Home Model series DeepSeek V4 Pro DeepSeek-V4-Pro-0813 DeepSeek-V4-Pro-0813 · Humanity's Last Exam · V4-0813/0731 card does not specify metric or task subset · Scores and configurations DeepSeek-V4-Pro-0813 · Humanity's Last Exam · V4-0813/0731 card does not specify metric or task subset · Scores and configurations DeepSeek-V4-Pro-0813 record for Humanity's Last Exam · V4-0813/0731 card does not specify metric or task subset. 2 score records for this release, including 2 exact values (may include historical records). Includes 2 source locations.
Scores and evaluation conditions DeepSeek-V4-Pro-0813 · Humanity's Last Exam scores and configurations Metric and score Configuration and evaluation conditions Sources Reported score 42.7 Reported 42.7 · Unit not specified Published Unconfirmed
DeepSeek-V4-Pro-0813, max reasoning effort Settings The card identifies Max reasoning effort and DeepSeek Harness Minimal mode for code-agent evaluations; temperature=1.0 and top_p=0.95. Unknowns Effort and harness applicability is only asserted for the card-defined code-agent/public rows. Tools Tools forbidden Reasoning budget not recorded Framework not recorded Protocol No-tools column in the source row. Conditions HLE without tools; the original row does not state metric or subset. View this score in rankings Reported score 60 Reported 60 · Unit not specified Published Unconfirmed
DeepSeek-V4-Pro-0813, max reasoning effort Settings The card identifies Max reasoning effort and DeepSeek Harness Minimal mode for code-agent evaluations; temperature=1.0 and top_p=0.95. Unknowns Effort and harness applicability is only asserted for the card-defined code-agent/public rows. Tools Tools allowed Reasoning budget not recorded Framework not recorded Protocol With-tools column in the source row. Conditions HLE with tools; the original row does not state metric or subset. View this score in rankings
Benchmark versions and metrics Reported score · Unit not specified · Ranking direction unconfirmed