GPQA Diamond

198 graduate-level biology, chemistry and physics questions that experts answer well and non-experts cannot look up. Run by Epoch AI. Near saturation.

CategoryReasoning
MetricAccuracy
SourceEpoch AI (evaluator)
LicenseCC BY 4.0
Benchmark pageepoch.ai
StatusScored
Weight0.8 within Reasoning
FitDiscrimination 0.87, noise 0.26
LineageShares weight with gpqa_diamond

Results

#ModelProviderResultDate
1 Gemini 4 Carbon High Google 96.5% 2026-11-02
2 Gemini 4 Argon High Google 96.4% 2026-10-13
3 GPT-6 Astra Max OpenAI 95.8% 2026-08-30
4 Claude Sonnet 5.5 Max Anthropic 95.6% 2026-09-29
5 GPT-6.1 Sol Max OpenAI 95.4% 2026-09-29
6 Gemini 3.8 Flash High Google 95.4% 2026-09-02
7 Gemini 3.7 Flash High Google 94.8% 2026-08-14
8 GPT-5.4 Pro Extra High OpenAI 94.6% 2026-03-20
9 Gemini 3.1 Pro Preview High Google 94.4% 2026-08-06
10 GPT-6.1 Terra Max OpenAI 94.3% 2026-10-26
11 GPT-6 Sol Max OpenAI 94.3% 2026-09-22
12 Kimi K3.1 Pro Max Moonshot AI 94.2% 2026-11-06
13 Gemini 3.6 Flash High Google 94.1% 2026-08-02
14 Gemini 3.1 Pro Preview Google 94.1% 2026-02-20
15 Grok 4.6 High xAI 94.0% 2026-08-12
16 GPT-5.5 Extra High OpenAI 94.0% 2026-04-24
17 GPT-5.5 Pro Extra High OpenAI 93.9% 2026-04-24
18 Claude Fable 5.2 Max Anthropic 93.9% 2026-11-06
19 Claude Opus 5 Max Anthropic 93.9% 2026-07-24
20 GPT-5.6 Sol Max OpenAI 93.5% 2026-07-09
21 Grok 4.5 High xAI 93.4% 2026-07-08
22 GPT-5.6 Terra Max OpenAI 93.3% 2026-07-09
23 GPT-5.4 Extra High OpenAI 93.3% 2026-03-06
24 DeepSeek V4.1 Flash 1017 Max DeepSeek 93.2% 2026-10-19
25 Grok 4.6 Extra High xAI 93.2% 2026-08-14
26 Doubao Seed Evolving (Nov 2026) High ByteDance 93.1% 2026-11-02
27 Kimi K3 Max Moonshot AI 93.1% 2026-07-16
28 Claude Opus 5 Anthropic 92.9% 2026-08-06
29 Gemini 3.5 Flash High Google 92.8% 2026-05-22
30 Grok 4.7 Extra High xAI 92.7% 2026-09-22
31 Qwen3.8 Max Extra High Alibaba 92.7% 2026-08-04
32 Gemini 3 Pro Preview Google 92.6% 2025-11-19
33 Qwen3.8 Max 0902 Extra High Alibaba 92.3% 2026-09-02
34 Kimi K3 High Moonshot AI 91.9% 2026-08-07
35 GLM-5.2 Max Zhipu AI 91.9% 2026-06-24
36 DeepSeek V4 Pro 0813 Max DeepSeek 91.7% 2026-08-18
37 GPT-5.6 Luna Max OpenAI 91.6% 2026-07-09
38 GPT-5.2 Extra High OpenAI 91.4% 2025-12-13
39 DeepSeek V4 Flash 0731 Max DeepSeek 91.0% 2026-08-02
40 Claude Opus 4.8 Max Anthropic 91.0% 2026-06-07
41 MiniMax-M3 MiniMax 90.9% 2026-08-10
42 Qwen3.7 Max Alibaba 90.9% 2026-08-07
43 GLM-5.3 Max Zhipu AI 90.9% 2026-08-24
44 DeepSeek V4 Pro High DeepSeek 90.9% 2026-08-06
45 Kimi K2.6 Moonshot AI 90.8% 2026-05-01
46 GPT-5.5 Low OpenAI 90.7% 2026-05-05
47 Claude Opus 5.5 Max Anthropic 90.6% 2026-09-22
48 Claude Sonnet 5 Extra High Anthropic 90.5% 2026-07-01
49 Claude Opus 4.6 Thinking Anthropic 90.5% 2026-02-06
50 GPT-6 Luna Max OpenAI 90.5% 2026-09-22
51 Mistral Large 4 High Mistral 90.2% 2026-11-02
52 GLM-5.3-Flash Max Zhipu AI 90.2% 2026-08-26
53 Claude Opus 4.7 Extra High Anthropic 90.2% 2026-04-17
54 GLM-5.1 Zhipu AI 89.9% 2026-08-10
55 GPT-5.6 Sol Low OpenAI 89.9% 2026-08-07
56 GPT-5.4 High OpenAI 89.9% 2026-07-15
57 DeepSeek V4.1 Flash Max DeepSeek 89.8% 2026-10-09
58 Muse Spark Meta 89.8% 2026-04-08
59 Claude Haiku 5.5 Max Anthropic 89.7% 2026-10-09
60 DeepSeek V4 Pro Max DeepSeek 89.7% 2026-06-16
61 Doubao Seed 2.1 Turbo High ByteDance 89.6% 2026-10-30
62 Gemini 3 Flash Preview High Google 89.4% 2026-08-06
63 Grok 4.20 (Reasoning) xAI 89.3% 2026-07-13
64 Doubao Seed 2.1 Pro High ByteDance 89.3% 2026-10-28
65 Gemini 3.5 Flash Low Google 88.9% 2026-08-06
66 GPT-5.4 Medium OpenAI 88.9% 2026-07-15
67 Grok 4.3 High xAI 88.8% 2026-06-17
68 Muse Spark Open Extra High Meta 88.6% 2026-10-15
69 Inkling Small Extra High Thinking Machines 88.5% 2026-08-14
70 Qwen3.6 Plus Alibaba 88.4% 2026-08-07
71 Claude Opus 4.6 Max Anthropic 88.4% 2026-08-06
72 Claude Opus 4.8 Low Anthropic 88.4% 2026-08-06
73 Inkling Extra High Thinking Machines 88.3% 2026-08-05
74 Doubao-Seed-2.0 Pro High ByteDance 88.2% 2026-10-28
75 GPT-5.2 High OpenAI 88.2% 2025-12-11
76 Doubao Seed 2.0 Lite (Apr 2026) High ByteDance 88.1% 2026-10-28
77 Mistral Large 4 Preview High Mistral 88.1% 2026-10-12
78 Kimi K2.7 Code Moonshot AI 87.9% 2026-08-07
79 Qwen3.7 Plus Alibaba 87.9% 2026-08-07
80 GLM-5.2 Low Zhipu AI 87.9% 2026-08-10
81 Claude Opus 5 Low Anthropic 87.9% 2026-08-06
82 GPT-5.2 Medium OpenAI 87.9% 2025-12-11
83 GLM-5 Zhipu AI 87.8% 2026-02-12
84 GPT-5.1 High OpenAI 87.6% 2025-11-13
85 Kimi K2.5 Moonshot AI 87.6% 2026-02-02
86 Qwen3.6 Max Preview Alibaba 87.4% 2026-08-07
87 GPT-5.6 Terra Low OpenAI 87.4% 2026-08-07
88 Claude Sonnet 4.6 Thinking Anthropic 87.4% 2026-02-20
89 Grok 4 xAI 87.0% 2026-11-11
90 GPT-5.4 mini Extra High OpenAI 86.9% 2026-08-07
91 Qwen3.5 397B-A17B Non-reasoning Alibaba 86.4% 2026-08-07
92 Gemini 3.6 Flash Low Google 86.4% 2026-08-06
93 Claude Opus 4.7 Max Anthropic 86.4% 2026-08-06
94 Gemini 3.5 Flash Minimal Google 86.4% 2026-07-15
95 GPT-5 High OpenAI 86.2% 2025-10-29
96 Claude Opus 4.5 Thinking Anthropic 86.1% 2025-11-24
97 Qwen3.5 397B-A17B Alibaba 85.9% 2026-08-07
98 Qwen3.6 27B Alibaba 85.9% 2026-08-07
99 Gemini 3.6 Flash Minimal Google 85.9% 2026-08-07
100 Claude Fable 5 Max Anthropic 85.9% 2026-08-06
101 Nemotron 3 Ultra NVIDIA 85.4% 2026-08-10
102 Claude Opus 4.8 Non-reasoning Anthropic 85.4% 2026-08-06
103 GPT-5 Medium OpenAI 85.4% 2025-08-07
104 Gemini 2.5 Pro Google 85.3% 2025-11-16
105 GPT-5.1 Medium OpenAI 85.0% 2025-11-17
106 Gemini 2.5 Pro Preview 06-05 Google 84.9% 2025-06-05
107 Qwen3.5 Plus Alibaba 84.9% 2026-08-07
108 Kimi K3 Low Moonshot AI 84.9% 2026-08-07
109 Qwen3.6 27B Non-reasoning Alibaba 84.9% 2026-08-07
110 Qwen3.6 35B-A3B Non-reasoning Alibaba 84.9% 2026-08-07
111 GPT-5.4 Low OpenAI 84.9% 2026-07-15
112 Kimi K2 Thinking Turbo Moonshot AI 84.2% 2025-11-11
113 Qwen3.6 35B-A3B Alibaba 83.8% 2026-08-07
114 GPT-5.4 mini High OpenAI 83.6% 2026-04-15
115 Qwen3.5 35B-A3B Alibaba 83.5% 2026-08-28
116 DeepSeek Reasoner DeepSeek 83.4% 2025-12-16
117 GLM-4.7 Zhipu AI 83.3% 2026-01-29
118 Qwen3.6 Flash Alibaba 83.3% 2026-08-07
119 Gemini 3.5 Flash Lite High Google 83.3% 2026-08-06
120 Claude Fable 5 High Anthropic 83.3% 2026-08-06
121 Claude Sonnet 4.6 High Anthropic 83.3% 2026-07-13
122 Claude Sonnet 4.6 Medium Anthropic 83.3% 2026-07-13
123 Gemini 3 Flash Preview Google 83.2% 2025-12-17
124 GPT-5.6 Sol Non-reasoning OpenAI 82.8% 2026-08-07
125 GPT-5.2 Low OpenAI 82.7% 2025-12-11
126 GPT-5.5 Instant OpenAI 82.5% 2026-08-02
127 Qwen3.7 Flash Alibaba 82.3% 2026-08-07
128 Qwen3.5 Flash Alibaba 82.3% 2026-08-07
129 GPT-5.6 Luna Low OpenAI 82.3% 2026-08-07
130 Claude Sonnet 4.5 Thinking Anthropic 82.3% 2025-10-28
131 Qwen3.7 Plus Non-reasoning Alibaba 81.8% 2026-08-07
132 Gemini 3.1 Flash Lite High Google 81.8% 2026-08-06
133 o3 High OpenAI 81.8% 2025-04-16
134 MiniMax-M3 Non-reasoning MiniMax 81.3% 2026-08-10
135 Qwen3.5 35B-A3B Non-reasoning Alibaba 81.2% 2026-08-28
136 o3 Medium OpenAI 80.8% 2026-08-07
137 Qwen3.7 Flash Non-reasoning Alibaba 80.8% 2026-08-07
138 Claude Opus 4.5 Anthropic 80.7% 2025-11-24
139 Claude Sonnet 5 Max Anthropic 80.3% 2026-08-06
140 Qwen3 235B-A22B Thinking 2507 Alibaba 80.1% 2025-12-11
141 o3 Low OpenAI 79.8% 2026-07-15
142 Claude Sonnet 3.7 Thinking Anthropic 79.7% 2025-05-26
143 o4-mini High OpenAI 79.6% 2025-04-16
144 Claude Sonnet 4 Thinking Anthropic 79.2% 2025-05-26
145 Qwen3.5 9B Alibaba 79.0% 2026-08-27
146 Qwen3.5 9B Non-reasoning Alibaba 78.9% 2026-08-27
147 Claude Sonnet 4.6 Max Anthropic 78.8% 2026-08-06
148 Claude Fable 5 Low Anthropic 78.8% 2026-08-06
149 GPT-5.4 nano High OpenAI 78.5% 2026-04-14
150 o4-mini Medium OpenAI 77.8% 2026-08-07
151 Seed 1.6 ByteDance 77.6% 2026-10-30
152 GPT-5.5 Non-reasoning OpenAI 77.3% 2026-08-07
153 GPT-5.6 Terra Non-reasoning OpenAI 77.3% 2026-08-07
154 Claude Opus 4.1 Thinking Anthropic 77.3% 2025-08-05
155 o3-mini High OpenAI 77.0% 2025-02-13
156 o1 High OpenAI 76.8% 2025-02-13
157 DeepSeek R1 0528 DeepSeek 76.3% 2025-05-29
158 Claude Opus 4 Thinking Anthropic 76.3% 2025-05-22
159 Grok-3 mini Low xAI 76.3% 2025-04-10
160 Grok 3 xAI 75.8% 2025-05-26
161 Gemma 4 31B IT Minimal Google 75.8% 2026-08-06
162 Gemini 3.5 Flash Lite Low Google 75.8% 2026-08-06
163 GPT OSS 120B High OpenAI 75.8% 2025-12-11
164 o1 Medium OpenAI 75.8% 2025-01-27
165 Grok-3 mini High xAI 75.5% 2025-05-26
166 o4-mini Low OpenAI 75.3% 2026-07-11
167 GPT-5 Mini High OpenAI 75.0% 2025-10-30
168 GPT-5.4 Non-reasoning OpenAI 74.8% 2026-07-15
169 o3-mini Medium OpenAI 74.3% 2025-01-31
170 Gemini 3.5 Flash Lite Minimal Google 74.2% 2026-08-06
171 Gemini 3.1 Flash Lite Low Google 74.2% 2026-08-06
172 o1 Low OpenAI 74.2% 2026-07-20
173 Claude Sonnet 4.5 Anthropic 73.7% 2025-09-29
174 Gemini 3.1 Flash Lite Minimal Google 73.7% 2026-08-06
175 Claude Opus 4.1 Anthropic 73.2% 2025-08-05
176 Gemma 4 26B A4B IT Minimal Google 73.2% 2026-08-06
177 GPT-5.2 Non-reasoning OpenAI 73.2% 2026-07-13
178 DeepSeek V4 Pro Non-reasoning DeepSeek 73.2% 2026-08-06
179 Qwen3 Max Alibaba 72.6% 2025-10-06
180 GPT-5.4 nano Low OpenAI 72.2% 2026-08-07
181 DeepSeek-R1 DeepSeek 71.7% 2025-05-26
182 GPT-5 Mini Minimal OpenAI 71.7% 2026-08-07
183 GPT-5 Minimal OpenAI 71.7% 2026-07-20
184 GPT-5 Mini Medium OpenAI 71.7% 2025-08-07
185 Seed-OSS-36B-Instruct ByteDance 71.5% 2026-08-30
186 DeepSeek Chat DeepSeek 71.2% 2026-07-16
187 GLM-5.2 Non-reasoning Zhipu AI 71.2% 2026-08-10
188 Claude Haiku 4.5 Thinking Anthropic 71.2% 2025-10-22
189 Qwen3 235B-A22B Alibaba 70.7% 2025-06-03
190 Qwen3-30B-A3B-Thinking (Jul 2025) Alibaba 70.1% 2026-08-30
191 GPT-5 Nano High OpenAI 69.4% 2025-10-30
192 Claude Opus 4 Anthropic 69.2% 2025-05-22
193 GPT-4.5 OpenAI 68.7% 2025-02-28
194 o3-mini Low OpenAI 68.2% 2026-07-20
195 DeepSeek V3 0324 DeepSeek 67.6% 2025-04-01
196 GPT-5 Nano Medium OpenAI 67.4% 2025-08-07
197 Llama 4 Maverick Meta 67.0% 2025-04-08
198 GPT-4.1 OpenAI 66.9% 2025-04-14
199 Claude Sonnet 4 Anthropic 66.7% 2025-05-22
200 GPT-5.1 Non-reasoning OpenAI 66.7% 2026-08-07
201 Claude Sonnet 3.7 Anthropic 66.0% 2025-02-24
202 GPT-4.1 mini OpenAI 65.9% 2025-04-14
203 Qwen3 32B Alibaba 65.7% 2026-08-28
204 Gemini 2.0 Pro Google 65.7% 2025-02-07
205 QwQ Plus Alibaba 65.4% 2025-04-11
206 QwQ 32B Alibaba 65.3% 2026-08-28
207 DeepSeek-R1-Distill-Qwen-32B DeepSeek 64.1% 2026-08-28
208 Gemini 2.0 Flash Google 64.1% 2025-02-06
209 GPT-5.4 mini Non-reasoning OpenAI 64.1% 2026-08-07
210 Qwen3-14B Alibaba 63.8% 2026-08-28
211 GPT-5.6 Luna Non-reasoning OpenAI 63.6% 2026-08-07
212 o1-mini High OpenAI 62.4% 2025-02-13
213 Qwen3 30B A3B Alibaba 61.7% 2026-08-30
214 GPT OSS 20B Medium OpenAI 60.8% 2026-08-27
215 GLM-4.7-Flash Zhipu AI 60.5% 2026-08-30
216 Claude Haiku 4.5 Anthropic 60.5% 2025-10-16
217 Mistral Medium 3 Mistral 59.5% 2025-05-07
218 o1-mini Medium OpenAI 59.5% 2025-01-27
219 GPT-5 Nano Low OpenAI 57.6% 2026-07-13
220 Gemini 1.5 Pro (Sept 2024) Google 57.2% 2025-01-27
221 Gemini 2.0 Flash Thinking (Jan 2025) Google 57.1% 2025-02-06
222 Qwen3 8B Alibaba 56.8% 2026-08-27
223 DeepSeek-V3 DeepSeek 56.5% 2025-01-27
224 Qwen Max Alibaba 56.1% 2025-04-01
225 Magistral Small Mistral 56.1% 2026-08-06
226 Phi-4 Microsoft 56.1% 2025-01-31
227 DeepSeek-R1-Distill-Llama-70B DeepSeek 55.7% 2025-03-10
228 Qwen3 30B-A3B Instruct 2507 Alibaba 55.6% 2026-08-30
229 GPT-5.4 nano Non-reasoning OpenAI 55.6% 2026-08-07
230 Claude Sonnet 3.5 v2 Anthropic 55.3% 2025-01-27
231 Qwen3 32B Non-reasoning Alibaba 54.1% 2026-08-30
232 Claude 3.5 Sonnet Anthropic 54.0% 2025-01-27
233 Grok-2 (Dec 2024) xAI 53.8% 2025-01-27
234 Qwen3-14B Non-reasoning Alibaba 53.4% 2026-08-28
235 GPT OSS 20B Low OpenAI 53.2% 2026-08-27
236 Qwen3-4B Alibaba 52.3% 2026-08-28
237 Llama 4 Scout Meta 51.8% 2025-04-08
238 Mistral Large 2.1 Mistral 51.3% 2025-02-25
239 Llama 3.1-405B Meta 50.9% 2025-01-27
240 Qwen3 30B A3B Non-reasoning Alibaba 50.4% 2026-08-30
241 o1-preview OpenAI 50.3% 2025-01-27
242 GPT-4o (2024-08-06) OpenAI 49.2% 2025-01-27
243 Qwen2.5-VL 72B Instruct Alibaba 49.2% 2025-01-27
244 Mistral Small 3.2 Mistral 49.1% 2026-08-28
245 Mistral Large 2407 Mistral 49.0% 2025-01-27
246 GPT-4.1 nano OpenAI 48.9% 2025-04-14
247 GPT-4o (2024-05-13) OpenAI 48.9% 2025-01-27
248 GPT-5 Nano Minimal OpenAI 48.5% 2026-07-13
249 Qwen Plus Alibaba 48.1% 2025-04-07
250 GPT-4o (2024-11-20) OpenAI 47.9% 2025-02-05
251 Gemma 3 27B IT Google 47.7% 2026-08-27
252 Magistral Small 1.2 Mistral 47.6% 2026-08-30
253 Mistral Small 3.1 Mistral 47.5% 2025-03-18
254 Qwen3 8B Non-reasoning Alibaba 47.5% 2026-08-27
255 Llama-3.3-70B-Instruct Meta 47.4% 2025-01-27
256 Gemini 1.5 Flash (Sep 2024) Google 47.3% 2025-01-27
257 Mistral Small 3 Mistral 47.3% 2026-08-30
258 Claude 3 Opus Anthropic 47.2% 2025-01-27
259 GPT-4 Turbo OpenAI 46.6% 2025-02-27
260 Tulu 3 (Tülu 3) 70B Ai2 46.3% 2025-01-27
261 Qwen2.5-32B Alibaba 46.1% 2025-01-30
262 GPT OSS 20B High OpenAI 46.0% 2026-08-06
263 Gemini 1.5 Pro (May 2024) Google 45.9% 2025-01-27
264 qwen3-4b-instruct-2507 Unknown 45.8% 2026-08-28
265 GLM-4.7-Flash Non-reasoning Zhipu AI 45.1% 2026-08-30
266 DeepSeek-R1-Distill-Qwen-14B DeepSeek 44.7% 2025-03-10
267 Llama-3.1-70B-Instruct Meta 44.2% 2025-01-27
268 Qwen3-4B Non-reasoning Alibaba 43.6% 2026-08-28
269 WizardLM 2 8x22B Microsoft 43.4% 2025-01-27
270 Qwen Turbo Alibaba 41.8% 2025-04-07
271 Llama-3.2-90B-Vision-Instruct Meta 41.0% 2025-01-27
272 Qwen2-72B Alibaba 40.8% 2025-01-27
273 Claude 3 Sonnet Anthropic 40.6% 2025-01-27
274 Llama 3-70B Meta 40.6% 2025-01-27
275 Gemini 1.5 Flash (May 2024) Google 40.4% 2025-01-27
276 Gemma 3 12B IT Google 39.5% 2026-08-28
277 Mistral Large Mistral 38.8% 2025-01-27
278 Claude Haiku 3.5 Anthropic 38.1% 2025-03-12
279 Qwen3-1.7B Alibaba 38.0% 2026-08-28
280 GPT-4o mini OpenAI 37.7% 2025-01-27
281 Hermes 2 Theta Llama-3 70B Nous Research 37.5% 2025-01-27
282 Gemma 2 27B Google 36.5% 2025-01-27
283 Claude Haiku 3 Anthropic 36.3% 2025-01-27
284 GPT-4 OpenAI 35.7% 2025-10-23
285 Qwen2.5 7B Instruct Alibaba 35.5% 2026-08-30
286 Claude 2 Anthropic 34.7% 2025-01-27
287 Mixtral 8x22B Instruct Mistral 34.1% 2025-01-27
288 Gemini 1.0 Pro Google 34.0% 2025-01-27
289 Eurus-2-7B-PRIME Tsinghua University 33.9% 2025-01-27
290 DeepSeek-R1-Distill-Qwen-1.5B DeepSeek 33.6% 2026-08-28
291 Claude 2.1 Anthropic 33.0% 2025-01-27
292 Gemini 1.5 Flash 8B Google 33.0% 2025-03-12
293 DBRX Databricks 32.9% 2025-01-27
294 Yi-1.5-34B 01.AI 32.0% 2025-01-27
295 Qwen1.5-32B Alibaba 30.7% 2025-01-27
296 Qwen3-1.7B Non-reasoning Alibaba 30.6% 2026-08-28
297 Mixtral 8x7B Instruct v0.1 Mistral 30.6% 2025-01-27
298 Mistral Nemo Mistral 29.9% 2025-01-27
299 Qwen1.5-72B Alibaba 28.8% 2025-01-27
300 granite-4.0-micro Unknown 28.3% 2026-08-30
301 GPT-3.5-turbo OpenAI 28.0% 2025-01-27
302 phi-3-medium 14B Microsoft 27.6% 2025-01-31
303 Gemma 2 9B Google 27.5% 2025-01-27
304 Ministral 8B Instruct Mistral 27.2% 2025-01-27
305 Llama-3.1-8B-Instruct Meta 27.0% 2026-08-27
306 Llama 2-70B Meta 26.3% 2025-01-27
307 Llama 3-8B Meta 26.1% 2025-01-27
308 Ministral 3B Mistral 25.3% 2025-01-27
309 DeepSeek LLM 67B DeepSeek 24.6% 2025-01-27
310 granite-4.0-1b Unknown 24.0% 2026-08-28
311 Llama 3.2 1B Instruct Meta 23.9% 2026-08-30
312 Gemma 3 4B IT Google 23.2% 2026-08-28
313 Gemma 3 1B Google 20.0% 2026-08-28
314 Mistral 7B Instruct v0.3 Mistral 15.2% 2025-01-27
315 Yi-34B 01.AI 14.7% 2025-01-27
316 granite-4.0-350m Unknown 11.2% 2026-08-28
317 DeepSeek R1 0528 Qwen3 8B DeepSeek 9.3% 2026-08-28