Home Model series DeepSeek V3 DeepSeek V3 · BrowseComp-zh · Version unspecified; Accuracy · Release history DeepSeek V3 · BrowseComp-zh · Version unspecified; Accuracy · Release history View scores, configurations, and disclosures for BrowseComp-zh · Version unspecified; Accuracy across 3 DeepSeek V3 releases, ordered by release date.
Differences are calculated only for unique, active, exact values between direct predecessors when the unit, metric, and explicitly recorded configuration and conditions match.
2025-08-21 · 1 score record for this release, including 1 exact value (may include historical records)
DeepSeek-V3.1 · BrowseComp-zh scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 49.2% Reported 49.2 · Unit % Published Unconfirmed
DeepSeek-V3.1-Thinking Settings Thinking mode as named in the official table. Unknowns none recorded Tools Tools allowed Reasoning budget not recorded Framework not recorded Protocol not specified Conditions Search Agent section; the card says its internal search framework uses a commercial search API, webpage filter, and 128K context. View this score in rankings
2025-09-22 · 1 score record for this release, including 1 exact value (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
DeepSeek-V3.1-Terminus · BrowseComp-zh scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 45% Reported 45 · Unit % Published Unconfirmed
DeepSeek-V3.1-Terminus reported comparison Settings The table does not specify an effort setting; search-agent template/tool-set changed as stated in the card. Unknowns Do not infer a reasoning mode from the predecessor comparison. Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol not specified Conditions Metric/task snapshot not stated in this comparison table. View this score in rankings
2025-09-29 · 1 score record for this release, including 1 exact value (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
DeepSeek-V3.2-Exp · BrowseComp-zh scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 47.9% Reported 47.9 · Unit % Published Unconfirmed
DeepSeek-V3.2-Exp agentic tool use Settings Rows are under “Agentic Tool Use”; exact scaffold and effort are not stated in this table. Unknowns none recorded Tools Tools allowed Reasoning budget not recorded Framework not recorded Protocol not specified Conditions Agentic Tool Use section; exact metric/harness not stated in this comparison table. View this score in rankings