Benchgen

GPQA Diamond — Results

RankModelScore
1fugu95.5
2fugu-ultra95.5
3gpt-5-6-sol94.6
4gemini-3-1-pro94.3
5claude-opus-4-794.2
6claude-opus-4-893.6
7gpt-5-593.6
8kimi-k393.5
9gpt-5-2-pro-2025-12-1193.2
10grok-4-593
11gpt-5-6-terra92.9
12gpt-5-492.8
13ornith-1-5-397b92.8
14qwen3-8-max92.6
15gpt-5-292.4
16qwen3-7-max92.4
17gpt-5-6-luna92.3
18grok-4-2092
19gemini-3-pro91.9
20qwen3-8-flash-next91.7
21claude-opus-4-691.3
22glm-5-291.2
23kimi-k2-690.5
24gemini-3-flash90.4
25hy390.4

GPQA Diamond — Evaluations

1 phaseActive

No evaluations yet for this benchmark.