Claude Opus 5 edges out Fable 5 overall, but Fable still leads coding-agent use
Hesamation · x · 2026-07-25
Claude Opus 5 tops Artificial Analysis, while Fable 5 remains the coding-agent leader
Artificial Analysis says Claude Opus 5 is now the narrow overall leader on its Intelligence Index, scoring 61 and effectively tying Claude Fable 5 (60) while beating GPT-5.6 Sol (59), Kimi K3 (57) and Claude Opus 4.8 (56).
Key points from the charts and quote:
- Opus 5 is described as having 26% lower Cost per Task than Fable 5.
- It posts the highest reported scores on GDPval-AA v2 and AA-Briefcase so far.
- On the Coding Agent Index, Claude Code + Opus 5 (high) ties for the lead at 67 with Codex + GPT-5.5 Sol (max).
- Claude Code + Fable 5 (max) follows at 66, ahead of Grok Build + Grok 4.5 (high) at 64 and several Codex / Kimi / OpenCode setups.
The takeaway is a split picture: Opus 5 looks strongest on general intelligence and knowledge-work benchmarks, while Fable 5 still remains highly competitive in coding-agent workflows.
Related event: Claude Opus 5 Surfaces: Tops Multiple Leaderboards as New SOTA(6 posts)→
More from coding & agent
- Chaining dependent MCP tool calls: no rollback, duplicate risk — agentrsdg · 2026-09-11
- DeepMind-led paper makes design docs the source of truth, code disposable — SMART regenerates in 1.5-3h for ~$100 — Roger_M_Taylor · 2026-09-11
- Agent-built classifier labels 192k docs for $0.70 vs $13-26 with frontier LLMs — vanstriendaniel · 2026-09-11
- MathModelAgent gains traction: auto-solves math modeling and writes a submission-ready paper — jihe520 · 2026-09-11
- alphaXiv open-sources OpenResearch to run parallel research agents with any model — alphaXiv · 2026-09-11
- DeskcommCRM: open-source AI sales CRM with native agents and WhatsApp hits 1k stars — melgarafael · 2026-09-11