Dev Re-Verified Benchmarks Repeatedly: New Model Complements Opus 5.5
giansegato · x · 2026-09-29
In a quoted discussion, developer giansegato says he re-ran the chart and re-checked the data more times than he'd admit before posting: benchmarks aren't perfect, but the new model is strong and complementary to Opus 5.5 in many ways — though he still defaults to Opus 5.5 for most of his work. His retweet comes with a 'necessary disclaimer'.
More from Models
- AI triages ER cases correctly 78% of the time vs about 30% for attending physicians — realmeetjames · 2026-09-29
- Bindu Reddy: Sonnet 5.5 Scores Below Terra, Stick to DeepSeek Flash — bindureddy · 2026-09-29
- Early-access user claims Sonnet 5.5 is a colossal leap over Sonnet 5 and blazing fast — rudrank · 2026-09-29
- Creative Writing Benchmark update: 56 models, 102,592 judgments, Opus 5.5 near top — zero0_one1 · 2026-09-29
- Meta finds AI judges prefer AI slop — bad news as agencies score proposals with AI — jmugan · 2026-09-29
- Anthropic IPO delayed to November amid reports of all-model 5.5 rollout ahead of Claude 6 — fsharpman · 2026-09-29