⌕Is ___ SOTA?
benchmarks / gdp-pdf

GDP.pdf

score. Status active. Contamination risk low. Maintainer Surge AI / Epoch collection. Source.

ModelScoreDateKind
Claude Fable 50.32026-06-09observation
GPT-5.50.262026-04-23observation
Claude Opus 4.80.242026-05-28observation
Claude Opus 4.70.212026-04-16observation
Gemini 3.1 Pro Preview0.172026-02-19observation
Gemini 3.5 Flash0.142026-05-19observation
Kimi K2 60.122026-04-20observation
Gemini 3 Flash Preview0.12025-12-17observation
Grok 4.30.082026-04-17observation
GPT-5.6 Sol0.3072026-07-09observation
Claude Fable 50.2982026-06-09observation
GPT-5.6 Terra0.2472026-07-09observation
Claude Opus 50.242026-07-24observation
GPT-5.6 Luna0.2272026-07-09observation
Kimi K30.192026-07-16observation
Claude Sonnet 4.60.182026-02-17observation
Muse Spark 1.10.152026-07-09observation
Gemini 3.6 Flash0.142026-07-21observation
Grok 4.50.142026-07-08observation
Gemini 3.5 Flash Lite0.12026-07-21observation
Grok 4.30.082026-04-17observation
GPT-5.6 Sol0.3072026-07-09observation
Gemini 3.6 Flash0.142026-07-21observation
Nova 2.0 Pro Preview0.022025-12-02observation
Muse Spark 1.20.162026-08-05observation
Muse Spark 1.20.122026-08-05observation
GPT-5.6 Terra0.2472026-07-09observation
Gemini 3.7 Flash0.238000000000000022026-08-13observation
Qwen3 8 Max0.231999999999999982026-08-02observation
GPT-5.6 Luna0.2272026-07-09observation