Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback): benchmark results

Provider: Anthropic. Released 2026-06-09. Access: API.

Unified ELO 1751 ± 1, rank #27 of 1761 rated models, from 23 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA Omniscience - Business57.4Accuracy (%)100
AA Omniscience - Humanities & Social Sciences64.3Accuracy (%)99.8
AA Omniscience - Software Engineering (SWE)91.1Accuracy (%)99.8
AA Omniscience - Law66.2Accuracy (%)99.6
AA Omniscience - Science, Engineering & Mathematics61.28Accuracy (%)99.6
AA-Omniscience Accuracy65.35Accuracy (%)99.6
AA Humanity's Last Exam55.47Accuracy (%)99.5
AA Terminal-Bench Hard62.88Accuracy (%)99.5
Epoch AI - Scicode60.19Score99.4
AA Omniscience43.3Score99.2
AA Omniscience - Health53.72Accuracy (%)99.2
AA TAU-2 Bench98.54Accuracy (%)99

Interactive version: theaggregate.ai/model?slug=claude-fable-5-adaptive-reasoning-max-effort-opus-4-8-fallback · How It Works · Data refreshed daily, snapshot 2026-09-05.