Independent Benchmark Puts Claude Opus 5 Narrowly Ahead of Fable 5, at 26% Lower Cost
Artificial Analysis, which helped Anthropic evaluate the model pre-release, scored Claude Opus 5 at 61 on its Intelligence Index versus Fable 5's 60, while pricing it well below Anthropic's flagship. The same testing found Opus 5's hallucination rate rose sharply.
A day after Anthropic launched Claude Opus 5 at half the price of Fable 5, independent evaluator Artificial Analysis published third-party benchmark numbers placing it as the top-ranked model on its Intelligence Index, edging out Fable 5 itself.
- Intelligence Index (max effort): Opus 5 scores 61, versus Fable 5 at 60, GPT-5.6 Sol at 59, Kimi K3 at 57, and Opus 4.8 at 56
- Cost per Intelligence Index task: $2.03 for Opus 5 versus $2.75 for Fable 5, a 26% reduction
- GDPval-AA v2 (agentic knowledge work): Opus 5 hits 1861 Elo, over 100 points ahead of Fable 5 and GPT-5.6 Sol
- AA-Briefcase: 1720 Elo, a 146-point lead over Fable 5
- AA-Omniscience hallucination rate climbed 14 points to 50%, even as factual accuracy improved 7 points over Opus 4.8
Claude Opus 5 is narrowly the most intelligent model on the Artificial Analysis Intelligence Index, offering comparable intelligence to Fable 5 at 26% lower Cost per Task - Artificial Analysis
Anthropic said it worked with Artificial Analysis to evaluate Opus 5 ahead of release. Pricing stays at Opus 4.8's $5/$25 per million input/output tokens, undercutting Fable 5 while Anthropic prepares for a reported IPO later this year. On raw coding, Opus 5 posts 89% on Terminal-Bench v2.1 at max effort, comparable to GPT-5.6 Sol at xhigh effort, and takes joint first on Artificial Analysis's Coding Agent Index.