Benchgen

CharXiv Reasoning (No Tools) — Results

RankModelScore
1claude-fable-586.5
2kimi-k384.8
3gpt-5-6-sol84.7
4kimi-k2-680.4
5gemini-3-1-pro80.2
6inkling78.1
7kimi-k2-577.5

CharXiv Reasoning (No Tools) — Leaderboard

1 phaseActive

CharXiv Reasoning (No Tools) Leaderboard

No self-reported entries.