| Votes | Benchmark | Creators | | Area |
| 25 | Terminal-Bench 4 |    | Alex ShawS., Andy KonwinskiK., Mike A. MerrillM. | Coding |
| 20 | Terminal-Bench Science |    | Steven DillmannD., Ludwig SchmidtS., Sanmi KoyejoK. | Science |
| 13 | FrontierCode |     | Eric LuL., Ben PanP., Deniz BirlikciB., Silas AlbertiA. | Coding |
| 10 | FrontierSWE |       | Evan ChuC., Rajan AgarwalA., Justus MatternM., Rishyanth KondraK., Sanket MhatreM., Akshit KumarK. | Coding |
| 8 | Humanity's Last Exam |      | Long PhanP., Dan HendrycksH., Alice GattiG., Ziwen HanH., Nathaniel LiL. | Expert knowledge |
| 7 | Vending-Bench |   | Axel BacklundB., Lukas PeterssonP. | Business |
| 5 | AutomationBench |    | Daniel ShepardS., Robin SalimansS., Anna Marie CliftonC. | Business |
| 5 | DeepSWE |     | Wenqi (Kevin) HuangH., Charley LeeL., Leonard TngT., Serena GeG. | Coding |
| 5 | PostTrainBench |        | Ben RankR., Hardik BhatnagarB., Ameya PrabhuP., Shira EisenbergE., Karina NguyenN., Matthias BethgeB., Maksym AndriushchenkoA. | ML engineering |
| 4 | AA-Briefcase |   | Micah Hill-SmithH., George CameronC. | Knowledge work |
| 4 | Agents' Last Exam |     | Yiyou SunS., Dawn SongS., Xinyang HanH., Weichen ZhangZ. | Knowledge work |
| 4 | FrontierCS 2 |         | Qiuyang MangM., Wenhao ChaiC., Runyuan HeH., Dongruixuan LiL., Zihan ZhengZ., Yujun HeH., Alvin CheungC., Joseph E. GonzalezG. | Coding |
| 4 | OSWorld 2 |  X  | Mengqi YuanY., Zilong ZhouZ., Xinzhuang XiongX., Tao YuY., Tianbao XieX. | Computer use |
| 3 | ARC-AGI-3 |     | Greg KamradtK., François CholletC., Mike KnoopK., Hunter HenryH. | Reasoning |
| 3 | FrontierMath |    | Elliot GlazerG., Tamay BesirogluB., Ege ErdilE. | Math |
| 3 | Harvey LAB |     | Niko GrupenG., Gabe PereyraP., Julio PereyraP., Spencer PoffP. | Legal |
| 3 | ProgramBench |      | John YangY., Kilian LieretL., Jeffrey Jian MaM., Diyi YangY., Ofir PressP. | Coding |
| 3 | SWE-sweep |     | Kilian LieretL., Jeffrey Jian MaM., Ofir PressP., John YangY. | Coding |
| 2 | GDPx |     | Max KanK., Andrew MegalaaM., Dylan PatelP., Abhijay RanaR. | Multi-domain |
| 2 | BrowseComp |     | Jason WeiW., Zhiqing SunS., Hyung Won ChungC., Mia (Amelia) GlaeseG. | Web research |
| 2 | Chartography |    | Suhaas GarreG., Chris MuttyM., Sushant MehtaM., Edwin ChenC. | Visual reasoning |
| 2 | CursorBench |  | Naman JainJ. | Coding |
| 2 | ExploitBench |   | Seunghyun Lee (Xion)(., David BrumleyB. | Cyber |
| 2 | GDP.pdf |   | Suhaas GarreG., Emily RitchieR., Sushant MehtaM., Edwin ChenC. | Knowledge work |
| 2 | GDPval-AA |     | Tejal PatwardhanP., Micah Hill-SmithH., George CameronC., Declan JacksonJ. | Knowledge work |
Counts are net: a few benchmarks got negative votes.
GDPx came out the day before I sent the survey.
GDPx was built with 14 data partners: Arcverex, Aria, Arithmetic, Beautiful Machines, Chakra, Datacurve, Emulated, Ergodex, Extrapolate, Fleet, Latch, Living Context, Third Moment, and ValenceForge.
The most common comment was that people don't really trust benchmarks at all.