Retired benchmark. These historical results are preserved for inspection and excluded from active-suite run counts. Browse the archive →
Focused model compare
Jabberwock
DeepSeek V4.1 Flash is the starting run, compared with GPT-6 Astra, Claude Fable 5.1, Kimi K3.
Starting model
DeepSeek V4.1 Flash
OpenAI
GPT-6 Astra
Anthropic
Claude Fable 5.1
Moonshot AI