Mercor |
Multi-Domain |
SFSanta Clara |
Thiel Fellowship, Harvard, Georgetown |
  Brendan Foody, Adarsh Hiremath, Surya Midha |
250+ |
APEX |
Handshake |
Multi-Domain |
SFNYC, Bangalore, Berlin |
Palantir, Meta, Scale AI |
       Garrett Lord, Ben Christensen, Scott RingwelskiRL envs: Paco Guzmán, Sahil Bhaiwala, Jack Bratches, Nishant Ranka, Yang Zhao |
250+ |
Gandalf the Grader |
Scale |
Multi-Domain Code |
SFNYC, DC, London |
Stanford, Coinbase, YC |
RL envs: Chetan Rane |
250+ |
SWE-bench Pro |
Turing |
Code |
SFPalo Alto, Gurugram |
Stanford, Rover, Yahoo |
 Jonathan Siddharth, Vijay Krishnan |
250+ |
VLMBench |
Toloka |
Multi-Domain |
AmsterdamBelgrade |
Yandex, Microsoft, McKinsey |
Olga Megorskaya |
250+ |
Toloka Arena |
Surge |
Multi-Domain |
SFNYC, Seattle |
Google, Meta, Twitter |
 Edwin ChenRL envs: Nick Heiner |
101-250 |
CoreCraft |
Snorkel |
Multi-Domain Code |
SFNYC |
Stanford, UW, Meta |
      Alex Ratner, Braden Hancock, Christopher Ré, Paroma Varma, Henry EhrenbergRL envs: Vincent Sunn Chen, Frederic Sala |
101-250 |
Senior SWE-Bench |
micro1 |
Multi-Domain |
SF |
Stanford, Berkeley |
Ali Ansari |
101-250 |
Realm |
AfterQuery |
Multi-Domain |
SFNYC, Seattle |
Wharton, Penn, UBC |
 Carlos Georgescu, Spencer Mateega |
51-100 |
AppBench |
Latch |
Science |
SF |
Berkeley, Google, Asimov |
  Alfredo Andere, Kenny Workman, Kyle Giffin |
51-100 |
benchmarks.bio |
Patronus AI |
Multi-Domain Code |
SF |
Meta AI, Google, Amazon |
 Anand Kannappan, Rebecca Qian |
51-100 |
FinanceBench, TRAIL |
Datacurve |
Code |
SF |
Waterloo |
 Serena Ge, Charley Lee |
26-50 |
DeepSWE |
Halluminate |
Finance Enterprise |
SF |
Capital One, Meta, Cornell |
 Jerry Wu, Wyatt Marshall |
26-50 |
WebBench |
Mechanize |
Code |
SF |
Epoch AI |
   Guive Assadi, Tamay Besiroglu, Ege Erdil, Matthew Barnett |
26-50 |
GBA Eval |
Pareto |
Multi-Domain Tool Use |
SF |
Stanford, Scale, Turing |
   Phoebe YaoRL envs: Mark Whiting, Youssef Elhady, Joe Crawley |
26-50 |
Leap, Attune |
Proximal |
Code |
SFBangalore |
Prime Intellect, Cursor |
  Justus Mattern, Navid Pour, Calvin Chen |
26-50 |
FrontierSWE |
Aptura |
Finance Enterprise |
LondonSF |
Lazard, McKinsey, EF |
Chirag Modi |
11-25 |
SpreadsheetBench 2 |
Bespoke Labs |
Code |
Mountain ViewMenlo Park, Bangalore, SF |
Google DeepMind, UC Berkeley |
 Mahesh Sathiamoorthy, Alex Dimakis |
11-25 |
OpenThoughts |
Collinear |
Enterprise Long Horizon |
Mountain ViewSunnyvale |
Hugging Face, Salesforce, Stanford |
 Nazneen Rajani, Soumyadeep Bakshi |
11-25 |
Curator Evals |
Emulated |
ML Science |
SF |
AWS, DeepMind, Prime Intellect |
 Joseph Wang, Sid Patllollu |
11-25 |
SWE, Autoresearch |
Quesma |
Security |
Warsaw |
Elastic, Sumo Logic, Dynatrace |
Jacek Migdal |
11-25 |
BinaryAudit |
ReasonCore |
Science Code |
SF |
Turing, Aera Technology, Oracle |
  Geoff Wolfe, Anshuman Lall, Satish Vutukuru |
11-25 |
Benchmarks |
Abundant |
Code |
SF |
Waymo, Google, Mercor |
  Jesse Hu, Ke Huang, Meji Abidoye |
1-10 |
SWE-Marathon |
Aviro |
Code ML |
SF |
YC, Princeton, Georgia Tech |
 Ayush Karupakula, Aarush Kukreja |
1-10 |
C⁴ |
BenchFlow |
Enterprise Browser |
SF |
Berkeley, Tesla |
Xiangyi Li |
1-10 |
SkillsBench |
Cua |
Code Computer Use |
SF |
Microsoft, Twitter |
 Francesco Bonacci, Dillon DuPont |
1-10 |
Cua-Bench |
EdotEnv |
Long Horizon ML |
SF |
G-Research, Etched, ETH Zurich |
 Rui Wang, Michael Zhang |
1-10 |
Long-Horizon Planning |
General Reasoning |
Finance |
LondonSF |
Meta, Conjecture, Aleph Alpha |
   Ross Taylor, Chengxi Taylor, Kip Parker, Thomas Grady |
1-10 |
OpenReward |
Markov |
Computer Use Tool Use |
SF |
YC, IIT Madras |
 Dev Mandal, Harish Ashok |
1-10 |
CUA data, AutoCAD-Bench |
Metaphi |
Code Enterprise |
SFNYC |
Waymo, Nuro, Netflix |
 Abhishek Chandwani, Ishan Gupta |
1-10 |
CREW |
Normal |
Hardware Engineering |
SF |
Cohere, Notion, Fuse |
 Hudzah, Anson Yu |
1-10 |
CAD Arena |
pre.dev |
Code Long Horizon |
Delaware |
Penn M&T, Wharton |
 Arjun Raj Jain, Adam Elkassas |
1-10 |
TB3 results |
Refresh |
Code Computer Use |
SF |
Uber, Amazon |
 Christopher Settles, Erik Quintanilla |
1-10 |
BlenderBench |
Tacit Labs |
Science Long Horizon |
SF |
MosaicML, MSR, EF |
 Nicole Fitzgerald, Anne Marie Droste |
1-10 |
LifeSciBench |
Ulam |
Math |
WarsawLondon |
Oxford |
Przemek Chojecki |
1-10 |
RLVR Trajectories |
Vmax |
ML |
SFNYC |
UCL |
 Matthew Sargent, Augustine Mavor-Parker |
1-10 |
unix-ctf |
Uber AI |
Audio |
SF |
Scale AI, Turing, Harvard |
Key people: Natesh Pillai |
250+ |
|
Originator |
Computer Use Code |
LondonParis |
Google, Dataform, Pareto Holdings |
 Ben Cambier, Lewis Hemens |
101-250 |
|
Fleet |
Multi-Domain Enterprise |
SFNYC |
Mercor, Anthropic, MSL |
 Nicolai Ouporov, Andrew Zhou |
51-100 |
|
Parsewave |
Long Horizon |
SFRemote |
Meta, Red Hat |
  Ivan Kudryavtsev, Louis Pan, Louka Ewington-Pitsos |
51-100 |
|
Wirestock |
Creative |
SF |
Utah State, MIT |
  Mikayel Khachatryan, Ashot Mnatsakanyan, Hovhannes Kuloghlyan |
51-100 |
|
Deeptune Acquired |
Code Computer Use |
NYC |
Hebbia |
Tim Lupo |
26-50 |
|
Huzzle Labs |
Long Horizon Code |
LondonBerlin, SF |
Turing |
 Ingmar Klein, Amit Choudhary |
26-50 |
|
Verita AI |
Creative |
SFVancouver |
HRT, Jane Street, Mercor |
 Rithika Kacham, Rishi Kalakuntla |
26-50 |
|
ARIMLABS |
Security Long Horizon |
Warsaw |
Akamai |
 Mykyta Mudryi, Markiian Chaklosh |
11-25 |
|
Chakra Labs |
Computer Use Tool Use |
Brooklyn |
Microsoft, L/S, Snap |
 Nirmal Krishnan, Alex Fung |
11-25 |
|
dmodel |
ML Alignment |
SF |
OpenAI, Google Brain, EleutherAI |
 Anish Tondwalkar, Daniel Moon |
11-25 |
|
HUD |
Long Horizon Code |
SFSingapore |
METR, AWS, Hume |
  Lorenss Martinsons, Parth Patel, Jay Ram |
11-25 |
|
Idler |
Code |
SF |
Meta, Microsoft, Cornell |
  Ivan Chub, Nalu Concepcion, Tony Goss |
11-25 |
|
Incalmo |
Security |
San Mateo |
CMU, MSR, RSAC Labs |
   Brian Singer, Mark DongRL envs: Omer Akgul, Ao Li |
11-25 |
|
Preference Model |
ML Code |
SFToronto, Seattle |
Anthropic, Stripe, Datology |
 Jennifer Zhou, Ning Cao |
11-25 |
|
Symbal |
Code Enterprise |
SF |
Meta AI, General Catalyst, Deeptune |
  Krishay Mukhija, Pranay Manocha, Akash Jain |
11-25 |
|
Taste Labs |
Creative |
NYC |
Exa, Palantir, Mercado Libre |
Thais Castello Branco |
11-25 |
|
Align AI |
Enterprise Code |
NYC |
Meta, Apple, Cornell |
 Spandana Govindgari, Girish Kumar |
1-10 |
|
Andromede |
Long Horizon |
Lausanne |
MIT, EPFL |
 Alexandre Sallinen, Guillaume Allegre |
1-10 |
|
Anthromind |
Medical Long Horizon |
SF |
Google, Forward Health |
 Pratik Karki, Mannat Sandhu |
1-10 |
|
Diffuse Labs |
ML Long Horizon |
Palo AltoSF |
a16z, CMU |
 Daljeet Virdi, Tejpal Singh |
1-10 |
|
Dissei |
Finance |
London |
Warwick, Goldman Sachs, HBS |
  Tudor Popescu, Jai Trivedi, Eddy B |
1-10 |
|
Exabite |
Code |
Remote |
Stanford, MIT, Magic |
Alana Xiang |
1-10 |
|
Good Start Labs |
Games Long Horizon |
BrooklynNYC, Toronto |
Waterloo, Every, Amazon Robotics |
 Alex Duffy, Tyler Marques |
1-10 |
|
Hillclimb |
Math |
SF |
DeepMind, Base |
 Jun Park, Ibrakhim Ustelbay |
1-10 |
|
Ooak Data |
Enterprise |
Paris |
Samsung, GoPuff, YC |
  Thomas Aubry, Pierre-Louis Vouteau, Grégoire Lamy |
1-10 |
|
Phinity |
Chip Design |
SFPalo Alto |
NVIDIA, AWS, Stanford |
 Sonya Jin, Aadi Nashikkar |
1-10 |
|
Plato |
Browser Enterprise |
SF |
MultiOn, Waterloo, Georgia Tech |
 Rob Farlow, Pranav Putta |
1-10 |
|
Rise Data Labs |
Enterprise |
NYC |
Wharton |
Vivian Chen |
1-10 |
|
| Sepal AI Acquired |
Science |
SF |
Turing, Bain, McKinsey |
 Robi Lin, Kat Hu |
1-10 |
|
Theta |
Enterprise |
SF |
DeepSilicon, Cornell, MultiOn |
  Rayan Garg, Tanmay Sharma, Gurvir Singh |
1-10 |
|
Trajectory Labs |
Alignment |
BerkeleyToronto |
METR, GovAI, 80000 Hours |
 Peter McIntyre, Ben West |
1-10 |
|
Vetto AI |
Code Computer Use |
SFSão Paulo, London |
DeepMind, Meta, ITA |
    José André Nunes, Rodrigo Schmidt, Lucas Smaira, Gabriel Albuquerque, Roberta Antunes |
1-10 |
|