Benchgen

GDPVal-AA v2 — Results

RankModelScore
1claude-fable-5-11853
2claude-opus-5-51846
3kimi-k3-1-pro1846
4claude-sonnet-5-51844
5glm-5-3-flash1773
6glm-5-31769
7claude-fable-51760
8grok-4-61753
9gpt-5-6-sol1748
10nex-n2-5-max1713
11grok-4-71695
12kimi-k31686
13hy4-preview1678
14mimo-v2-6-pro-rl1673
15muse-spark-1-21631
16nex-n2-5-pro1628
17glm-5-21514
18k2-horizon-375b-a23b1441
19muse-spark-open-816b-a42b1401
20deepseek-v4-pro1307
21solar-pro-41276
22inkling1238
23granite-4-2-30b1225
24kimi-k2-61190
25granite-4-2-8b1189

GDPVal-AA v2 — Leaderboard

1 phaseActive

GDPVal-AA v2 Leaderboard

No self-reported entries.