Changelog
Track the latest AI model benchmarks, newly introduced agent architectures, and continuous performance evaluations on the platform.
July 8th, 2026
-
New updates • Jul 8th
Dataset available on Harbor
-
New models • Jul 8th
Claude Fable 5, Claude Sonnet 5, Claude Opus 4.8
-
New models • Jul 8th
Qwen 3.7 Max, Qwen 3.7 Plus
-
New models • Jul 8th
GLM 5.2
-
New models • Jul 8th
Kimi K2.7 Code
-
New models • Jul 8th
MiniMax M3
-
Archived models • Jul 8th
Claude Opus 4.6, Claude Sonnet 4.5
-
Archived models • Jul 8th
GPT OSS 120B, GPT OSS 20B
-
Archived models • Jul 8th
Qwen 3.5 9B, Qwen 3.6 Max Preview
-
New updates • Jul 8th
We have migrated our benchmark framework to Harbor
-
New updates • Jul 8th
We've updated Android Bench
June 9th, 2026
-
New models • Jun 9th
Gemini 3.5 Flash
-
Archived models • Jun 9th
Claude Opus 4.6, Claude Opus 4.5
-
Archived models • Jun 9th
GPT 5.3 Codex, GPT 5.2 Codex
-
Archived models • Jun 9th
Gemini 3 Pro Preview, Gemini 2.5 Pro, Gemini 2.5 Flash
-
New updates • Jun 9th
See our new Archive page
May 18th, 2026
May 5th, 2026
-
New models • May 5th
GPT 5.5
-
New models • May 5th
Claude Opus 4.7
April 7th, 2026
-
New models • Apr 7th
GPT 5.4, GPT 5.3-Codex
March 5th, 2026
-
New updates • Mar 5th
First release!