Organizations

Public evidence by organization

Published evidence grouped by organization.

frontier lab22 published results

Anthropic

CoBench and operational automation included. Internal tasks are not public; lab disclosure is not independent replication.

frontier lab41 published results

Current AI self-improvement suite plus original MLE-bench and PaperBench. Graph-only scores withheld.

frontier lab8 published results

GRB, a qualitative RE-Bench assessment and AlphaEvolve. Different internal metrics cannot rank labs.

independent evaluator4 published results

Independent evaluations, task horizons and productivity studies. Selected historical snapshots, not a live leaderboard.

benchmark creator0 published results

Original benchmark-author report; no independent replication included.

academic group0 published results

Historical v1 study; later revisions require separate reconciliation.

frontier lab1 published results

Only Kimi K3 in the original AI4AI-Bench study is included.

academic group0 published results

Source-authored research, with classification separated from independent empirical verification.

other0 published results

Source-authored research, with classification separated from independent empirical verification.

frontier lab1 published results

Organization of Grok 4 in METR's historical TH1 table.

frontier lab1 published results

Organization of DeepSeek-R1 in PaperBench's original Table 4.