Benchgen

GDPVal-AA v2 — Results

RankModelScore
1claude-fable-5-11853
2claude-opus-5-51846
3claude-sonnet-5-51844
4glm-5-3-flash1773
5glm-5-31769
6claude-fable-51760
7grok-4-61753
8gpt-5-6-sol1748
9nex-n2-5-max1713
10grok-4-71695
11kimi-k31686
12hy4-preview1678
13mimo-v2-6-pro-rl1673
14muse-spark-1-21631
15nex-n2-5-pro1628
16glm-5-21514
17k2-horizon-375b-a23b1441
18deepseek-v4-pro1307
19solar-pro-41276
20inkling1238
21granite-4-2-30b1225
22kimi-k2-61190
23granite-4-2-8b1189
24nemotron-3-ultra-550b-a55b1164
25kimi-k2-51009

GDPVal-AA v2 — Leaderboard

1 phaseActive

GDPVal-AA v2 Leaderboard

No self-reported entries.