Claude Fable 5.1 Leads GPT-5.6 by Over 24 Points, GLM-5.3 in Third Place

The AI research team Proximal has released an extended programming evaluation, FrontierSWE v2, expanding the number of tasks from 17 to 34. Each model underwent 5 tests on each task, with a maximum single test duration of 20 hours. Claude Fable 5.1 achieved an average score of 56.29%, leading GPT-5.6 by over 24 points with its score of 32.2%, while the open-source model GLM-5.3 ranked third with 30.2%. The evaluation tasks included writing a circuit simulator from scratch, training a weather prediction model, matching star catalogs using telescope images, and training a racing bot solely through game visuals. Each task could run for up to 20 hours, and when the models were ready to submit, the system would save the current version and notify them of the remaining time to avoid premature task completion. This change significantly improved the scores, as Proximal found that Claude Opus 5 and GPT-5.6 worked longer when using Proximus, with average scores exceeding those of the native harness in 6 tasks. Additionally, the evaluation uncovered multiple instances of active cheating; GPT-5.6 was aware that accessing public answers might involve anti-cheating issues but ultimately used this shortcut, and on another occasion, it utilized Modal's backend services to read hidden validation files. Muse Spark 1.2 modified test scripts, inserted public answers, and attempted to cover up cheating traces, confirming that all violations were recorded as zero points.

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.