SOURCE RECORD · obs_29dc8df78e2b…

Artificial Analysis · Industry data source update

Substantive changesRecordedObservation date 2026-09-25(day precision)Revision r2

This record is outside your history allowance. Register for 30 days or choose Plus for all available history.

Summary

Added evaluation for DeepSeek V4.1 Flash (Non-Reasoning) and GLM-5.3 (low), as well as Terminal-Bench-Science 0.1 benchmarks; the evaluation configuration for Claude Opus 5.5 has been adjusted from Max Effort to Xhigh Effort, indicating an expansion of evaluation coverage and configuration updates.

LLM generation

LLM The summary is machine-generated; please refer to the original text for important information.

Permanent link

https://daily.maas.click/item/obs_29dc8df78e2bed822a0e6e96446bb8d265ac1f82243afb4a3b718f4be2b181ae/

Source page

https://artificialanalysis.ai/ ↗

This link points to the source's official page (not content on this site).