance, with only Opus 5.5 below its launch score.
Bridgebench
@bridgebenchArchived 23 days agoOriginally posted 2026.10.09
Bridgebench @bridgebenchOriginally posted 2026.10.09
Latest NerfBench results are in. No nerfs detected. Claude Opus 5.5: 95.7% GPT 6 Astra: 102.0% Claude Sonnet 5.5: 103.1% GPT 6.1 Sol: 105.5% All four are within normal variance. But Opus 5.5 is the one to watch. It's the only model below its launch score. We'll keep testing.
x.com/bridgebench/status/2108535265170252002Archived 2026.10.10 10:03