HyperAI
Command Palette
Search for a command to run...
CritPt
一项基准,用于测试 LLM 在研究级物理推理任务上的表现,包含 71 个复合研究挑战。
- 模型
- 265 当前,600 总共
- 中位数
- 0.3%
- 范围
- 0.0%–35.7%
| 排名 | 比较 | 模型 | 评分 |
|---|---|---|---|
| 201 | Ling 3.0 Tiny InclusionAI | 0.0% | |
| 202 | 0.0% | ||
| 203 | 0.0% | ||
| 204 | 0.0% | ||
| 205 | 0.0% | ||
| 206 | Llama 4 Maverick Meta | 0.0% | |
| 207 | Llama 4 Scout Meta | 0.0% | |
| 208 | LongCat Flash Lite LongCat | 0.0% | |
| 209 | Mercury 2.5 Inception | 0.0% | |
| 210 | Mi:dm K 2.5 Pro Korea Telecom | 0.0% | |
| 211 | MiniCPM-V 4.6 1.3B OpenBMB | 0.0% | |
| 212 | MiniCPM5-1B (Reasoning) OpenBMB | 0.0% | |
| 213 | MiniCPM5-1B (Non-reasoning) OpenBMB | 0.0% | |
| 214 | Ministral 3 14B Mistral | 0.0% | |
| 215 | Ministral 3 3B Mistral | 0.0% | |
| 216 | Ministral 3 8B Mistral | 0.0% | |
| 217 | Mistral Medium 3.5 Mistral | 0.0% | |
| 218 | Molmo2-8B Allen Institute for AI | 0.0% | |
| 219 | Motif-2-12.7B-Reasoning Motif Technologies | 0.0% | |
| 220 | Nanbeige4.1-3B Nanbeige | 0.0% | |
| 221 | Nemotron 3.5 Lightning NVIDIA | 0.0% | |
| 222 | 0.0% | ||
| 223 | 0.0% | ||
| 224 | Nova 2.0 Lite (Low) Amazon | 0.0% | |
| 225 | Nova 2.0 Lite (Medium) Amazon | 0.0% | |
| 226 | 0.0% | ||
| 227 | Nova 2.0 Omni (Low) Amazon | 0.0% | |
| 228 | Nova 2.0 Omni (Medium) Amazon | 0.0% | |
| 229 | 0.0% | ||
| 230 | 0.0% | ||
| 231 | 0.0% | ||
| 232 | Nova Micro Amazon | 0.0% | |
| 233 | Nova Premier Amazon | 0.0% | |
| 234 | 0.0% | ||
| 235 | 0.0% | ||
| 236 | 0.0% | ||
| 237 | 0.0% | ||
| 238 | 0.0% | ||
| 239 | 0.0% | ||
| 240 | Olmo 3.1 32B Instruct Allen Institute for AI | 0.0% | |
| 241 | Olmo 3.1 32B Think Allen Institute for AI | 0.0% | |
| 242 | Olmo 3 7B Instruct Allen Institute for AI | 0.0% | |
| 243 | Olmo 3 7B Think Allen Institute for AI | 0.0% | |
| 244 | Phi-4 Microsoft | 0.0% | |
| 245 | Phi-4 Mini Instruct Microsoft | 0.0% | |
| 246 | Qwen3.5 0.8B (Reasoning) Alibaba | 0.0% | |
| 247 | Qwen3.5 0.8B (Non-reasoning) Alibaba | 0.0% | |
| 248 | Qwen3.5 2B (Reasoning) Alibaba | 0.0% | |
| 249 | Qwen3.5 2B (Non-reasoning) Alibaba | 0.0% | |
| 250 | Qwen3.5 4B (Reasoning) Alibaba | 0.0% |