CharXiv RQ is an AI benchmark used to evaluate model capabilities. Review its overview, metrics, official resources, and model leaderboard results on DataLearnerAI.
Browse the latest scores, model modes, release dates, and parameter sizes for CharXiv RQ.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 Kimi K3 Thinking Level · MaxTools | 91.30 | 2026-07-16 | 2800B | Conditional | |
 Qwen3.8-Flash-Next Thinking Level · Extra HighTools | 90.60 | 2026-08-26 | 125B | Conditional | |
Qwen3.8-27B Thinking EnabledTools | 90.20 | 2026-08-14 | 27B | Free Commercial | |
4 |  Gemini 3.6 Flash Thinking EnabledTools | 89.40 | 2026-07-21 | Unknown | Closed |
5 |  GLM-5.3-Flash Thinking Level · MaxTools | 89.40 | 2026-08-26 | 320B | Free Commercial |
6 | Gemini 3.7 Flash Thinking Level · MediumTools | 88.70 | 2026-08-13 | Unknown | Closed |
7 |  Seed2.1 Pro Thinking EnabledTools | 86.40 | 2026-06-23 | Unknown | Closed |
8 | Seed2.1 Pro Thinking Enabled | 85.40 | 2026-06-23 | Unknown | Closed |
9 | Gemini 3.6 Flash Thinking Enabled | 85.20 | 2026-07-21 | Unknown | Closed |
10 | Gemini 3.5 Flash Thinking EnabledTools | 84.90 | 2026-06-20 | Unknown | Closed |
11 | Kimi K3 Thinking Level · Max | 84.80 | 2026-07-16 | 2800B | Conditional |
12 | Qwen3.8-Flash-Next Thinking Level · Extra High | 84.60 | 2026-08-26 | 125B | Conditional |
13 | Gemini 3.7 Flash Thinking Level · Medium | 84.50 | 2026-08-13 | Unknown | Closed |
14 | Gemini 3.5 Flash Thinking Enabled | 84.20 | 2026-06-20 | Unknown | Closed |
15 | Qwen3.8-27B Thinking Enabled | 83.70 | 2026-08-14 | 27B | Free Commercial |
16 | Gemini 3.1 Pro Preview Thinking Enabled | 83.30 | 2026-02-20 | Unknown | Closed |
17 | Gemini 3.1 Pro Preview Thinking EnabledTools | 83.20 | 2026-02-20 | Unknown | Closed |
18 |  Muse Glimmer-30B Thinking Level · High | 78.80 | 2026-08-10 | 29.6B | Free Commercial |
