The Wayback Machine - https://web.archive.org/web/20260603180559/https://artificialanalysis.ai/evaluations/gdpval-aa
All evaluations

GDPval-AA Leaderboard

GDPval-AA is Artificial Analysis' evaluation framework for OpenAI's GDPval dataset. It tests AI models on real-world tasks across 44 occupations and 9 major industries. Models are given shell access and web browsing capabilities in an agentic loop via Stirrup to solve tasks, with Elo ratings derived from blind pairwise comparisons.
See example tasks

The GDPval gold public dataset includes 220 tasks developed by OpenAI in collaboration with industry professionals to reflect real-world complexity.
The benchmark requires models to produce diverse outputs including documents, slides, diagrams, and spreadsheets, mirroring actual work products across finance, healthcare, legal, and other professional domains.

All evaluations are conducted independently by Artificial Analysis. More information can be found on our Intelligence Benchmarking Methodology page.

Publication

View on arXiv

GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks

Tejal Patwardhan, Rachel Dias, Elizabeth Proehl, Grace Kim, Michele Wang, Olivia Watkins, Simรณn Posada Fishman, Marwan Aljubeh, Phoebe Thacker, Laurance Fauconnet, Natalie S. Kim, Patrick Chao, Samuel Miserendino, Gildas Chabot, David Li, Michael Sharman, Alexandra Barr, Amelia Glaese, Jerry Tworek.

We introduce GDPval, a benchmark designed to evaluate AI models on real-world, economically valuable tasks across 44 occupations. The dataset encompasses 1,320 tasks derived from nine major industries contributing significantly to the U.S. GDP. These tasks were developed in collaboration with industry professionals averaging 14 years of experience, ensuring they accurately represent real-world complexities. The evaluation requires models to produce diverse outputs, including documents, slides, diagrams, and spreadsheets, mirroring actual work products. Initial results indicate that frontier AI models are approaching the quality of work produced by human experts, with models able to perform certain professional tasks approximately 100 times faster and at a fraction of the cost compared to human experts.

GDPval

Claude Opus 4.8 (Adaptive Reasoning, Max Effort) scores the highest on GDPval with a score of 1890, followed by GPT-5.5 (xhigh) with a score of 1769, and GPT-5.5 (high) with a score of 1755

GDPval-AA Elo

GDPval-AA Leaderboard

Elo scores for agentic performance on real-world work tasks using web and shell access via Stirrup, an open-source harness developed by Artificial Analysis
Stirrup Agent Harness
AI Chatbot

Chatbots

GDPval-AA: AI Chatbots

Elo scores for AI chatbots tested in the GDPval-AA evaluation
AI Chatbot

Score Comparisons

GDPval-AA: Elo vs. Artificial Analysis Intelligence Index

GDPval-AA Elo ยท Artificial Analysis Intelligence Index
Most attractive quadrant
Alibaba
Amazon
Anthropic
DeepSeek
Google
Kimi
MBZUAI Institute of Foundation Models
Meta
MiniMax
Mistral
NVIDIA
OpenAI
Upstage
xAI
Xiaomi
Z AI

Artificial Analysis Intelligence Index v4.0 includes: GDPval-AA, ๐œยฒ-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Token Usage

GDPval-AA: Output Token Usage

Output tokens used to run the evaluation
Reasoning tokens
Answer tokens

The total number of tokens used to run the evaluation, including input tokens (prompt), reasoning tokens (for reasoning models), and answer tokens (final response).

Average Turns

GDPval-AA: Average Turns per Task

Average number of turns per task

Score vs. Release Date

GDPval-AA: Elo vs. Release Date

Most attractive region
Alibaba
Amazon
Anthropic
DeepSeek
Google
Kimi
MBZUAI Institute of Foundation Models
Meta
MiniMax
Mistral
NVIDIA
OpenAI
Upstage
xAI
Xiaomi
Z AI

GDPval-AA Leaderboard

1
Anthropic logoAnthropic
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)
1890-34 / +35May 2026
2
OpenAI logoOpenAI
GPT-5.5 (xhigh)
1769-32 / +31Apr 2026
3
OpenAI logoOpenAI
GPT-5.5 (high)
1755-31 / +32Apr 2026
4
Anthropic logoAnthropic
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
1753-41 / +40Apr 2026
5
Anthropic logoAnthropic
Claude Opus 4.7 (Non-reasoning, High Effort)
1677-27 / +28Apr 2026
6
Anthropic logoAnthropic
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)
1676-26 / +29Feb 2026
7
OpenAI logoOpenAI
GPT-5.4 (xhigh)
1674-34 / +32Mar 2026
8
Google logoGoogle
Gemini 3.5 Flash (medium)
1659-29 / +28May 2026
9
Google logoGoogle
Gemini 3.5 Flash (high)
1656-26 / +30May 2026
10
OpenAI logoOpenAI
GPT-5.5 (medium)
1650-24 / +28Apr 2026
11
Anthropic logoAnthropic
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
1619-31 / +33Feb 2026
12
Anthropic logoAnthropic
Claude Sonnet 4.6 (Non-reasoning, High Effort)
1599-26 / +28Feb 2026
13
Anthropic logoAnthropic
Claude Opus 4.6 (Non-reasoning, High Effort)
1591-23 / +27Feb 2026
14
Xiaomi logoXiaomi
MiMo-V2.5-Pro
1571-27 / +28Apr 2026
15
DeepSeek logoDeepSeek
DeepSeek V4 Pro (Reasoning, High Effort)
1558-29 / +31Apr 2026
16
DeepSeek logoDeepSeek
DeepSeek V4 Pro (Reasoning, Max Effort)
1554-29 / +29Apr 2026
17
Xiaomi logoXiaomi
MiMo-V2.5
1551-25 / +25Apr 2026
18
Alibaba logoAlibaba
Qwen3.7 Max
1546-25 / +27May 2026
19
Z AI logoZ AI
GLM-5.1 (Reasoning)
1535-0 / +0Apr 2026
20
Alibaba logoAlibaba
Qwen3.7 Plus
1523-24 / +25Jun 2026
21
MiniMax logoMiniMax
MiniMax-M2.7
1505-24 / +26Mar 2026
22
Alibaba logoAlibaba
Qwen3.6 Max Preview
1504-20 / +21Apr 2026
23
OpenAI logoOpenAI
GPT-5.4 (low)
1503-27 / +29Mar 2026
24
Z AI logoZ AI
GLM-5-Turbo
1497-21 / +23Mar 2026
25
xAI logoxAI
Grok 4.3 (high)
1495-25 / +23Apr 2026
26
Z AI logoZ AI
GLM-5.1 (Non-reasoning)
1494-25 / +26Apr 2026
27
OpenAI logoOpenAI
GPT-5.3 Codex (xhigh)
1482-25 / +25Feb 2026
28
Kimi logoKimi
Kimi K2.6
1481-25 / +26Apr 2026
29
DeepSeek logoDeepSeek
DeepSeek V4 Pro (Non-reasoning)
1476-24 / +27Apr 2026
30
OpenAI logoOpenAI
GPT-5.2 (xhigh)
1467-27 / +26Dec 2025
31
Anthropic logoAnthropic
Claude Sonnet 4.6 (Non-reasoning, Low Effort)
1456-23 / +27Feb 2026
32
Anthropic logoAnthropic
Claude Opus 4.5 (Reasoning)
1452-24 / +25Nov 2025
33
OpenAI logoOpenAI
GPT-5.5 (low)
1443-23 / +25Apr 2026
34
Google logoGoogle
Gemini 3.5 Flash (minimal)
1440-24 / +27May 2026
35
OpenAI logoOpenAI
GPT-5.4 mini (xhigh)
1438-23 / +26Mar 2026
36
Anthropic logoAnthropic
Claude Opus 4.5 (Non-reasoning)
1419-21 / +23Nov 2025
37
Meta logoMeta
Muse Spark
1417-23 / +23Apr 2026
38
DeepSeek logoDeepSeek
DeepSeek V4 Flash (Reasoning, High Effort)
1414-25 / +26Apr 2026
39
Xiaomi logoXiaomi
MiMo-V2-Pro
1406-22 / +22Mar 2026
40
OpenAI logoOpenAI
GPT-5.2 (medium)
1405-21 / +23Dec 2025
41
Alibaba logoAlibaba
Qwen3.6 27B (Reasoning)
1403-23 / +24Apr 2026
42
Z AI logoZ AI
GLM-5 (Reasoning)
1395-23 / +23Feb 2026
43
DeepSeek logoDeepSeek
DeepSeek V4 Flash (Non-reasoning)
1392-25 / +28Apr 2026
44
DeepSeek logoDeepSeek
DeepSeek V4 Flash (Reasoning, Max Effort)
1388-20 / +34Apr 2026
45
Alibaba logoAlibaba
Qwen3.6 27B (Non-reasoning)
1385-21 / +26Apr 2026
46
Alibaba logoAlibaba
Qwen3.6 Plus
1354-23 / +24Apr 2026
47
Xiaomi logoXiaomi
MiMo-V2-Omni-0327
1344-24 / +25Mar 2026
48
OpenAI logoOpenAI
GPT-5.4 (Non-reasoning)
1342-26 / +26Mar 2026
49
Z AI logoZ AI
GLM 5V Turbo (Reasoning)
1330-22 / +24Apr 2026
50
Kimi logoKimi
Kimi K2.6 (Non-reasoning)
1326-25 / +28Apr 2026
51
Google logoGoogle
Gemini 3 Deep Think
1324-30 / +31Feb 2026
52
Z AI logoZ AI
GLM-5 (Non-reasoning)
1323-23 / +24Feb 2026
53
 logo
Claude Pro - 4.5 Opus (Extended Thinking)
1319-41 / +38-
54
Xiaomi logoXiaomi
MiMo-V2-Omni
1319-21 / +23Mar 2026
55
Anthropic logoAnthropic
Claude 4.5 Sonnet (Reasoning)
1317-23 / +26Sep 2025
56
OpenAI logoOpenAI
GPT-5.4 mini (medium)
1316-22 / +24Mar 2026
57
OpenAI logoOpenAI
GPT-5.5 (Non-reasoning)
1315-23 / +25Apr 2026
58
Google logoGoogle
Gemini 3.1 Pro Preview
1314-26 / +27Feb 2026
59
xAI logoxAI
Grok 4.3 (medium)
1310-24 / +26Apr 2026
60
Anthropic logoAnthropic
Claude 4.5 Sonnet (Non-reasoning)
1306-21 / +24Sep 2025
61
xAI logoxAI
Grok 4.3 (Non-reasoning)
1300-24 / +25Apr 2026
62
Alibaba logoAlibaba
Qwen3.6 35B A3B (Reasoning)
1299-23 / +25Apr 2026
63
StepFun logoStepFun
Step 3.7 Flash
1298-25 / +25May 2026
64
Xiaomi logoXiaomi
MiMo-V2.5-Pro (Non-reasoning)
1298-23 / +25Apr 2026
65
OpenAI logoOpenAI
GPT-5 (high)
1294-22 / +23Aug 2025
66
OpenAI logoOpenAI
GPT-5.2 Codex (xhigh)
1288-25 / +28Dec 2025
67
Kimi logoKimi
Kimi K2.5 (Reasoning)
1285-23 / +25Jan 2026
68
Kimi logoKimi
Kimi K2.5 (Non-reasoning)
1265-23 / +25Jan 2026
69
Tencent logoTencent
Hy3-preview (Reasoning)
1238-24 / +23Apr 2026
70
OpenAI logoOpenAI
GPT-5.1 (high)
1227-20 / +22Nov 2025
71
Tencent logoTencent
Hy3-preview (Non-reasoning)
1226-23 / +28Apr 2026
72
Alibaba logoAlibaba
Qwen3.6 35B A3B (Non-reasoning)
1225-23 / +23Apr 2026
73
OpenAI logoOpenAI
GPT-5.2 (Non-reasoning)
1222-22 / +21Dec 2025
74
Alibaba logoAlibaba
Qwen3.5 397B A17B (Non-reasoning)
1220-23 / +25Feb 2026
75
OpenAI logoOpenAI
GPT-5 Codex (high)
1214-22 / +24Sep 2025
76
Google logoGoogle
Gemini 3 Flash Preview (Reasoning)
1204-24 / +24Dec 2025
77
OpenAI logoOpenAI
GPT-5.4 nano (medium)
1199-21 / +22Mar 2026
78
DeepSeek logoDeepSeek
DeepSeek V3.2 (Reasoning)
1197-24 / +22Dec 2025
79
OpenAI logoOpenAI
GPT-5.4 nano (xhigh)
1194-24 / +28Mar 2026
80
OpenAI logoOpenAI
GPT-5.1 Codex (high)
1192-25 / +25Nov 2025
81
Alibaba logoAlibaba
Qwen3.5 397B A17B (Reasoning)
1190-23 / +22Feb 2026
82
Alibaba logoAlibaba
Qwen3.5 Omni Plus
1185-21 / +23Mar 2026
83
Z AI logoZ AI
GLM-4.7 (Reasoning)
1185-22 / +23Dec 2025
84
OpenAI logoOpenAI
GPT-5 mini (high)
1184-21 / +23Aug 2025
85
Google logoGoogle
Gemini 3 Pro Preview (high)
1184-23 / +23Nov 2025
86
Z AI logoZ AI
GLM-4.7 (Non-reasoning)
1177-25 / +23Dec 2025
87
MiniMax logoMiniMax
MiniMax-M2.5
1176-21 / +24Feb 2026
88
Anthropic logoAnthropic
Claude 4.5 Haiku (Reasoning)
1171-24 / +25Oct 2025
89
xAI logoxAI
Grok 4.20 0309 v2 (Reasoning)
1169-24 / +24Apr 2026
90
Mistral logoMistral
Mistral Medium 3.5
1168-25 / +24Apr 2026
91
Google logoGoogle
Gemini 3 Pro Preview (low)
1167-26 / +27Nov 2025
92
Alibaba logoAlibaba
Qwen3.5 27B (Non-reasoning)
1161-22 / +22Feb 2026
93
Alibaba logoAlibaba
Qwen3.5 27B (Reasoning)
1160-22 / +22Feb 2026
94
 logo
ChatGPT Plus - 5.1 Thinking (Extended Thinking)
1149-41 / +45-
95
OpenAI logoOpenAI
GPT-5 (low)
1149-23 / +23Aug 2025
96
OpenAI logoOpenAI
GPT-5.5 Instant (May 2026)
1141-23 / +23May 2026
97
Alibaba logoAlibaba
Qwen3 Max Thinking
1136-23 / +23Jan 2026
98
Anthropic logoAnthropic
Claude 4.5 Haiku (Non-reasoning)
1135-25 / +27Oct 2025
99
Anthropic logoAnthropic
Claude 4 Sonnet (Reasoning)
1133-26 / +26May 2025
100
Anthropic logoAnthropic
Claude 4 Sonnet (Non-reasoning)
1125-23 / +23May 2025
101
xAI logoxAI
Grok 4.3 (low)
1124-22 / +24Apr 2026
102
InclusionAI logoInclusionAI
Ring-2.6-1T
1122-26 / +25May 2026
103
KwaiKAT logoKwaiKAT
KAT Coder Pro V2
1120-23 / +24Mar 2026
104
Google logoGoogle
Gemini 3 Flash Preview (Non-reasoning)
1116-24 / +25Dec 2025
105
Alibaba logoAlibaba
Qwen3.5 122B A10B (Reasoning)
1116-22 / +23Feb 2026
106
Google logoGoogle
Gemma 4 31B (Reasoning)
1113-22 / +23Apr 2026
107
Alibaba logoAlibaba
Qwen3.5 122B A10B (Non-reasoning)
1111-22 / +24Feb 2026
108
MiniMax logoMiniMax
MiniMax-M2.1
1091-24 / +23Dec 2025
109
DeepSeek logoDeepSeek
DeepSeek V3.1 (Non-reasoning)
1080-21 / +25Aug 2025
110
Xiaomi logoXiaomi
MiMo-V2-Flash (Reasoning)
1079-23 / +24Dec 2025
111
China Mobile logoChina Mobile
JT-35B-Flash
1076-23 / +25May 2026
112
Google logoGoogle
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)
1071-24 / +24Sep 2025
113
StepFun logoStepFun
Step 3.5 Flash 2603
1070-23 / +24Apr 2026
114
DeepSeek logoDeepSeek
DeepSeek V3.2 Exp (Non-reasoning)
1067-24 / +25Sep 2025
115
Xiaomi logoXiaomi
MiMo-V2-Flash (Non-reasoning)
1059-25 / +24Dec 2025
116
StepFun logoStepFun
Step 3.5 Flash
1054-27 / +27Feb 2026
117
OpenAI logoOpenAI
GPT-5.1 Codex mini (high)
1052-24 / +25Nov 2025
118
Anthropic logoAnthropic
Claude 3.7 Sonnet (Reasoning)
1048-23 / +26Feb 2025
119
Alibaba logoAlibaba
Qwen3.5 35B A3B (Non-reasoning)
1047-24 / +23Feb 2026
120
Anthropic logoAnthropic
Claude 3.7 Sonnet (Non-reasoning)
1047-24 / +24Feb 2025
121
xAI logoxAI
Grok 4.1 Fast (Reasoning)
1046-24 / +26Nov 2025
122
InclusionAI logoInclusionAI
Ling-2.6-1T
1046-23 / +24Apr 2026
123
xAI logoxAI
Grok 4.20 0309 (Reasoning)
1043-22 / +24Mar 2026
124
Xiaomi logoXiaomi
MiMo-V2-Flash (Feb 2026)
1043-26 / +25Dec 2025
125
Alibaba logoAlibaba
Qwen3 Max
1038-22 / +23Sep 2025
126
xAI logoxAI
Grok 4.20 0309 v2 (Non-reasoning)
1037-27 / +26Apr 2026
127
 logo
Perplexity Pro - Labs
1032-41 / +39-
128
MiniMax logoMiniMax
MiniMax-M2
1031-25 / +26Oct 2025
129
Z AI logoZ AI
GLM-4.6 (Reasoning)
1029-25 / +31Sep 2025
130
Google logoGoogle
Gemma 4 26B A4B (Reasoning)
1014-22 / +23Apr 2026
131
xAI logoxAI
Grok 4 Fast (Reasoning)
1014-23 / +24Sep 2025
132
OpenAI logoOpenAI
o4-mini (high)
1008-24 / +23Apr 2025
133
Google logoGoogle
Gemma 4 31B (Non-reasoning)
1005-21 / +23Apr 2026
134
DeepSeek logoDeepSeek
DeepSeek V3.1 Terminus (Reasoning)
1004-25 / +27Sep 2025
135
NVIDIA logoNVIDIA
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
1003-22 / +21Mar 2026
136
OpenAI logoOpenAI
GPT-5.4 mini (Non-Reasoning)
1002-22 / +24Mar 2026
137
OpenAI logoOpenAI
GPT-5 mini (medium)
1002-25 / +25Aug 2025
138
OpenAI logoOpenAI
GPT-5.1 (Non-reasoning)
1000-0 / +0Nov 2025
139
DeepSeek logoDeepSeek
DeepSeek V3.2 Exp (Reasoning)
1000-25 / +25Sep 2025
140
OpenAI logoOpenAI
GPT-5 (medium)
1000-25 / +25Aug 2025
141
MiniMax logoMiniMax
MiniMax M1 80k
997-24 / +25Jun 2025
142
Kimi logoKimi
Kimi K2 Thinking
992-23 / +25Nov 2025
143
xAI logoxAI
Grok 4
989-24 / +24Jul 2025
144
ByteDance Seed logoByteDance Seed
Doubao Seed Code
986-26 / +27Nov 2025
145
Z AI logoZ AI
GLM-4.6 (Non-reasoning)
985-23 / +26Sep 2025
146
DeepSeek logoDeepSeek
DeepSeek V3.1 Terminus (Non-reasoning)
975-23 / +24Sep 2025
147
Amazon logoAmazon
Nova 2.0 Pro Preview (medium)
973-27 / +23Nov 2025
148
 logo
Google AI Pro - Thinking with 3 Pro
972-43 / +43-
149
Inception logoInception
Mercury 2
959-23 / +24Feb 2026
150
Google logoGoogle
Gemma 4 26B A4B (Non-reasoning)
948-24 / +24Apr 2026
151
Alibaba logoAlibaba
Qwen3 Max Thinking (Preview)
948-25 / +26Nov 2025
152
OpenAI logoOpenAI
gpt-oss-120b (high)
947-28 / +27Aug 2025
153
OpenAI logoOpenAI
GPT-5.4 nano (Non-Reasoning)
941-30 / +30Mar 2026
154
Google logoGoogle
Gemini 3.1 Flash-Lite
928-22 / +24Mar 2026
155
Google logoGoogle
Gemini 2.5 Pro
919-23 / +26Jun 2025
156
Cohere logoCohere
Command A+
919-24 / +24May 2026
157
Alibaba logoAlibaba
Qwen3 Coder Next
912-24 / +23Feb 2026
158
xAI logoxAI
Grok 4.20 0309 (Non-reasoning)
909-22 / +22Mar 2026
159
Alibaba logoAlibaba
Qwen3.5 35B A3B (Reasoning)
906-22 / +24Feb 2026
160
Alibaba logoAlibaba
Qwen3.5 Omni Flash
897-24 / +28Mar 2026
161
 logo
SuperGrok - Grok 4
882-46 / +40-
162
DeepSeek logoDeepSeek
DeepSeek V3.2 (Non-reasoning)
877-28 / +28Dec 2025
163
Arcee AI logoArcee AI
Trinity Large Thinking
865-24 / +23Apr 2026
164
Mistral logoMistral
Mistral Large 3
864-25 / +24Dec 2025
165
Kimi logoKimi
Kimi K2 0905
864-28 / +28Sep 2025
166
Mistral logoMistral
Mistral Small 4 (Reasoning)
861-23 / +25Mar 2026
167
Mistral logoMistral
Devstral 2
854-24 / +28Dec 2025
168
Amazon logoAmazon
Nova 2.0 Lite (high)
854-24 / +25Oct 2025
169
Google logoGoogle
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)
852-26 / +27Sep 2025
170
Mistral logoMistral
Mistral Small 4 (Non-reasoning)
845-23 / +22Mar 2026
171
Alibaba logoAlibaba
Qwen3.5 9B (Non-reasoning)
844-22 / +23Mar 2026
172
LongCat logoLongCat
LongCat Flash Lite
837-25 / +26Jan 2026
173
Z AI logoZ AI
GLM-4.7-Flash (Reasoning)
837-26 / +26Jan 2026
174
China Mobile logoChina Mobile
JT-MINI
832-25 / +23Apr 2026
175
Mistral logoMistral
Devstral Small (May '25)
829-26 / +25May 2025
176
OpenAI logoOpenAI
gpt-oss-120b (low)
828-23 / +26Aug 2025
177
LG AI Research logoLG AI Research
K-EXAONE (Reasoning)
825-28 / +24Dec 2025
178
Mistral logoMistral
Devstral Small 2
820-25 / +25Dec 2025
179
Alibaba logoAlibaba
Qwen3 235B A22B 2507 (Reasoning)
820-24 / +24Jul 2025
180
KwaiKAT logoKwaiKAT
KAT-Coder-Pro V1
818-27 / +26Nov 2025
181
Alibaba logoAlibaba
Qwen3 Max (Preview)
816-23 / +22Sep 2025
182
LG AI Research logoLG AI Research
EXAONE 4.5 33B
813-25 / +27Apr 2026
183
Z AI logoZ AI
GLM-4.7-Flash (Non-reasoning)
801-41 / +38Jan 2026
184
Baidu logoBaidu
ERNIE 5.0 Thinking Preview
789-27 / +27Nov 2025
185
Amazon logoAmazon
Nova 2.0 Omni (medium)
783-24 / +26Nov 2025
186
InclusionAI logoInclusionAI
Ling 2.6 Flash
783-21 / +24Apr 2026
187
xAI logoxAI
Grok 4.1 Fast (Non-reasoning)
783-25 / +27Nov 2025
188
Mistral logoMistral
Mistral Medium 3.1
780-27 / +27Aug 2025
189
Alibaba logoAlibaba
Qwen3 235B A22B 2507 Instruct
778-28 / +27Jul 2025
190
xAI logoxAI
Grok 4 Fast (Non-reasoning)
778-27 / +26Sep 2025
191
OpenAI logoOpenAI
GPT-4.1
776-26 / +29Apr 2025
192
Alibaba logoAlibaba
Qwen3 VL 4B (Reasoning)
776-39 / +40Oct 2025
193
LG AI Research logoLG AI Research
K-EXAONE (Non-reasoning)
764-26 / +25Dec 2025
194
NVIDIA logoNVIDIA
Nemotron 3 Nano Omni 30B A3B Reasoning
763-26 / +27Apr 2026
195
xAI logoxAI
Grok Code Fast 1
762-26 / +28Aug 2025
196
ByteDance Seed logoByteDance Seed
Seed-OSS-36B-Instruct
759-27 / +27Aug 2025
197
Alibaba logoAlibaba
Qwen3 235B A22B (Reasoning)
756-26 / +30Apr 2025
198
NVIDIA logoNVIDIA
Nemotron Cascade 2 30B A3B
756-23 / +25Mar 2026
199
OpenAI logoOpenAI
GPT-5 nano (high)
755-25 / +26Aug 2025
200
OpenAI logoOpenAI
o3
753-32 / +29Apr 2025
201
Prime Intellect logoPrime Intellect
INTELLECT-3
749-25 / +25Nov 2025
202
OpenAI logoOpenAI
o3-mini (high)
747-25 / +26Jan 2025
203
Google logoGoogle
Gemini 2.5 Flash (Non-reasoning)
741-28 / +26May 2025
204
Alibaba logoAlibaba
Qwen3 235B A22B (Non-reasoning)
738-30 / +28Apr 2025
205
Sarvam logoSarvam
Sarvam 105B (high)
738-22 / +23Mar 2026
206
OpenAI logoOpenAI
o1
736-28 / +29Dec 2024
207
Alibaba logoAlibaba
Qwen3 Next 80B A3B (Reasoning)
725-27 / +26Sep 2025
208
Alibaba logoAlibaba
Qwen3.5 9B (Reasoning)
714-24 / +23Mar 2026
209
Alibaba logoAlibaba
Qwen3 VL 235B A22B (Reasoning)
714-25 / +27Sep 2025
210
Alibaba logoAlibaba
Qwen3 Coder 30B A3B Instruct
711-24 / +26Jul 2025
211
Anthropic logoAnthropic
Claude 3.5 Haiku
708-24 / +25Oct 2024
212
Google logoGoogle
Gemini 2.5 Flash (Reasoning)
698-28 / +26May 2025
213
Z AI logoZ AI
GLM-4.6V (Non-reasoning)
692-27 / +27Dec 2025
214
Mistral logoMistral
Devstral Medium
690-27 / +26Jul 2025
215
InclusionAI logoInclusionAI
Ring-1T
687-27 / +27Oct 2025
216
Alibaba logoAlibaba
Qwen3 VL 8B Instruct
682-37 / +40Oct 2025
217
DeepSeek logoDeepSeek
DeepSeek R1 0528 (May '25)
681-28 / +28May 2025
218
Naver logoNaver
HyperCLOVA X SEED Think (32B)
679-27 / +28Dec 2025
219
Upstage logoUpstage
Solar Pro 3
675-25 / +24Apr 2026
220
Mistral logoMistral
Magistral Small 1.2
669-26 / +25Sep 2025
221
Alibaba logoAlibaba
Qwen3 VL 8B (Reasoning)
669-27 / +29Oct 2025
222
Alibaba logoAlibaba
Qwen3.5 4B (Non-reasoning)
668-22 / +23Mar 2026
223
Alibaba logoAlibaba
Qwen3 VL 30B A3B (Reasoning)
667-37 / +37Oct 2025
224
xAI logoxAI
Grok 3
666-24 / +28Feb 2025
225
Mistral logoMistral
Magistral Medium 1
666-27 / +27Jun 2025
226
Upstage logoUpstage
Solar Open 100B (Reasoning)
665-27 / +28Dec 2025
227
Alibaba logoAlibaba
Qwen3 30B A3B 2507 (Reasoning)
660-25 / +25Jul 2025
228
Amazon logoAmazon
Nova 2.0 Pro Preview (low)
659-28 / +29Nov 2025
229
Mistral logoMistral
Ministral 3 14B
655-26 / +27Dec 2025
230
OpenAI logoOpenAI
gpt-oss-20B (high)
649-25 / +26Aug 2025
231
Alibaba logoAlibaba
Qwen3 VL 32B (Reasoning)
647-25 / +27Oct 2025
232
Amazon logoAmazon
Nova 2.0 Lite (medium)
643-27 / +27Oct 2025
233
Korea Telecom logoKorea Telecom
Mi:dm K 2.5 Pro
642-26 / +26Dec 2025
234
Mistral logoMistral
Ministral 3 8B
639-28 / +26Dec 2025
235
Alibaba logoAlibaba
Qwen3 VL 235B A22B Instruct
636-33 / +36Sep 2025
236
Alibaba logoAlibaba
Qwen3 Next 80B A3B Instruct
627-29 / +28Sep 2025
237
Mistral logoMistral
Magistral Medium 1.2
627-29 / +27Sep 2025
238
OpenAI logoOpenAI
GPT-4.1 mini
620-28 / +25Apr 2025
239
DeepSeek logoDeepSeek
DeepSeek V3.1 (Reasoning)
614-29 / +31Aug 2025
240
Z AI logoZ AI
GLM-4.6V (Reasoning)
609-30 / +32Dec 2025
241
MBZUAI Institute of Foundation Models logoMBZUAI Institute of Foundation Models
K2 Think V2
608-25 / +26Dec 2025
242
OpenAI logoOpenAI
GPT-5 nano (medium)
593-27 / +27Aug 2025
243
Alibaba logoAlibaba
Qwen3 4B 2507 (Reasoning)
589-28 / +27Aug 2025
244
Mistral logoMistral
Mistral Medium 3
586-27 / +25May 2025
245
Nous Research logoNous Research
Hermes 4 - Llama-3.1 405B (Reasoning)
585-23 / +25Aug 2025
246
MBZUAI Institute of Foundation Models logoMBZUAI Institute of Foundation Models
K2-V2 (medium)
581-26 / +26Dec 2025
247
ServiceNow logoServiceNow
Apriel-v1.6-15B-Thinker
571-26 / +25Nov 2025
248
Google logoGoogle
Gemini 2.0 Flash (Feb '25)
566-26 / +26Feb 2025
249
Mistral logoMistral
Devstral Small (Jul '25)
564-30 / +29Jul 2025
250
NVIDIA logoNVIDIA
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
563-28 / +27Dec 2025
251
MBZUAI Institute of Foundation Models logoMBZUAI Institute of Foundation Models
K2-V2 (high)
561-27 / +27Dec 2025
252
Z AI logoZ AI
GLM-4.5-Air
559-31 / +27Jul 2025
253
OpenAI logoOpenAI
gpt-oss-20B (low)
550-25 / +26Aug 2025
254
IBM logoIBM
Granite 4.1 8B
542-26 / +26Apr 2026
255
Nous Research logoNous Research
Hermes 4 - Llama-3.1 70B (Reasoning)
538-24 / +23Aug 2025
256
Kimi logoKimi
Kimi K2
526-29 / +31Jul 2025
257
Nous Research logoNous Research
Hermes 4 - Llama-3.1 70B (Non-reasoning)
522-26 / +24Aug 2025
258
Alibaba logoAlibaba
Qwen3 30B A3B 2507 Instruct
515-27 / +27Jul 2025
259
Nous Research logoNous Research
Hermes 4 - Llama-3.1 405B (Non-reasoning)
510-24 / +24Aug 2025
260
Z AI logoZ AI
GLM-4.5V (Reasoning)
510-23 / +22Aug 2025
261
Alibaba logoAlibaba
Qwen3.5 4B (Reasoning)
510-28 / +31Mar 2026
262
Amazon logoAmazon
Nova 2.0 Lite (low)
508-29 / +30Oct 2025
263
Alibaba logoAlibaba
Qwen3 30B A3B (Reasoning)
507-26 / +26Apr 2025
264
Alibaba logoAlibaba
Qwen3 Coder 480B A35B Instruct
506-30 / +29Jul 2025
265
Amazon logoAmazon
Nova Premier
505-28 / +28Apr 2025
266
LG AI Research logoLG AI Research
EXAONE 4.0 32B (Reasoning)
503-28 / +25Jul 2025
267
Allen Institute for AI logoAllen Institute for AI
Molmo2-8B
500-0 / +0Dec 2025
268
DeepSeek logoDeepSeek
DeepSeek V3.2 Speciale
500-0 / +0Dec 2025
269
Alibaba logoAlibaba
Qwen3 8B (Reasoning)
496-27 / +29Apr 2025
270
Alibaba logoAlibaba
Qwen3 Omni 30B A3B (Reasoning)
495-27 / +26Sep 2025
271
Alibaba logoAlibaba
Qwen3 VL 30B A3B Instruct
495-30 / +28Oct 2025
272
IBM logoIBM
Granite 4.1 30B
495-25 / +25Apr 2026
273
Alibaba logoAlibaba
Qwen3 32B (Reasoning)
489-27 / +27Apr 2025
274
Motif Technologies logoMotif Technologies
Motif-2-12.7B-Reasoning
484-30 / +30Dec 2025
275
Mistral logoMistral
Ministral 3 3B
483-28 / +29Dec 2025
276
Alibaba logoAlibaba
Qwen3 14B (Reasoning)
479-30 / +27Apr 2025
277
NVIDIA logoNVIDIA
NVIDIA Nemotron 3 Nano 4B
478-29 / +28Mar 2026
278
Alibaba logoAlibaba
Qwen3 8B (Non-reasoning)
473-27 / +26Apr 2025
279
Alibaba logoAlibaba
Qwen3 14B (Non-reasoning)
471-27 / +25Apr 2025
280
OpenAI logoOpenAI
GPT-5 mini (minimal)
471-28 / +29Aug 2025
281
Z AI logoZ AI
GLM-4.5 (Reasoning)
468-31 / +33Jul 2025
282
Z AI logoZ AI
GLM-4.5V (Non-reasoning)
459-31 / +31Aug 2025
283
Upstage logoUpstage
Solar Pro 2 (Reasoning)
449-30 / +28Jul 2025
284
Upstage logoUpstage
Solar Pro 2 (Non-reasoning)
445-27 / +28Jul 2025
285
NVIDIA logoNVIDIA
NVIDIA Nemotron Nano 9B V2 (Reasoning)
439-26 / +28Aug 2025
286
Meta logoMeta
Llama 4 Maverick
435-28 / +29Apr 2025
287
Google logoGoogle
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
434-30 / +29Sep 2025
288
InclusionAI logoInclusionAI
Ling-flash-2.0
419-30 / +29Sep 2025
289
xAI logoxAI
Grok 3 mini Reasoning (high)
419-40 / +36Feb 2025
290
DeepSeek logoDeepSeek
DeepSeek V3 (Dec '24)
410-30 / +28Dec 2024
291
DeepSeek logoDeepSeek
DeepSeek V3 0324
407-27 / +28Mar 2025
292
InclusionAI logoInclusionAI
Ling-1T
401-28 / +31Oct 2025
293
Meta logoMeta
Llama 3.3 Instruct 70B
400-31 / +28Dec 2024
294
Amazon logoAmazon
Nova Pro
387-31 / +30Dec 2024
295
OpenAI logoOpenAI
GPT-5 (minimal)
385-30 / +30Aug 2025
296
Amazon logoAmazon
Nova 2.0 Lite (Non-reasoning)
380-30 / +29Oct 2025
297
Google logoGoogle
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)
380-29 / +30Sep 2025
298
NVIDIA logoNVIDIA
Llama Nemotron Super 49B v1.5 (Non-reasoning)
379-28 / +28Jul 2025
299
OpenAI logoOpenAI
GPT-4o (Aug '24)
378-28 / +29Aug 2024
300
Anthropic logoAnthropic
Claude 3 Haiku
378-24 / +23Mar 2024
301
Trillion Labs logoTrillion Labs
Tri-21B-Think
372-25 / +26Feb 2026
302
TII UAE logoTII UAE
Falcon-H1R-7B
372-31 / +28Jan 2026
303
NVIDIA logoNVIDIA
Llama Nemotron Super 49B v1.5 (Reasoning)
368-31 / +29Jul 2025
304
MBZUAI Institute of Foundation Models logoMBZUAI Institute of Foundation Models
K2-V2 (low)
365-29 / +30Dec 2025
305
IBM logoIBM
Granite 4.1 3B
364-25 / +29Apr 2026
306
Amazon logoAmazon
Nova 2.0 Omni (low)
359-34 / +29Nov 2025
307
Sarvam logoSarvam
Sarvam 30B (high)
357-23 / +24Mar 2026
308
Nanbeige logoNanbeige
Nanbeige4.1-3B
356-30 / +31Feb 2026
309
Allen Institute for AI logoAllen Institute for AI
Olmo 3.1 32B Instruct
354-28 / +29Jan 2026
310
OpenAI logoOpenAI
GPT-4o (Nov '24)
348-26 / +25Nov 2024
311
NVIDIA logoNVIDIA
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
346-30 / +29Dec 2025
312
IBM logoIBM
Granite 4.0 H Small
343-30 / +29Sep 2025
313
Amazon logoAmazon
Nova Lite
343-30 / +32Dec 2024
314
Alibaba logoAlibaba
Qwen3 VL 4B Instruct
342-28 / +27Oct 2025
315
Amazon logoAmazon
Nova Micro
339-31 / +29Dec 2024
316
Trillion Labs logoTrillion Labs
Tri-21B-think Preview
337-33 / +30Feb 2026
317
Mistral logoMistral
Mistral Small 3.1
336-31 / +27Mar 2025
318
NVIDIA logoNVIDIA
Llama 3.1 Nemotron Instruct 70B
335-30 / +31Oct 2024
319
Alibaba logoAlibaba
Qwen3 30B A3B (Non-reasoning)
329-31 / +28Apr 2025
320
LG AI Research logoLG AI Research
EXAONE 4.0 32B (Non-reasoning)
328-33 / +29Jul 2025
321
NVIDIA logoNVIDIA
NVIDIA Nemotron Nano 12B v2 VL (Reasoning)
328-29 / +28Oct 2025
322
Mistral logoMistral
Mistral Large 2 (Nov '24)
323-31 / +31Nov 2024
323
Alibaba logoAlibaba
Qwen3.5 2B (Reasoning)
319-25 / +24Mar 2026
324
OpenAI logoOpenAI
GPT-4.1 nano
318-32 / +29Apr 2025
325
Google logoGoogle
Gemini 2.5 Flash-Lite (Reasoning)
318-31 / +29Jun 2025
326
Amazon logoAmazon
Nova 2.0 Pro Preview (Non-reasoning)
317-30 / +30Nov 2025
327
Alibaba logoAlibaba
Qwen3 0.6B (Reasoning)
314-31 / +28Apr 2025
328
Alibaba logoAlibaba
Qwen3 4B 2507 Instruct
305-31 / +28Aug 2025
329
Amazon logoAmazon
Nova 2.0 Omni (Non-reasoning)
304-32 / +30Nov 2025
330
Google logoGoogle
Gemini 2.5 Flash-Lite (Non-reasoning)
303-31 / +30Jun 2025
331
Mistral logoMistral
Mistral Small 3.2
303-31 / +32Jun 2025
332
Google logoGoogle
Gemma 4 E4B (Reasoning)
302-26 / +24Apr 2026
333
NVIDIA logoNVIDIA
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
302-28 / +29Aug 2025
334
Alibaba logoAlibaba
Qwen3 VL 32B Instruct
300-34 / +29Oct 2025
335
Alibaba logoAlibaba
Qwen3 Omni 30B A3B Instruct
295-31 / +30Sep 2025
336
LG AI Research logoLG AI Research
Exaone 4.0 1.2B (Non-reasoning)
294-28 / +27Jul 2025
337
LG AI Research logoLG AI Research
Exaone 4.0 1.2B (Reasoning)
291-28 / +30Jul 2025
338
Google logoGoogle
Gemma 4 E4B (Non-reasoning)
291-26 / +26Apr 2026
339
IBM logoIBM
Granite 4.0 H 350M
289-31 / +31Oct 2025
340
Google logoGoogle
Gemma 3 27B Instruct
285-31 / +28Mar 2025
341
Meta logoMeta
Llama 3.1 Instruct 70B
284-27 / +27Jul 2024
342
NVIDIA logoNVIDIA
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
283-27 / +29Oct 2025
343
AI21 Labs logoAI21 Labs
Jamba 1.7 Large
282-30 / +31Jul 2025
344
Google logoGoogle
Gemma 3 12B Instruct
279-30 / +26Mar 2025
345
OpenAI logoOpenAI
GPT-5 nano (minimal)
279-30 / +27Aug 2025
346
IBM logoIBM
Granite 4.0 Micro
279-29 / +28Sep 2025
347
Alibaba logoAlibaba
Qwen3 0.6B (Non-reasoning)
277-34 / +30Apr 2025
348
Meta logoMeta
Llama 3.1 Instruct 8B
277-32 / +31Jul 2024
349
Alibaba logoAlibaba
Qwen3.5 0.8B (Reasoning)
276-25 / +24Mar 2026
350
Allen Institute for AI logoAllen Institute for AI
Olmo 3 7B Instruct
276-27 / +30Nov 2025
351
Alibaba logoAlibaba
Qwen3 1.7B (Reasoning)
275-28 / +32Apr 2025
352
AI21 Labs logoAI21 Labs
Jamba 1.7 Mini
274-30 / +30Jul 2025
353
Cohere logoCohere
Command A
273-29 / +30Mar 2025
354
Liquid AI logoLiquid AI
LFM2 1.2B
271-32 / +28Jul 2025
355
Meta logoMeta
Llama 4 Scout
270-30 / +29Apr 2025
356
Google logoGoogle
Gemma 4 E2B (Reasoning)
269-25 / +25Apr 2026
357
IBM logoIBM
Granite 4.0 H 1B
266-30 / +29Oct 2025
358
IBM logoIBM
Granite 4.0 350M
265-31 / +28Oct 2025
359
Liquid AI logoLiquid AI
LFM2.5-1.2B-Instruct
265-32 / +31Jan 2026
360
InclusionAI logoInclusionAI
Ling-mini-2.0
260-24 / +26Sep 2025
361
Liquid AI logoLiquid AI
LFM2 8B A1B
258-31 / +29Oct 2025
362
IBM logoIBM
Granite 4.0 1B
258-30 / +30Oct 2025
363
StepFun logoStepFun
Step3 VL 10B
257-29 / +29Jan 2026
364
OpenBMB logoOpenBMB
MiniCPM-V 4.6 1.3B
256-28 / +28May 2026
365
Meta logoMeta
Llama 3.1 Instruct 405B
255-31 / +29Jul 2024
366
Google logoGoogle
Gemma 3 4B Instruct
254-30 / +28Mar 2025
367
AI21 Labs logoAI21 Labs
Jamba Reasoning 3B
254-30 / +29Oct 2025
368
Alibaba logoAlibaba
Qwen3 1.7B (Non-reasoning)
253-30 / +31Apr 2025
369
Liquid AI logoLiquid AI
LFM2.5-1.2B-Thinking
252-31 / +29Jan 2026
370
Google logoGoogle
Gemma 4 E2B (Non-reasoning)
251-27 / +26Apr 2026
371
DeepSeek logoDeepSeek
DeepSeek R1 (Jan '25)
248-30 / +28Jan 2025
372
Google logoGoogle
Gemma 3n E4B Instruct
243-35 / +31Jun 2025
373
NVIDIA logoNVIDIA
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
238-26 / +25Apr 2025
374
Alibaba logoAlibaba
Qwen3.5 2B (Non-reasoning)
237-24 / +24Mar 2026
375
Liquid AI logoLiquid AI
LFM2 2.6B
235-28 / +30Sep 2025
376
Liquid AI logoLiquid AI
LFM2 24B A2B
234-27 / +24Feb 2026
377
Alibaba logoAlibaba
Qwen3.5 0.8B (Non-reasoning)
233-27 / +24Mar 2026
378
Liquid AI logoLiquid AI
LFM2.5-VL-1.6B
231-33 / +29Jan 2026
379
OpenBMB logoOpenBMB
MiniCPM5-1B (Non-reasoning)
231-29 / +27May 2026
380
Microsoft logoMicrosoft
Phi-4 Mini Instruct
228-30 / +28Feb 2024
381
IBM logoIBM
Granite 3.3 8B (Non-reasoning)
224-29 / +28Apr 2025

Example Tasks

Frequently Asked Questions

GDPval-AA is Artificial Analysis' evaluation based on OpenAI's GDPval dataset, which tests AI models on real-world economically valuable tasks across 44 occupations and 9 major industries.

GDPval-AA compares model submissions head-to-head on the same task. For each matchup, the two outputs are anonymized and an LLM judge picks a winner. These blind pairwise results are aggregated into an Elo rating per model.

Claude Opus 4.8 (Adaptive Reasoning, Max Effort) has the highest GDPval-AA score, with a GDPval-AA Elo rating of 1,890 among models with published GDPval-AA results. View model

GDPval-AA covers real-world professional tasks across a range of occupations and industries, producing outputs such as documents, spreadsheets, slides, and diagrams. Generating these deliverables generally requires interacting with a sandbox filesystem through shell access and using web search, capabilities the model is given through the Stirrup agentic harness.

Most benchmarks test short-answer or multiple-choice responses. GDPval-AA instead evaluates complete deliverables: models operate in an agentic environment with tools, produce file outputs, and have their submissions scored through pairwise grading on relative quality.

Explore Evaluations

Artificial Analysis Intelligence IndexArtificial Analysis Intelligence Index

A composite benchmark aggregating ten challenging evaluations to provide a holistic measure of AI capabilities across mathematics, science, coding, and reasoning.

GDPval-AA LeaderboardGDPval-AA Leaderboard

GDPval-AA is Artificial Analysis' evaluation framework for OpenAI's GDPval dataset. It tests AI models on real-world tasks across 44 occupations and 9 major industries. Models are given shell access and web browsing capabilities in an agentic loop via Stirrup to solve tasks, with Elo ratings derived from blind pairwise comparisons.

APEX-Agents-AA Benchmark LeaderboardAPEX-Agents-AA Benchmark Leaderboard

Artificial Analysis' implementation of the APEX-Agents benchmark, testing AI agents on long-horizon, cross-application tasks in professional-services environments with realistic application tooling.

๐œยฒ-Bench Telecom Benchmark Leaderboard๐œยฒ-Bench Telecom Benchmark Leaderboard

A dual-control conversational AI benchmark simulating technical support scenarios where both agent and user must coordinate actions to resolve telecom service issues.

Terminal-Bench Hard Benchmark LeaderboardTerminal-Bench Hard Benchmark Leaderboard

An agentic benchmark evaluating AI capabilities in terminal environments through software engineering, system administration, and data processing tasks.

SciCode Benchmark LeaderboardSciCode Benchmark Leaderboard

A scientist-curated coding benchmark featuring 288 test set subproblems from 80 laboratory problems across 16 scientific disciplines.

Artificial Analysis Long Context Reasoning Benchmark LeaderboardArtificial Analysis Long Context Reasoning Benchmark Leaderboard

A challenging benchmark measuring language models' ability to extract, reason about, and synthesize information from long-form documents ranging from 10k to 100k tokens (measured using the cl100k_base tokenizer).

AA-Omniscience: Knowledge and Hallucination BenchmarkAA-Omniscience: Knowledge and Hallucination Benchmark

A benchmark measuring factual recall and hallucination across various economically relevant domains.

IFBench Benchmark LeaderboardIFBench Benchmark Leaderboard

A benchmark evaluating precise instruction-following generalization on 58 diverse, verifiable out-of-domain constraints that test models' ability to follow specific output requirements.

Humanity's Last Exam Benchmark LeaderboardHumanity's Last Exam Benchmark Leaderboard

A frontier-level benchmark with 2,500 expert-vetted questions across mathematics, sciences, and humanities, designed to be the final closed-ended academic evaluation.

GPQA Diamond Benchmark Leaderboard

The most challenging 198 questions from GPQA, where PhD experts achieve 65% accuracy but skilled non-experts only reach 34% despite web access.

CritPt Benchmark LeaderboardCritPt Benchmark Leaderboard

A benchmark designed to test LLMs on research-level physics reasoning tasks, featuring 71 composite research challenges.

ITBench-AA Benchmark LeaderboardITBench-AA Benchmark Leaderboard

Artificial Analysis' implementation of IBM's ITBench benchmark, testing AI agents on Kubernetes incident root-cause analysis from offline incident snapshots. The agent inspects alerts, events, traces, and topology and identifies the contributing-factor entities (deployments, pods, namespaces, network policies, etc.) responsible for the failure.

Artificial Analysis Openness IndexArtificial Analysis Openness Index

A composite measure providing an industry standard to communicate model openness for users and developers.

MMLU-Pro Benchmark LeaderboardMMLU-Pro Benchmark Leaderboard

An enhanced version of MMLU with 12,000 graduate-level questions across 14 subject areas, featuring ten answer options and deeper reasoning requirements.

Global-MMLU-Lite Benchmark LeaderboardGlobal-MMLU-Lite Benchmark Leaderboard

A lightweight, multilingual version of MMLU, designed to evaluate knowledge and reasoning skills across a diverse range of languages and cultural contexts.

LiveCodeBench Benchmark LeaderboardLiveCodeBench Benchmark Leaderboard

A contamination-free coding benchmark that continuously harvests fresh competitive programming problems from LeetCode, AtCoder, and CodeForces, evaluating code generation, self-repair, and execution.

MATH-500 Benchmark LeaderboardMATH-500 Benchmark Leaderboard

A 500-problem subset from the MATH dataset, featuring competition-level mathematics across six domains including algebra, geometry, and number theory.

AIME 2025 Benchmark LeaderboardAIME 2025 Benchmark Leaderboard

All 30 problems from the 2025 American Invitational Mathematics Examination, testing olympiad-level mathematical reasoning with integer answers from 000-999.

MMMU-Pro Benchmark LeaderboardMMMU-Pro Benchmark Leaderboard

An enhanced MMMU benchmark that eliminates shortcuts and guessing strategies to more rigorously test multimodal models across 30 academic disciplines.