Claude Opus 5 appears to beat Fable 5 on most benchmarks at half the price
Yuchenj_UW · x · 2026-07-25
Claude Opus 5 claims strong benchmark gains at half the price
The post says Opus 5 beats Fable 5 on nearly every benchmark and looks like a major jump in coding and agentic capability, with better token efficiency.
The attached benchmark chart shows Opus 5 leading or remaining highly competitive on:
- Agentic terminal coding: 43.3%
- Knowledge work: 1861
- ARC-AGI-3: 30.2%
- Agentic search: 90.8%
- Computer use: 70.6%
- Business workflows: 26.0%
- Biology: 49.4% hard / 90.1% human solved
The author’s key takeaway is that the model appears significantly better for coding and agentic work while costing half the price of Fable 5.
Related event: Anthropic Releases Claude Opus 5: SOTA Performance at Half the Price(128 posts)→
More from Models
- MissionReport benchmark: only 3 of 540 AI-generated government reports pass all criteria — Exp_Mark · 2026-10-27
- Local beats cloud: Qwen 3.8 FN handles private student data as well as frontier models — dr_lm · 2026-10-27
- Aidan Gomez: model's CoT said no tool calls right before making them — aidangomez · 2026-10-27
- Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
- OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27