Benchgen

GDPVal-AA v2 — Results

RankModelScore
1claude-fable-5-11853
2claude-opus-5-51846
3glm-5-3-flash1773
4glm-5-31769
5claude-fable-51760
6grok-4-61753
7gpt-5-6-sol1748
8nex-n2-5-max1713
9grok-4-71695
10kimi-k31686
11hy4-preview1678
12muse-spark-1-21631
13nex-n2-5-pro1628
14glm-5-21514
15k2-horizon-375b-a23b1441
16deepseek-v4-pro1307
17solar-pro-41276
18inkling1238
19granite-4-2-30b1225
20kimi-k2-61190
21granite-4-2-8b1189
22nemotron-3-ultra-550b-a55b1164
23kimi-k2-51009
24gemini-3-1-pro962
25muse-glimmer953

GDPVal-AA v2 — Evaluations

1 phaseActive

No evaluations yet for this benchmark.