Skip to content
Weights Not Walls
Menu

CritPt

Reported

No description yet: we only describe an eval set when we can do it correctly.

Kind
Published by a third party's leaderboard, collected by Epoch AI. The leaderboard is named and linked.
Score shown
Epoch's column "Accuracy", as a percentage, higher is better. The source gives no error bars.
Results
271 in all: 105 for open-weight models, 166 for closed ones. 87 linked to a model page here.

Best open-weight result: mimo-v2.6-pro, 26.6%, number 44 of 271 results.

CritPt results
#ModelWeightsSettingScoreDateSource
1gemini-4-carbon_highGoogle DeepMindclosedeffort high36.0%not datedvia Epoch AI
2claude-fable-5-2_xhighAnthropicclosedeffort xhigh35.7%not datedvia Epoch AI
3claude-fable-5-2_maxAnthropicclosedeffort max35.4%not datedvia Epoch AI
4claude-fable-5-2_highAnthropicclosedeffort high32.9%not datedvia Epoch AI
5gpt-5.6-sol_maxOpenAIclosedeffort max32.3%not datedvia Epoch AI
6claude-opus-5-5_maxAnthropicclosedeffort max31.7%not datedvia Epoch AI
7claude-opus-5-5_xhighAnthropicclosedeffort xhigh31.7%not datedvia Epoch AI
8gpt-6-astra_maxOpenAIclosedeffort max31.7%not datedvia Epoch AI
9gpt-6.1-sol_maxOpenAIclosedeffort max31.7%not datedvia Epoch AI
10gpt-6.1-sol_xhighOpenAIclosedeffort xhigh31.7%not datedvia Epoch AI
11claude-sonnet-5-5_maxAnthropicclosedeffort max31.4%not datedvia Epoch AI
12gpt-6-astra_xhighOpenAIclosedeffort xhigh31.4%not datedvia Epoch AI
13claude-fable-5-1_xhighAnthropicclosedeffort xhigh31.1%not datedvia Epoch AI
14claude-sonnet-5-5_xhighAnthropicclosedeffort xhigh31.1%not datedvia Epoch AI
15claude-fable-5-2_mediumAnthropicclosedeffort medium30.9%not datedvia Epoch AI
16claude-opus-5-5_highAnthropicclosedeffort high30.9%not datedvia Epoch AI
17gpt-6-sol_maxOpenAIclosedeffort max30.9%not datedvia Epoch AI
18gpt-5.5-pro_xhighOpenAIclosedeffort xhigh30.6%not datedvia Epoch AI
19claude-fable-5-1_highAnthropicclosedeffort high30.3%not datedvia Epoch AI
20gpt-5.4-pro-2026-03-05_xhighOpenAIclosedeffort xhigh30.0%not datedvia Epoch AI
21gpt-5.6-terra_maxOpenAIclosedeffort max30.0%not datedvia Epoch AI
22gpt-6.1-sol_highOpenAIclosedeffort high30.0%not datedvia Epoch AI
23claude-fable-5-1_maxAnthropicclosedeffort max29.7%not datedvia Epoch AI
24claude-fable-5-2_lowAnthropicclosedeffort low29.4%not datedvia Epoch AI
25claude-fable-5-1_mediumAnthropicclosedeffort medium29.1%not datedvia Epoch AI
26claude-opus-5_maxAnthropicclosedeffort max29.1%not datedvia Epoch AI
27gpt-6-astra_mediumOpenAIclosedeffort medium29.1%not datedvia Epoch AI
28gpt-6-astra_highOpenAIclosedeffort high28.9%not datedvia Epoch AI
29claude-fable-5_maxAnthropicclosedeffort max28.6%not datedvia Epoch AI
30gpt-5.6-sol_xhighOpenAIclosedeffort xhigh28.6%not datedvia Epoch AI
31claude-opus-5_highAnthropicclosedeffort high28.3%not datedvia Epoch AI
32muse-wonder-1.0_maxMeta AIclosedeffort max28.3%not datedvia Epoch AI
33gpt-6-sol_xhighOpenAIclosedeffort xhigh28.0%not datedvia Epoch AI
34gpt-6.1-terra_maxOpenAIclosedeffort max28.0%not datedvia Epoch AI
35claude-fable-5-1_lowAnthropicclosedeffort low27.7%not datedvia Epoch AI
36claude-opus-5_xhighAnthropicclosedeffort xhigh27.7%not datedvia Epoch AI
37claude-opus-5-5_mediumAnthropicclosedeffort medium27.7%not datedvia Epoch AI
38gpt-6.1-sol_mediumOpenAIclosedeffort medium27.7%not datedvia Epoch AI
39gemini-4-argon_highGoogle DeepMindclosedeffort high27.1%not datedvia Epoch AI
40gpt-5.5_xhighOpenAIclosedeffort xhigh27.1%not datedvia Epoch AI
41gpt-5.6-terra_xhighOpenAIclosedeffort xhigh27.1%not datedvia Epoch AI
42claude-opus-5_mediumAnthropicclosedeffort medium26.9%not datedvia Epoch AI
43gpt-6.1-terra_xhighOpenAIclosedeffort xhigh26.6%not datedvia Epoch AI
44mimo-v2.6-proXiaomi Corpno page matchopendefault26.6%not datedvia Epoch AI
45gpt-6-astra_lowOpenAIclosedeffort low26.3%not datedvia Epoch AI
46muse-spark-1.3_xhighMeta AIclosedeffort xhigh26.0%not datedvia Epoch AI
47gemini-3-deep-think-previewGoogle DeepMindcloseddefault25.7%not datedvia Epoch AI
48gpt-5.6-sol_highOpenAIclosedeffort high25.7%not datedvia Epoch AI
49gpt-6.1-terra_highOpenAIclosedeffort high25.7%not datedvia Epoch AI
50gpt-5.5_highOpenAIclosedeffort high25.4%not datedvia Epoch AI
51gpt-6-sol_highOpenAIclosedeffort high25.4%not datedvia Epoch AI
52gpt-6.1-sol_lowOpenAIclosedeffort low24.9%not datedvia Epoch AI
53muse-spark-1.3_maxMeta AIclosedeffort max24.9%not datedvia Epoch AI
54claude-sonnet-5-5_highAnthropicclosedeffort high24.6%not datedvia Epoch AI
55gpt-6-sol_mediumOpenAIclosedeffort medium24.6%not datedvia Epoch AI
56moonshotai/Kimi-K3.1-ProEpoch: kimi-k3.1-pro_unknown, Moonshotopeneffort unknown24.6%not datedvia Epoch AI
57deepseek-ai/DeepSeek-V4.1-Flash-1017Epoch: deepseek-v4.1-flash-1017_max, DeepSeekopeneffort max24.0%not datedvia Epoch AI
58gpt-5.4-2026-03-05_xhighOpenAIclosedeffort xhigh23.4%not datedvia Epoch AI
59moonshotai/Kimi-K3Epoch: kimi-k3_max, Moonshotopeneffort max23.4%not datedvia Epoch AI
60claude-opus-5_lowAnthropicclosedeffort low23.1%not datedvia Epoch AI
61gemini-4-argon_mediumGoogle DeepMindclosedeffort medium23.1%not datedvia Epoch AI
62gpt-5.6-sol_mediumOpenAIclosedeffort medium22.9%not datedvia Epoch AI
63gpt-5.6-terra_highOpenAIclosedeffort high22.9%not datedvia Epoch AI
64claude-haiku-5-5_xhighAnthropicclosedeffort xhigh22.6%not datedvia Epoch AI
65gpt-6.1-terra_mediumOpenAIclosedeffort medium21.4%not datedvia Epoch AI
66claude-opus-4-8_maxAnthropicclosedeffort max20.9%not datedvia Epoch AI
67zai-org/GLM-5.2Epoch: glm-5.2_max, Z.ai (Zhipu AI)openeffort max20.9%not datedvia Epoch AI
68step-5-preview_unknownStepFunclosedeffort unknown20.9%not datedvia Epoch AI
69gpt-5.6-luna_maxOpenAIclosedeffort max20.6%not datedvia Epoch AI
70gpt-5.6-luna_xhighOpenAIclosedeffort xhigh20.6%not datedvia Epoch AI
71qwen3.8-max_unknownAlibabaclosedeffort unknown20.0%not datedvia Epoch AI
72gpt-6-astra_noneOpenAIclosedeffort none19.7%not datedvia Epoch AI
73grok-4.6_xhighxAIclosedeffort xhigh19.7%not datedvia Epoch AI
74gpt-6-luna_maxOpenAIclosedeffort max19.4%not datedvia Epoch AI
75zai-org/GLM-5.3Epoch: glm-5.3_max, Z.ai (Zhipu AI)openeffort max19.1%not datedvia Epoch AI
76claude-haiku-5-5_maxAnthropicclosedeffort max18.9%not datedvia Epoch AI
77claude-haiku-5-5_highAnthropicclosedeffort high18.6%not datedvia Epoch AI
78deepseek-ai/DeepSeek-V4-Pro-0813Epoch: deepseek-v4-pro-0813_high, DeepSeekopeneffort high18.6%not datedvia Epoch AI
79gpt-5.5_mediumOpenAIclosedeffort medium18.6%not datedvia Epoch AI
80gemini-3.8-flash_highGoogle DeepMindclosedeffort high18.3%not datedvia Epoch AI
81deepseek-ai/DeepSeek-V4-Pro-0813Epoch: deepseek-v4-pro-0813_max, DeepSeekopeneffort max18.0%not datedvia Epoch AI
82grok-4.7_highxAIclosedeffort high18.0%not datedvia Epoch AI
83claude-opus-5-5_lowAnthropicclosedeffort low17.7%not datedvia Epoch AI
84gemini-3.1-pro-previewGoogle DeepMindcloseddefault17.7%not datedvia Epoch AI
85grok-4.6_mediumxAIclosedeffort medium17.7%not datedvia Epoch AI
86grok-4.7_xhighxAIclosedeffort xhigh17.7%not datedvia Epoch AI
87muse-spark-1.2_xhighMeta AIclosedeffort xhigh17.7%not datedvia Epoch AI
88qwen3.8-max-0902_unknownAlibabaclosedeffort unknown17.7%not datedvia Epoch AI
89gpt-5.6-terra_mediumOpenAIclosedeffort medium17.4%not datedvia Epoch AI
90gpt-6-luna_xhighOpenAIclosedeffort xhigh17.4%not datedvia Epoch AI
91grok-4.6_highxAIclosedeffort high17.1%not datedvia Epoch AI
92claude-sonnet-5_maxAnthropicclosedeffort max16.9%not datedvia Epoch AI
93claude-sonnet-5-5_mediumAnthropicclosedeffort medium16.9%not datedvia Epoch AI
94gpt-5.3-codex_xhighOpenAIclosedeffort xhigh16.9%not datedvia Epoch AI
95deepseek-ai/DeepSeek-V4-Flash-0731Epoch: deepseek-v4-flash-0731_max, DeepSeekopeneffort max16.6%not datedvia Epoch AI
96gpt-5.6-luna_highOpenAIclosedeffort high16.6%not datedvia Epoch AI
97gpt-6-sol_lowOpenAIclosedeffort low16.3%not datedvia Epoch AI
98claude-sonnet-5_xhighAnthropicclosedeffort xhigh15.4%not datedvia Epoch AI
99zai-org/GLM-5.3-FlashEpoch: glm-5.3-flash_unknown, Z.ai (Zhipu AI)openeffort unknown15.4%not datedvia Epoch AI
100gpt-6-luna_highOpenAIclosedeffort high15.4%not datedvia Epoch AI
101grok-4.5_highxAIclosedeffort high15.4%not datedvia Epoch AI
102gpt-6.1-terra_lowOpenAIclosedeffort low15.1%not datedvia Epoch AI
103muse-spark-1.1_xhighMeta AIclosedeffort xhigh15.1%not datedvia Epoch AI
104muse-spark-1.1Meta AIcloseddefault15.1%not datedvia Epoch AI
105gpt-5.6-sol_lowOpenAIclosedeffort low14.9%not datedvia Epoch AI
106meta-models/Muse-Spark-Open-816B-A42BEpoch: Muse-Spark-Open-816B-A42B_xhigh, Meta AIopeneffort xhigh14.9%not datedvia Epoch AI
107zai-org/GLM-5.3Epoch: glm-5.3_low, Z.ai (Zhipu AI)openeffort low14.6%not datedvia Epoch AI
108deepseek-ai/DeepSeek-V4.1-FlashEpoch: deepseek-v4.1-flash_max, DeepSeekopeneffort max14.3%not datedvia Epoch AI
109gemini-3.7-flash_highGoogle DeepMindclosedeffort high14.3%not datedvia Epoch AI
110grok-4.7_lowxAIclosedeffort low13.4%not datedvia Epoch AI
111qwen3.7-maxAlibabacloseddefault13.4%not datedvia Epoch AI
112beam-1.0_unknownReflectionno page matchopeneffort unknown13.1%not datedvia Epoch AI
113gemini-3.5-flash_highGoogle DeepMindclosedeffort high13.1%not datedvia Epoch AI
114claude-haiku-5-5_mediumAnthropicclosedeffort medium12.9%not datedvia Epoch AI
115deepseek-ai/DeepSeek-V4-ProEpoch: deepseek-v4-pro_max, DeepSeekopeneffort max12.9%not datedvia Epoch AI
116gpt-5-2025-08-07_highOpenAIclosedeffort high12.6%not datedvia Epoch AI
117gemini-3.8-flash_mediumGoogle DeepMindclosedeffort medium12.3%not datedvia Epoch AI
118claude-opus-4-7_maxAnthropicclosedeffort max12.0%not datedvia Epoch AI
119mimo-v2.6-flashXiaomi Corpno page matchopendefault12.0%not datedvia Epoch AI
120claude-sonnet-5-5_lowAnthropicclosedeffort low11.4%not datedvia Epoch AI
121muse-sparkMeta AIcloseddefault11.3%not datedvia Epoch AI
122mistral-large-4-0-oss_mediumMistral AIno page matchopeneffort medium11.1%not datedvia Epoch AI
123gemini-3.6-flash_highGoogle DeepMindclosedeffort high10.6%not datedvia Epoch AI
124gpt-6-luna_mediumOpenAIclosedeffort medium10.6%not datedvia Epoch AI
125mistral-large-4-0_unknownMistral AIno page matchopeneffort unknown10.6%not datedvia Epoch AI
126deepseek-ai/DeepSeek-V4-ProEpoch: deepseek-v4-pro_high, DeepSeekopeneffort high10.0%not datedvia Epoch AI
127gpt-5.4-mini-2026-03-17_xhighOpenAIclosedeffort xhigh10.0%not datedvia Epoch AI
128moonshotai/Kimi-K2.7-CodeEpoch: kimi-k2.7-code, Moonshotopendefault10.0%not datedvia Epoch AI
129mistral-large-4-0-oss_highMistral AIno page matchopeneffort high10.0%not datedvia Epoch AI
130gemini-3.7-flash_mediumGoogle DeepMindclosedeffort medium9.4%not datedvia Epoch AI
131gpt-5.6-terra_lowOpenAIclosedeffort low9.4%not datedvia Epoch AI
132gpt-5.4-nano-2026-03-17_xhighOpenAIclosedeffort xhigh9.3%not datedvia Epoch AI
133claude-haiku-5-5_lowAnthropicclosedeffort low9.1%not datedvia Epoch AI
134grok-build-0.1xAIcloseddefault9.1%not datedvia Epoch AI
135qwen3.7-plusAlibabacloseddefault9.1%not datedvia Epoch AI
136claude-sonnet-5_mediumAnthropicclosedeffort medium8.6%not datedvia Epoch AI
137thinkingmachines/Inkling-SmallEpoch: inkling-small, Thinking Machinesopendefault8.3%not datedvia Epoch AI
138gpt-5.5_lowOpenAIclosedeffort low8.0%not datedvia Epoch AI
139grok-4.3_highxAIclosedeffort high8.0%not datedvia Epoch AI
140moonshotai/Kimi-K2.6Epoch: kimi-k2.6, Moonshotopendefault8.0%not datedvia Epoch AI
141deepseek-ai/DeepSeek-V4-FlashEpoch: deepseek-v4-flash_max, DeepSeekopeneffort max7.1%not datedvia Epoch AI
142gemini-3-pro-previewGoogle DeepMindcloseddefault6.9%not datedvia Epoch AI
143gemini-3.7-flash_lowGoogle DeepMindclosedeffort low5.7%not datedvia Epoch AI
144grok-4.6_lowxAIclosedeffort low5.7%not datedvia Epoch AI
145thinkingmachines/InklingEpoch: Inkling_xhigh, Thinking Machinesopeneffort xhigh5.4%not datedvia Epoch AI
146Qwen/Qwen3.8-27BEpoch: qwen3.8-27b_xhigh, Alibabaopeneffort xhigh5.4%not datedvia Epoch AI
147gpt-5.6-sol_noneOpenAIclosedeffort none5.1%not datedvia Epoch AI
148gpt-5.1-2025-11-13_unknownOpenAIclosedeffort unknown4.9%not datedvia Epoch AI
149gpt-5.6-luna_mediumOpenAIclosedeffort medium4.9%not datedvia Epoch AI
150gpt-6.1-terra_noneOpenAIclosedeffort none4.9%not datedvia Epoch AI
151claude-sonnet-5_lowAnthropicclosedeffort low4.6%not datedvia Epoch AI
152zai-org/GLM-5.1Epoch: glm-5.1, Z.ai (Zhipu AI)opendefault4.6%not datedvia Epoch AI
153gemini-3.8-flash_lowGoogle DeepMindclosedeffort low4.0%not datedvia Epoch AI
154gpt-6-sol_noneOpenAIclosedeffort none4.0%not datedvia Epoch AI
155XiaomiMiMo/MiMo-V2.5-ProEpoch: mimo-v2.5-pro, Xiaomi Corpopendefault4.0%not datedvia Epoch AI
156XiaomiMiMo/MiMo-V2.5Epoch: mimo-v2.5, Xiaomi Corpopendefault3.7%not datedvia Epoch AI
157MiniMaxAI/MiniMax-M3Epoch: MiniMax-M3, MiniMaxopendefault3.7%not datedvia Epoch AI
158inclusionAI/Ring-2.6-1TEpoch: Ring-2.6-1T, Ant Groupopendefault3.7%not datedvia Epoch AI
159deepseek-ai/DeepSeek-V4-FlashEpoch: deepseek-v4-flash_high, DeepSeekopeneffort high3.4%not datedvia Epoch AI
160claude-sonnet-4-6_maxAnthropicclosedeffort max3.1%not datedvia Epoch AI
161zai-org/GLM-5.2Epoch: glm-5.2_none, Z.ai (Zhipu AI)openeffort none3.1%not datedvia Epoch AI
162moonshotai/Kimi-K2.5Epoch: kimi-k2.5, Moonshotopendefault3.1%not datedvia Epoch AI
163moonshotai/Kimi-K3Epoch: kimi-k3_low, Moonshotopeneffort low3.1%not datedvia Epoch AI
164nemotron-3-superNvidiano page matchopendefault3.1%not datedvia Epoch AI
165nemotron-3-ultraNvidiano page matchopendefault3.1%not datedvia Epoch AI
166deepseek-ai/DeepSeek-V3.2-ExpEpoch: DeepSeek-V3.2-Exp_thinking, DeepSeekopeneffort thinking2.9%not datedvia Epoch AI
167qwen3.6-plusAlibabacloseddefault2.9%not datedvia Epoch AI
168gpt-5.6-luna_lowOpenAIclosedeffort low2.6%not datedvia Epoch AI
169gpt-6-luna_lowOpenAIclosedeffort low2.6%not datedvia Epoch AI
170muse-glimmer_highMeta AIno page matchopeneffort high2.6%not datedvia Epoch AI
171stepfun-ai/Step-3.7-FlashEpoch: step-3.7-flash, StepFunopendefault2.3%not datedvia Epoch AI
172gemini-2.5-proGoogle DeepMindcloseddefault2.0%not datedvia Epoch AI
173gpt-5.6-terra_noneOpenAIclosedeffort none2.0%not datedvia Epoch AI
174deepseek-ai/DeepSeek-V3.1-TerminusEpoch: DeepSeek-V3.1-Terminus, DeepSeekopendefault1.7%not datedvia Epoch AI
175zai-org/GLM-4.7Epoch: glm-4.7, Z.ai (Zhipu AI)opendefault1.7%not datedvia Epoch AI
176google/gemma-4-31B-itEpoch: gemma-4-31b-it, Google DeepMindopendefault1.4%not datedvia Epoch AI
177gpt-5.5_noneOpenAIclosedeffort none1.4%not datedvia Epoch AI
178openai/gpt-oss-20bEpoch: gpt-oss-20b_high, OpenAIopeneffort high1.4%not datedvia Epoch AI
179claude-sonnet-4-5-20250929_unknownAnthropicclosedeffort unknown1.1%not datedvia Epoch AI
180claude-sonnet-5_highAnthropicclosedeffort high1.1%not datedvia Epoch AI
181gemini-3.1-flash-liteGooglecloseddefault1.1%not datedvia Epoch AI
182zai-org/GLM-4.6Epoch: glm-4.6, Z.ai (Zhipu AI),Tsinghua Universityopendefault1.1%not datedvia Epoch AI
183gpt-6-luna_noneOpenAIclosedeffort none1.1%not datedvia Epoch AI
184o3-2025-04-16_highOpenAIclosedeffort high1.1%not datedvia Epoch AI
185openai/gpt-oss-120bEpoch: openai/gpt-oss-120b_high, OpenAIopeneffort high1.1%not datedvia Epoch AI
186deepseek-ai/DeepSeek-R1Epoch: DeepSeek-R1, DeepSeekopendefault1.1%not datedvia Epoch AI
187gemini-2.5-flashGoogle DeepMindcloseddefault1.1%not datedvia Epoch AI
188Qwen/Qwen3.5-122B-A10BEpoch: qwen3.5-122b-a10b_none, Alibabaopeneffort none0.9%not datedvia Epoch AI
189Qwen/Qwen3.5-397B-A17BEpoch: qwen3.5-397b-a17b_none, Alibabaopeneffort none0.9%not datedvia Epoch AI
190Qwen/Qwen3.6-27BEpoch: qwen3.6-27b_none, Alibabaopeneffort none0.9%not datedvia Epoch AI
191trinity-large-thinkingArcee AIno page matchopendefault0.9%not datedvia Epoch AI
192mercury-2Inception Labscloseddefault0.8%not datedvia Epoch AI
193o4-mini-2025-04-16_highOpenAIclosedeffort high0.6%not datedvia Epoch AI
194MiniMaxAI/MiniMax-M2.7Epoch: MiniMax-M2.7, MiniMaxopendefault0.6%not datedvia Epoch AI
195Qwen/Qwen3.5-35B-A3BEpoch: qwen3.5-35b-a3b_none, Alibabaopeneffort none0.6%not datedvia Epoch AI
196Qwen/Qwen3.5-9BEpoch: qwen3.5-9B_none, Alibabaopeneffort none0.6%not datedvia Epoch AI
197claude-opus-4-20250514_unknownAnthropicclosedeffort unknown0.3%not datedvia Epoch AI
198claude-sonnet-4-20250514_unknownAnthropicclosedeffort unknown0.3%not datedvia Epoch AI
199command-a-plus-05-2026Cohere,Cohere Labs (formerly Cohere for AI)no page matchopendefault0.3%not datedvia Epoch AI
200deepseek-ai/DeepSeek-V4.1-FlashEpoch: deepseek-v4.1-flash_none, DeepSeekopeneffort none0.3%not datedvia Epoch AI
201deepseek-ai/DeepSeek-V4.1-Flash-1017Epoch: deepseek-v4.1-flash-1017_none, DeepSeekopeneffort none0.3%not datedvia Epoch AI
202gpt-5.6-luna_noneOpenAIclosedeffort none0.3%not datedvia Epoch AI
203magistral-medium-2509Mistral AIcloseddefault0.3%not datedvia Epoch AI
204mistralai/Magistral-Small-2509Epoch: magistral-small-2509, Mistral AIopendefault0.3%not datedvia Epoch AI
205o3-mini-2025-01-31_highOpenAIclosedeffort high0.3%not datedvia Epoch AI
206Qwen/Qwen3-30B-A3B-Thinking-2507Epoch: qwen3-30b-a3b-thinking-2507, Alibabaopendefault0.3%not datedvia Epoch AI
207Qwen/Qwen3-32BEpoch: Qwen3-32B, Alibabaopendefault0.3%not datedvia Epoch AI
208Qwen/Qwen3.5-9BEpoch: qwen3.5-9B, Alibabaopendefault0.3%not datedvia Epoch AI
209Qwen/Qwen3.6-35B-A3BEpoch: qwen3.6-35b-a3b, Alibabaopendefault0.3%not datedvia Epoch AI
210Qwen/Qwen3.8-27BEpoch: qwen3.8-27b_none, Alibabaopeneffort none0.3%not datedvia Epoch AI
211amazon.nova-micro-v1:0Amazoncloseddefault0.0%not datedvia Epoch AI
212CohereLabs/c4ai-command-a-03-2025Epoch: c4ai-command-a-03-2025, Cohereopendefault0.0%not datedvia Epoch AI
213meta-llama/Llama-4-Maverick-17B-128E-InstructEpoch: chutes/Llama-4-Maverick-17B-128E-Instruct, Meta AIopendefault0.0%not datedvia Epoch AI
214claude-3-5-haiku-20241022Anthropiccloseddefault0.0%not datedvia Epoch AI
215claude-haiku-4-5-20251001_unknownAnthropicclosedeffort unknown0.0%not datedvia Epoch AI
216cogito-671b-v2.1Deep Cogitono page matchopendefault0.0%not datedvia Epoch AI
217deepseek-ai/DeepSeek-V3Epoch: DeepSeek-V3, DeepSeekopendefault0.0%not datedvia Epoch AI
218deepseek-ai/DeepSeek-V3-0324Epoch: DeepSeek-V3-0324, DeepSeekopendefault0.0%not datedvia Epoch AI
219deepseek-ai/DeepSeek-V4-Pro-0813Epoch: deepseek-v4-pro-0813_none, DeepSeekopeneffort none0.0%not datedvia Epoch AI
220devstral-small-2512Mistral AIno page matchopendefault0.0%not datedvia Epoch AI
221gemini-3.5-flash-liteGoogle DeepMindcloseddefault0.0%not datedvia Epoch AI
222google/gemma-3-12b-itEpoch: gemma-3-12b-it, Google DeepMindopendefault0.0%not datedvia Epoch AI
223google/gemma-3-270m-itEpoch: gemma-3-270m-it, Google DeepMindopendefault0.0%not datedvia Epoch AI
224google/gemma-3-27b-itEpoch: gemma-3-27b-it, Google DeepMindopendefault0.0%not datedvia Epoch AI
225gemma-4-26b-a4bGoogle DeepMindno page matchopendefault0.0%not datedvia Epoch AI
226gpt-4.1-mini-2025-04-14OpenAIcloseddefault0.0%not datedvia Epoch AI
227gpt-4.1-nano-2025-04-14OpenAIcloseddefault0.0%not datedvia Epoch AI
228gpt-4o-2024-11-20OpenAIcloseddefault0.0%not datedvia Epoch AI
229gpt-5-2025-08-07_minimalOpenAIclosedeffort minimal0.0%not datedvia Epoch AI
230gpt-5-mini-2025-08-07_highOpenAIclosedeffort high0.0%not datedvia Epoch AI
231gpt-5-mini-2025-08-07_unknownOpenAIclosedeffort unknown0.0%not datedvia Epoch AI
232gpt-5.5-instantOpenAIcloseddefault0.0%not datedvia Epoch AI
233openai/gpt-oss-20bEpoch: gpt-oss-20b_low, OpenAIopeneffort low0.0%not datedvia Epoch AI
234ibm-granite/granite-4.0-350mEpoch: granite-4.0-350mopendefault0.0%not datedvia Epoch AI
235ibm-granite/granite-4.0-microEpoch: granite-4.0-microopendefault0.0%not datedvia Epoch AI
236ibm-granite/granite-4.1-30bEpoch: granite-4.1-30b, IBMopendefault0.0%not datedvia Epoch AI
237grok-4.3_nonexAIclosedeffort none0.0%not datedvia Epoch AI
238grok-4.3_unknownxAIclosedeffort unknown0.0%not datedvia Epoch AI
239meta-llama/Llama-3.1-405B-InstructEpoch: Llama-3.1-405B-Instruct, Meta AIopendefault0.0%not datedvia Epoch AI
240meta-llama/Llama-3.1-8B-InstructEpoch: Llama-3.1-8B-Instruct, Meta AIopendefault0.0%not datedvia Epoch AI
241meta-llama/Llama-3.2-11B-Vision-InstructEpoch: Llama-3.2-11B-Vision-Instruct, Meta AIopendefault0.0%not datedvia Epoch AI
242meta-llama/Llama-3.3-70B-InstructEpoch: Llama-3.3-70B-Instruct, Meta AIopendefault0.0%not datedvia Epoch AI
243meta-llama/Llama-4-Maverick-17B-128E-InstructEpoch: Llama-4-Maverick-17B-128E-Instruct, Meta AIopendefault0.0%not datedvia Epoch AI
244meta-llama/Llama-4-Scout-17B-16E-InstructEpoch: Llama-4-Scout-17B-16E-Instruct, Meta AIopendefault0.0%not datedvia Epoch AI
245mercury-2.5_unknownInception Labsclosedeffort unknown0.0%not datedvia Epoch AI
246XiaomiMiMo/MiMo-V2-FlashEpoch: mimo-v2-flash, Xiaomi Corpopendefault0.0%not datedvia Epoch AI
247mistral-large-2512Mistral AIno page matchopendefault0.0%not datedvia Epoch AI
248mistral-medium-2508Mistral AIcloseddefault0.0%not datedvia Epoch AI
249mistral-medium-2604Mistral AIno page matchopendefault0.0%not datedvia Epoch AI
250mistral-small-2503Mistral AIno page matchopendefault0.0%not datedvia Epoch AI
251mistral-small-2506Mistral AIno page matchopendefault0.0%not datedvia Epoch AI
252nova-2.0-pro-preview_lowAmazonclosedeffort low0.0%not datedvia Epoch AI
253nova-2.0-pro-preview_mediumAmazonclosedeffort medium0.0%not datedvia Epoch AI
254nova-2.0-pro-preview_noneAmazonclosedeffort none0.0%not datedvia Epoch AI
255nvidia/NVIDIA-Nemotron-Nano-9B-v2Epoch: nvidia-nemotron-nano-9b-v2opendefault0.0%not datedvia Epoch AI
256openai/gpt-oss-120bEpoch: openai/gpt-oss-120b_low, OpenAIopeneffort low0.0%not datedvia Epoch AI
257microsoft/phi-4Epoch: phi-4, Microsoft Researchopendefault0.0%not datedvia Epoch AI
258microsoft/Phi-4-mini-instructEpoch: Phi-4-mini-instruct, Microsoftopendefault0.0%not datedvia Epoch AI
259Qwen/Qwen3-235B-A22B-Thinking-2507Epoch: qwen/qwen3-235b-a22b-thinking-2507, Alibabaopendefault0.0%not datedvia Epoch AI
260Qwen/Qwen3-14BEpoch: qwen3-14b, Alibabaopendefault0.0%not datedvia Epoch AI
261Qwen/Qwen3-8BEpoch: qwen3-8b, Alibabaopendefault0.0%not datedvia Epoch AI
262Qwen/Qwen3-Coder-NextEpoch: qwen3-coder-nextopendefault0.0%not datedvia Epoch AI
263Qwen/Qwen3.5-0.8BEpoch: qwen3.5-0.8b, Alibabaopendefault0.0%not datedvia Epoch AI
264Qwen/Qwen3.5-0.8BEpoch: qwen3.5-0.8b_none, Alibabaopeneffort none0.0%not datedvia Epoch AI
265Qwen/Qwen3.5-2BEpoch: qwen3.5-2b_none, Alibabaopeneffort none0.0%not datedvia Epoch AI
266Qwen/Qwen3.5-4BEpoch: qwen3.5-4b_none, Alibabaopeneffort none0.0%not datedvia Epoch AI
267Qwen/Qwen3.6-35B-A3BEpoch: qwen3.6-35b-a3b_none, Alibabaopeneffort none0.0%not datedvia Epoch AI
268Qwen/Qwen3.8-27BEpoch: qwen3.8-27b_low, Alibabaopeneffort low0.0%not datedvia Epoch AI
269Qwen/Qwen3.8-27BEpoch: qwen3.8-27b_medium, Alibabaopeneffort medium0.0%not datedvia Epoch AI
270RekaAI/reka-flash-3Epoch: reka-flash-3, Reka AIopendefault0.0%not datedvia Epoch AI
271solar-pro-3Upstagecloseddefault0.0%not datedvia Epoch AI

Open-weight rows are shaded. Dates are when the result was run or evaluated, where the data says. Data from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Epoch AI. Method