CritPt

Unpublished research-level physics problems.

CategoryReasoning
MetricAccuracy
SourceEpoch AI (evaluator)
LicenseCC BY 4.0
Benchmark pagecritpt.com
StatusScored
Weight1.0 within Reasoning
FitDiscrimination 1.49, noise 0.57

Results

#ModelProviderResultDate
1 Gemini 4 Carbon High Google 36.0% 2026-11-11
2 Claude Fable 5.2 Extra High Anthropic 35.7% 2026-11-11
3 Claude Fable 5.2 Max Anthropic 35.4% 2026-11-11
4 Claude Fable 5.2 High Anthropic 32.9% 2026-11-11
5 GPT-5.6 Sol Max OpenAI 32.3% 2026-11-11
6 GPT-6.1 Sol Max OpenAI 31.7% 2026-11-11
7 Claude Opus 5.5 Max Anthropic 31.7% 2026-11-11
8 GPT-6 Astra Max OpenAI 31.7% 2026-11-11
9 Claude Opus 5.5 Extra High Anthropic 31.7% 2026-11-11
10 GPT-6.1 Sol Extra High OpenAI 31.7% 2026-11-11
11 Claude Sonnet 5.5 Max Anthropic 31.4% 2026-11-11
12 GPT-6 Astra Extra High OpenAI 31.4% 2026-11-11
13 Claude Fable 5.1 Extra High Anthropic 31.1% 2026-11-11
14 Claude Sonnet 5.5 Extra High Anthropic 31.1% 2026-11-11
15 GPT-6 Sol Max OpenAI 30.9% 2026-11-11
16 Claude Opus 5.5 High Anthropic 30.9% 2026-11-11
17 Claude Fable 5.2 Medium Anthropic 30.9% 2026-11-11
18 GPT-5.5 Pro Extra High OpenAI 30.6% 2026-11-11
19 Claude Fable 5.1 High Anthropic 30.3% 2026-11-11
20 GPT-5.6 Terra Max OpenAI 30.0% 2026-11-11
21 GPT-5.4 Pro Extra High OpenAI 30.0% 2026-11-11
22 GPT-6.1 Sol High OpenAI 30.0% 2026-11-11
23 Claude Fable 5.1 Max Anthropic 29.7% 2026-11-11
24 Claude Fable 5.2 Low Anthropic 29.4% 2026-11-11
25 Claude Opus 5 Max Anthropic 29.1% 2026-11-11
26 GPT-6 Astra Medium OpenAI 29.1% 2026-11-11
27 Claude Fable 5.1 Medium Anthropic 29.1% 2026-11-11
28 GPT-6 Astra High OpenAI 28.9% 2026-11-11
29 Claude Fable 5 Max Anthropic 28.6% 2026-11-11
30 GPT-5.6 Sol Extra High OpenAI 28.6% 2026-11-11
31 Muse Wonder Max Meta 28.3% 2026-11-11
32 Claude Opus 5 High Anthropic 28.3% 2026-11-11
33 GPT-6.1 Terra Max OpenAI 28.0% 2026-11-11
34 GPT-6 Sol Extra High OpenAI 28.0% 2026-11-11
35 Claude Opus 5 Extra High Anthropic 27.7% 2026-11-11
36 Claude Fable 5.1 Low Anthropic 27.7% 2026-11-11
37 Claude Opus 5.5 Medium Anthropic 27.7% 2026-11-11
38 GPT-6.1 Sol Medium OpenAI 27.7% 2026-11-11
39 Gemini 4 Argon High Google 27.1% 2026-11-11
40 GPT-5.5 Extra High OpenAI 27.1% 2026-11-11
41 GPT-5.6 Terra Extra High OpenAI 27.1% 2026-11-11
42 Claude Opus 5 Medium Anthropic 26.9% 2026-11-11
43 MiMo-V2.6-Pro Xiaomi 26.6% 2026-11-11
44 GPT-6.1 Terra Extra High OpenAI 26.6% 2026-11-11
45 GPT-6 Astra Low OpenAI 26.3% 2026-11-11
46 Muse Spark 1.3 Extra High Meta 26.0% 2026-11-11
47 Gemini 3 Deep Think Google 25.7% 2026-11-11
48 GPT-5.6 Sol High OpenAI 25.7% 2026-11-11
49 GPT-6.1 Terra High OpenAI 25.7% 2026-11-11
50 GPT-5.5 High OpenAI 25.4% 2026-11-11
51 GPT-6 Sol High OpenAI 25.4% 2026-11-11
52 Muse Spark 1.3 Max Meta 24.9% 2026-11-11
53 GPT-6.1 Sol Low OpenAI 24.9% 2026-11-11
54 Kimi K3.1 Pro Moonshot AI 24.6% 2026-11-11
55 Claude Sonnet 5.5 High Anthropic 24.6% 2026-11-11
56 GPT-6 Sol Medium OpenAI 24.6% 2026-11-11
57 DeepSeek V4.1 Flash 1017 Max DeepSeek 24.0% 2026-11-11
58 GPT-5.4 Extra High OpenAI 23.4% 2026-11-11
59 Kimi K3 Max Moonshot AI 23.4% 2026-11-11
60 Claude Opus 5 Low Anthropic 23.1% 2026-11-11
61 GPT-5.6 Sol Medium OpenAI 22.9% 2026-11-11
62 GPT-5.6 Terra High OpenAI 22.9% 2026-11-11
63 Claude Haiku 5.5 Extra High Anthropic 22.6% 2026-11-11
64 GPT-6.1 Terra Medium OpenAI 21.4% 2026-11-11
65 Step 5 Preview StepFun 20.9% 2026-11-11
66 GLM-5.2 Max Zhipu AI 20.9% 2026-11-11
67 Claude Opus 4.8 Max Anthropic 20.9% 2026-11-11
68 GPT-5.6 Luna Max OpenAI 20.6% 2026-11-11
69 GPT-5.6 Luna Extra High OpenAI 20.6% 2026-11-11
70 Qwen3.8 Max Alibaba 20.0% 2026-11-11
71 Grok 4.6 Extra High xAI 19.7% 2026-11-11
72 GPT-6 Astra Non-reasoning OpenAI 19.7% 2026-11-11
73 GPT-6 Luna Max OpenAI 19.4% 2026-11-11
74 GLM-5.3 Max Zhipu AI 19.1% 2026-11-11
75 Claude Haiku 5.5 Max Anthropic 18.9% 2026-11-11
76 Claude Haiku 5.5 High Anthropic 18.6% 2026-11-11
77 GPT-5.5 Medium OpenAI 18.6% 2026-11-11
78 Gemini 3.8 Flash High Google 18.3% 2026-11-11
79 DeepSeek V4 Pro 0813 Max DeepSeek 18.0% 2026-11-11
80 Grok 4.7 High xAI 18.0% 2026-11-11
81 Gemini 3.1 Pro Preview Google 17.7% 2026-11-11
82 Qwen3.8 Max 0902 Alibaba 17.7% 2026-11-11
83 Grok 4.7 Extra High xAI 17.7% 2026-11-11
84 Muse Spark 1.2 Extra High Meta 17.7% 2026-11-11
85 Grok 4.6 Medium xAI 17.7% 2026-11-11
86 Claude Opus 5.5 Low Anthropic 17.7% 2026-11-11
87 GPT-5.6 Terra Medium OpenAI 17.4% 2026-11-11
88 GPT-6 Luna Extra High OpenAI 17.4% 2026-11-11
89 Grok 4.6 High xAI 17.1% 2026-11-11
90 Claude Sonnet 5 Max Anthropic 16.9% 2026-11-11
91 Claude Sonnet 5.5 Medium Anthropic 16.9% 2026-11-11
92 GPT-5.3 Codex Extra High OpenAI 16.9% 2026-11-11
93 DeepSeek V4 Flash 0731 Max DeepSeek 16.6% 2026-11-11
94 GPT-5.6 Luna High OpenAI 16.6% 2026-11-11
95 GPT-6 Sol Low OpenAI 16.3% 2026-11-11
96 GLM-5.3-Flash Zhipu AI 15.4% 2026-11-11
97 Grok 4.5 High xAI 15.4% 2026-11-11
98 Claude Sonnet 5 Extra High Anthropic 15.4% 2026-11-11
99 GPT-6 Luna High OpenAI 15.4% 2026-11-11
100 Muse Spark 1.1 Extra High Meta 15.1% 2026-11-11
101 GPT-6.1 Terra Low OpenAI 15.1% 2026-11-11
102 Muse Spark 1.1 Meta 15.1% 2026-11-11
103 Muse Spark Open Extra High Meta 14.9% 2026-11-11
104 GPT-5.6 Sol Low OpenAI 14.9% 2026-11-11
105 GLM-5.3 Low Zhipu AI 14.6% 2026-11-11
106 DeepSeek V4.1 Flash Max DeepSeek 14.3% 2026-11-11
107 Gemini 3.7 Flash High Google 14.3% 2026-11-11
108 Qwen3.7 Max Alibaba 13.4% 2026-11-11
109 Grok 4.7 Low xAI 13.4% 2026-11-11
110 Beam 1.0 Reflection 13.1% 2026-11-11
111 Gemini 3.5 Flash High Google 13.1% 2026-11-11
112 Claude Haiku 5.5 Medium Anthropic 12.9% 2026-11-11
113 DeepSeek V4 Pro Max DeepSeek 12.9% 2026-11-11
114 GPT-5 High OpenAI 12.6% 2026-11-11
115 Gemini 3.8 Flash Medium Google 12.3% 2026-11-11
116 MiMo-V2.6-Flash Xiaomi 12.0% 2026-11-11
117 Claude Opus 4.7 Max Anthropic 12.0% 2026-11-11
118 Claude Sonnet 5.5 Low Anthropic 11.4% 2026-11-11
119 Muse Spark Meta 11.3% 2026-11-11
120 Mistral Large 4 Medium Mistral 11.1% 2026-11-11
121 Mistral Large 4 Preview Mistral 10.6% 2026-11-11
122 Gemini 3.6 Flash High Google 10.6% 2026-11-11
123 GPT-6 Luna Medium OpenAI 10.6% 2026-11-11
124 Kimi K2.7 Code Moonshot AI 10.0% 2026-11-11
125 Mistral Large 4 High Mistral 10.0% 2026-11-11
126 GPT-5.4 mini Extra High OpenAI 10.0% 2026-11-11
127 DeepSeek V4 Pro High DeepSeek 10.0% 2026-11-11
128 GPT-5.6 Terra Low OpenAI 9.4% 2026-11-11
129 Gemini 3.7 Flash Medium Google 9.4% 2026-11-11
130 GPT-5.4 nano Extra High OpenAI 9.3% 2026-11-11
131 Grok Build 0.1 xAI 9.1% 2026-11-11
132 Qwen3.7 Plus Alibaba 9.1% 2026-11-11
133 Claude Haiku 5.5 Low Anthropic 9.1% 2026-11-11
134 Claude Sonnet 5 Medium Anthropic 8.6% 2026-11-11
135 Inkling Small Thinking Machines 8.3% 2026-11-11
136 Kimi K2.6 Moonshot AI 8.0% 2026-11-11
137 Grok 4.3 High xAI 8.0% 2026-11-11
138 GPT-5.5 Low OpenAI 8.0% 2026-11-11
139 DeepSeek V4 Flash Max DeepSeek 7.1% 2026-11-11
140 Gemini 3 Pro Preview Google 6.9% 2026-11-11
141 Grok 4.6 Low xAI 5.7% 2026-11-11
142 Gemini 3.7 Flash Low Google 5.7% 2026-11-11
143 Inkling Extra High Thinking Machines 5.4% 2026-11-11
144 Qwen3.8 27B Extra High Alibaba 5.4% 2026-11-11
145 GPT-5.6 Sol Non-reasoning OpenAI 5.1% 2026-11-11
146 GPT-5.1 OpenAI 4.9% 2026-11-11
147 GPT-5.6 Luna Medium OpenAI 4.9% 2026-11-11
148 GPT-6.1 Terra Non-reasoning OpenAI 4.9% 2026-11-11
149 GLM-5.1 Zhipu AI 4.6% 2026-11-11
150 Claude Sonnet 5 Low Anthropic 4.6% 2026-11-11
151 MiMo-V2.5-Pro Xiaomi 4.0% 2026-11-11
152 Gemini 3.8 Flash Low Google 4.0% 2026-11-11
153 GPT-6 Sol Non-reasoning OpenAI 4.0% 2026-11-11
154 MiniMax-M3 MiniMax 3.7% 2026-11-11
155 MiMo-V2.5 Xiaomi 3.7% 2026-11-11
156 Ring-2.6-1T Ant Group 3.7% 2026-11-11
157 DeepSeek V4 Flash High DeepSeek 3.4% 2026-11-11
158 Kimi K2.5 Moonshot AI 3.1% 2026-11-11
159 Nemotron 3 Super NVIDIA 3.1% 2026-11-11
160 Nemotron 3 Ultra NVIDIA 3.1% 2026-11-11
161 GLM-5.2 Non-reasoning Zhipu AI 3.1% 2026-11-11
162 Kimi K3 Low Moonshot AI 3.1% 2026-11-11
163 Claude Sonnet 4.6 Max Anthropic 3.1% 2026-11-11
164 Qwen3.6 Plus Alibaba 2.9% 2026-11-11
165 DeepSeek-V3.2-Exp Thinking DeepSeek 2.9% 2026-11-11
166 GPT-5.6 Luna Low OpenAI 2.6% 2026-11-11
167 GPT-6 Luna Low OpenAI 2.6% 2026-11-11
168 Muse Glimmer High Meta 2.6% 2026-11-11
169 Step 3.7 Flash StepFun 2.3% 2026-11-11
170 Gemini 2.5 Pro Google 2.0% 2026-11-11
171 GPT-5.6 Terra Non-reasoning OpenAI 2.0% 2026-11-11
172 GLM-4.7 Zhipu AI 1.7% 2026-11-11
173 DeepSeek-V3.1-Terminus DeepSeek 1.7% 2026-11-11
174 Gemma 4 31B IT Google 1.4% 2026-11-11
175 GPT-5.5 Non-reasoning OpenAI 1.4% 2026-11-11
176 GPT OSS 20B High OpenAI 1.4% 2026-11-11
177 Claude Sonnet 4.5 Anthropic 1.1% 2026-11-11
178 GLM-4.6 Zhipu AI 1.1% 2026-11-11
179 Gemini 3.1 Flash Lite Google 1.1% 2026-11-11
180 GPT OSS 120B High OpenAI 1.1% 2026-11-11
181 o3 High OpenAI 1.1% 2026-11-11
182 Claude Sonnet 5 High Anthropic 1.1% 2026-11-11
183 GPT-6 Luna Non-reasoning OpenAI 1.1% 2026-11-11
184 DeepSeek-R1 DeepSeek 1.1% 2026-11-11
185 Gemini 2.5 Flash Google 1.1% 2026-11-11
186 Trinity Large Thinking Arcee AI 0.9% 2026-11-11
187 Qwen3.6 27B Non-reasoning Alibaba 0.9% 2026-11-11
188 Qwen3.5 397B-A17B Non-reasoning Alibaba 0.9% 2026-11-11
189 Qwen3.5 122B-A10B Non-reasoning Alibaba 0.9% 2026-11-11
190 Mercury 2 Inception 0.9% 2026-11-11
191 o4-mini High OpenAI 0.6% 2026-11-11
192 MiniMax-M2.7 MiniMax 0.6% 2026-11-11
193 Qwen3.5 35B-A3B Non-reasoning Alibaba 0.6% 2026-11-11
194 Qwen3.5 9B Non-reasoning Alibaba 0.6% 2026-11-11
195 Claude Opus 4 Anthropic 0.3% 2026-11-11
196 Magistral Small 1.2 Mistral 0.3% 2026-11-11
197 Claude Sonnet 4 Anthropic 0.3% 2026-11-11
198 Command A Plus Cohere 0.3% 2026-11-11
199 Qwen3.5 9B Alibaba 0.3% 2026-11-11
200 Qwen3 32B Alibaba 0.3% 2026-11-11
201 Qwen3.6 35B-A3B Alibaba 0.3% 2026-11-11
202 Magistral Medium 1.2 Mistral 0.3% 2026-11-11
203 Qwen3-30B-A3B-Thinking (Jul 2025) Alibaba 0.3% 2026-11-11
204 GPT-5.6 Luna Non-reasoning OpenAI 0.3% 2026-11-11
205 o3-mini High OpenAI 0.3% 2026-11-11
206 Qwen3.8 27B Non-reasoning Alibaba 0.3% 2026-11-11
207 DeepSeek V4.1 Flash Non-reasoning DeepSeek 0.3% 2026-11-11
208 DeepSeek V4.1 Flash 1017 Non-reasoning DeepSeek 0.3% 2026-11-11
209 Llama-3.3-70B-Instruct Meta 0.0% 2026-11-11
210 Llama-3.2-11B-Vision-Instruct Meta 0.0% 2026-11-11
211 Llama-3.1-8B-Instruct Meta 0.0% 2026-11-11
212 Grok 4.3 xAI 0.0% 2026-11-11
213 Phi-4-mini Microsoft 0.0% 2026-11-11
214 Mistral Medium 3.5 Mistral 0.0% 2026-11-11
215 Mistral Medium 3.1 Mistral 0.0% 2026-11-11
216 Mistral Large 3 Mistral 0.0% 2026-11-11
217 Mistral Small 3.2 Mistral 0.0% 2026-11-11
218 Devstral Small 2 Mistral 0.0% 2026-11-11
219 Claude Haiku 3.5 Anthropic 0.0% 2026-11-11
220 Claude Haiku 4.5 Anthropic 0.0% 2026-11-11
221 GPT-5 Mini OpenAI 0.0% 2026-11-11
222 GPT-4.1 mini OpenAI 0.0% 2026-11-11
223 GPT-4o (2024-11-20) OpenAI 0.0% 2026-11-11
224 GPT-4.1 nano OpenAI 0.0% 2026-11-11
225 GPT-5.5 Instant OpenAI 0.0% 2026-11-11
226 DeepSeek V3 0324 DeepSeek 0.0% 2026-11-11
227 DeepSeek-V3 DeepSeek 0.0% 2026-11-11
228 Mercury 2.5 Inception 0.0% 2026-11-11
229 Gemma 4 26B A4B IT Google 0.0% 2026-11-11
230 Gemma 3 27B IT Google 0.0% 2026-11-11
231 Gemma 3 12B IT Google 0.0% 2026-11-11
232 Gemini 3.5 Flash Lite Google 0.0% 2026-11-11
233 Reka Flash 3 Reka 0.0% 2026-11-11
234 Solar Pro 3 Upstage 0.0% 2026-11-11
235 MiMo-V2-Flash Xiaomi 0.0% 2026-11-11
236 Qwen3 Coder Next Alibaba 0.0% 2026-11-11
237 Qwen3 235B-A22B Thinking 2507 Alibaba 0.0% 2026-11-11
238 Qwen3 8B Alibaba 0.0% 2026-11-11
239 Qwen3.5 0.8B Alibaba 0.0% 2026-11-11
240 Amazon Nova Micro Amazon 0.0% 2026-11-11
241 Cohere Command A Cohere 0.0% 2026-11-11
242 Llama 4 Maverick Meta 0.0% 2026-11-11
243 Llama 4 Scout Meta 0.0% 2026-11-11
244 Qwen3-14B Alibaba 0.0% 2026-11-11
245 Cogito v2.1 Deep Cogito 0.0% 2026-11-11
246 Gemma 3 270M Google 0.0% 2026-11-11
247 granite-4.0-350m Unknown 0.0% 2026-11-11
248 granite-4.0-micro Unknown 0.0% 2026-11-11
249 Granite 4.1 30B IBM 0.0% 2026-11-11
250 Llama 3.1-405B Meta 0.0% 2026-11-11
251 Mistral Small 3.1 Mistral 0.0% 2026-11-11
252 nvidia-nemotron-nano-9b-v2 Unknown 0.0% 2026-11-11
253 Phi-4 Microsoft 0.0% 2026-11-11
254 GPT OSS 20B Low OpenAI 0.0% 2026-11-11
255 Qwen3.6 35B-A3B Non-reasoning Alibaba 0.0% 2026-11-11
256 DeepSeek V4 Pro 0813 Non-reasoning DeepSeek 0.0% 2026-11-11
257 GPT-5 Minimal OpenAI 0.0% 2026-11-11
258 GPT-5 Mini High OpenAI 0.0% 2026-11-11
259 Qwen3.5 4B Non-reasoning Alibaba 0.0% 2026-11-11
260 Nova 2.0 Pro Preview Medium Amazon 0.0% 2026-11-11
261 Nova 2.0 Pro Preview Non-reasoning Amazon 0.0% 2026-11-11
262 Nova 2.0 Pro Preview Low Amazon 0.0% 2026-11-11
263 GPT OSS 120B Low OpenAI 0.0% 2026-11-11
264 Qwen3.8 27B Low Alibaba 0.0% 2026-11-11
265 Qwen3.8 27B Medium Alibaba 0.0% 2026-11-11
266 Grok 4.3 Non-reasoning xAI 0.0% 2026-11-11
267 Qwen3.5 2B Non-reasoning Alibaba 0.0% 2026-11-11
268 Qwen3.5 0.8B Non-reasoning Alibaba 0.0% 2026-11-11