Home Model series Claude Sonnet Claude Sonnet 4.6 Claude Sonnet 4.6 · Finance Agent · Vals AI SEC-filing research benchmark · Scores and configurations Claude Sonnet 4.6 · Finance Agent · Vals AI SEC-filing research benchmark · Scores and configurations Claude Sonnet 4.6 record for Finance Agent · Vals AI SEC-filing research benchmark. 2 score records for this release, including 2 exact values (may include historical records). Includes 2 source locations.
Scores and evaluation conditions Claude Sonnet 4.6 · Finance Agent scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 63.3% Reported 63.30% · Unit % Published Unconfirmed
Max thinking Settings Max thinking setting, as named by Vals AI for Finance Agent. Unknowns Thinking token budget and sampling settings are not stated. Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol Vals AI Finance Agent SEC-filing research benchmark. Conditions Max Thinking configuration; task count and thinking-token budget not stated in the System Card. View this score in rankings Accuracy 61.4% Reported 61.40% · Unit % Published Unconfirmed
High thinking Settings High thinking setting, as named by Vals AI for Finance Agent. Unknowns Thinking token budget and sampling settings are not stated. Tools Tool access not recorded Reasoning budget high Framework not recorded Protocol Vals AI Finance Agent SEC-filing research benchmark. Conditions High Thinking configuration; task count and thinking-token budget not stated in the System Card. View this score in rankings
Benchmark versions and metrics Aliases Finance Agent v1.1
Accuracy · % · Higher is better