Find tools, models, companies, news, guides, comparisons and benchmark data from one research-driven index.
Agents' Last Exam — official/provider-reported evaluation result. Methodology conditions are preserved in the re...
Publicly reported professional agents benchmark result.
Human-validated 500-instance SWE-bench subset used to evaluate coding agents and systems.
Terminal-Bench 2.0 leaderboard accuracy for terminal-based agent tasks. Results are listed with agent, model, da...
Publicly reported finance agents benchmark result.
Publicly reported legal agents benchmark result.
Real-world production-time reduction calculated from an official customer example: two weeks to five days.
SWE-bench Verified (OpenAI 477 Tasks) — official/provider-reported evaluation result. Methodology conditions are...
Toolathlon — official/provider-reported evaluation result. Methodology conditions are preserved in the result no...
Tau2 Average — official/provider-reported evaluation result. Methodology conditions are preserved in the result...
Publicly reported coding & terminal agents benchmark result.
Publicly reported scientific agents benchmark result.
MMLU-Pro is a robust multi-task language-understanding benchmark with a stronger emphasis on challenging reasoni...
DeepResearch Bench RACE overall report-quality score across 100 PhD-level tasks in 22 fields.
Percent correct for Methods, Participants and Interventions extraction tasks on the published evaluation.
