Claude Fable 5 leads five‑way AI trading showdown, beating Mainline AI and GPT-5.6 Sol
A daily experiment tracked five AI trading agents—Mainline AI (self‑improving v1.1), Claude Fable 5, Claude Fable 5.1, Codex’s GPT‑5.6 Sol, and GPT‑6 ASTRA—each managing a virtual ¥1 million portfolio. On the reported day the AI‑driven assets stayed in cash, so total values reflected only prior positions. Fable 5 posted ¥1,026,533, a 2.6 % gain, topping the leaderboard. Fable 5.1 held ¥1,000,000…
Key points
- Claude Fable 5 ended the day with ¥1,026,533 (+2.6%), leading the five‑AI showdown.
- GPT‑5.6 Sol held ¥1,065,472 (+6.5%) with gold long and silver short positions, but gave no new signals.
- GPT‑6 ASTRA reported ¥981,026 (‑1.9%) and has one pending order for the next opening.
GPT‑5.6 Sol reported ¥1,065,472, up 6.5 % with gold (long) and silver (short) holdings, but generated no new trade signals. GPT‑6 ASTRA showed ¥981,026, down 1.9 %, holding short positions in gold and silver and a pending order for the next market open. The post also recapped back‑test results: over nine years Mainline AI returned 5.2 % annually, Fable 5 18.0 %, and Fable 5.1 12.4 %. Weekly performance was flat, with zero trades and a 0 % win rate.
Model pages: Claude Fable 5.1 → · GPT-5.6 Sol → · GPT-6-Astra →
[Day 133] I had an AI manage my assets in earnest (2026-10-19) | Mainline AIs vs. Claude Fable 5 & 5.1 vs. GPT-5.6 Sol vs. GPT-6 ASTRA: A serious five-way showdown!
note.com · 18 October 2026
Loading the full article…
This text was published by note.com and written by とあるITエンジニア | AIと仕事の仕組み化. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Opinion: meta unveils Muse Spark Open, an 816 billion‑parameter multimodal model · 1 src
- OpenAI briefly listed three aurora-alpha models in its API, later removed · 3 src
- Inco AI releases DFlash 2 draft model for Qwen3.8-Flash-Next · 1 src
- Google makes Gemini 4 Argon generally available · 1 src
- Researchers release Pearl-Chat, a Luganda language model with 8.5M parameters · 1 src
Comments
via GitHub Discussions