Benchgen

CharXiv Reasoning — Results

RankModelScore
1kimi-k391.3
2qwen3-8-flash-next90.6
3qwen3-8-27b90.2
4fugu-ultra86.6
5fugu85.1
6minimax-m3-1-flash82.5
7inkling82
8muse-glimmer78.8
9kimi-k30.913
10claude-opus-4-70.91
11claude-opus-4-80.899
12muse-spark0.884
13claude-sonnet-50.883
14kimi-k2-60.867
15seed-2-1-pro0.864
16qwen3-7-plus0.859
17seed-2-1-turbo0.836
18gpt-5-20.821
19gpt-5-50.816
20qwen3-6-plus0.815
21gemini-3-pro0.814
22gpt-50.811
23gemini-3-flash0.803
24qwen3-5-27b0.795
25o30.786

CharXiv Reasoning — Leaderboard

1 phaseActive

CharXiv Reasoning Leaderboard

No self-reported entries.