A benchmark that measures performance on knowledge-work tasks drawn from industries that contribute heavily to United States GDP.
Browse the latest scores, model modes, release dates, and parameter sizes for GDPval-AA.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
![]() Claude Opus 4.8 Extended ThinkingTools | 1890.00 | 2026-05-28 | Unknown | Closed | |
![]() GPT-5.5 Thinking Level · High | 1769.00 | 2026-04-23 | Unknown | Closed | |
![]() Claude Opus 4.6 Extended ThinkingToolsInternet | 1606.00 | 2026-02-05 | Unknown | Closed | |
4 | ![]() DeepSeek-V4-Pro Thinking Level · Extra HighTools | 1554.00 | 2026-04-24 | 1600B | Free Commercial |
5 | ![]() Muse Spark Thinking EnabledTools | 1444.00 | 2026-04-08 | Unknown | Closed |
6 | ![]() DeepSeek-V4-Flash Thinking Level · Extra HighTools | 1395.00 | 2026-04-24 | 284B | Free Commercial |
7 | ![]() GPT-5.5 Pro Thinking Level · Extra High | 82.30 | 2026-04-23 | Unknown | Closed |
8 | ![]() GPT-5.4 Pro Thinking Level · HighTools | 82.00 | 2026-03-05 | Unknown | Closed |
9 | ![]() GPT-5.2 Thinking Level · HighTools | 70.90 | 2025-12-11 | Unknown | Closed |
10 | ![]() GPT-5.2 Thinking Level · Extra HighTools | 61.00 | 2025-12-11 | Unknown | Closed |
11 | ![]() Claude Sonnet 4.6 Thinking Enabled | 57.00 | 2026-02-17 | Unknown | Closed |
12 | ![]() Qwen3.6-Max-Preview Deep Thinking Mode | 51.00 | 2026-04-18 | Unknown | Closed |
13 | ![]() MiniMax-M2.7 Thinking Enabled | 50.00 | 2026-03-18 | 229B | Non-Commercial |
14 | ![]() GLM-5 Thinking Enabled | 46.00 | 2026-02-11 | 744B | Free Commercial |
15 | ![]() Kimi K2.5 Thinking Enabled | 40.00 | 2026-01-27 | 1000B | Free Commercial |
16 | ![]() Claude Sonnet 4.5 Thinking Enabled | 39.00 | 2025-09-30 | Unknown | Closed |
17 | ![]() MiniMax M2.5 Thinking Enabled | 36.00 | 2026-02-12 | 229B | Free Commercial |
18 | ![]() Gemini 3.0 Pro (Preview 11-2025) Thinking Level · High | 35.00 | 2025-11-18 | Unknown | Closed |
19 | ![]() Claude Sonnet 4 Thinking Enabled | 33.00 | 2025-05-23 | Unknown | Closed |
20 | ![]() Claude Sonnet 3.7 Thinking Enabled | 28.00 | 2025-02-25 | Unknown | Closed |
21 | ![]() Gemini 2.5-Pro Thinking Enabled | 22.00 | 2025-06-05 | Unknown | Closed |