Artificial Analysis Releases Endpoint Accuracy Index v1.1 with Expanded Model Coverage

1 reports 1 reporting sources Updated 22 minutes ago

Understand the event

AI overview

Artificial Analysis released Endpoint Accuracy Index v1.1, adding GLM-5.3 Flash and Meta’s Muse Spark Open to a benchmark covering more than 100 serverless endpoints. The update revises AA-LCR grading and raises the number of repeats from 10 to 25, reducing the average 95% confidence interval from ±4.7 to ±2.6 points. On HLE-250, two GLM-5.3 Flash endpoints capped at about 32K output tokens scored 22% and 29%; the reference scored 55%.

Generated by AI from reports · Updated 16 minutes ago

Latest development11/6 10:44 (UTC+8)

Artificial Analysis Updates Endpoint Accuracy Index to v1.1 Artificial Analysis · X

Models in this story

GLM-5.3 Flash#28 overall$0.15 input / $0.5 output per million tokens

API prices of all models

Report timeline

Follow the reports to explore different sides of the event.

11/6

10:44
Artificial Analysis · X
Artificial Analysis Updates Endpoint Accuracy Index to v1.1
Artificial Analysis released Endpoint Accuracy Index v1.1, expanding coverage to GLM-5.3 Flash and Meta’s Muse Spark Open across a benchmark of more than 100 serverless endpoints. The update revises AA-LCR grading and increases repeats from 10 to 25, reducing the average 95% confidence interval from ±4.7 to ±2.6 points. For GLM-5.3 Flash, two endpoints capped at about 32K output tokens score 22% and 29% on HLE-250, compared with 55% for the reference.

Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue

Event heat trend

There is not enough continuous observation data to plot a trend yet.