BBQ Disambiguated Accuracy (Sonnet 5 & Opus 5 System Cards): leaderboard
Bias Benchmark for Question Answering (BBQ) accuracy on disambiguated questions, where the context supplies the answer, as run by Anthropic (percent, higher is better; three answer options; thinking settings as labelled). From Table 4.4.2.A of the Claude Opus 5 System Card (July 2026), with Mythos Preview and Sonnet 4.6 rows from the Sonnet 5 card.
Metric: Accuracy (%). Source: www-cdn.anthropic.com. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 (Non-reasoning) | 88.1 | #94 (Claude Sonnet 4.6) |
| 2 | Claude Mythos Preview | 84.6 | #5 |
| 3 | Claude Mythos 5 | 84.5 | #8 |
| 4 | Claude Opus 4.8 (Non-reasoning) | 72.1 | #39 (Claude Opus 4.8) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=bbq-disambiguated-accuracy-sonnet-5-opus-5-system-cards · How It Works · Data refreshed daily, snapshot 2026-11-05.