← DeepSeek V4 Pro · API · Max effort
Evidencesupersededvendor_reported
GPQA Diamond
DeepSeek V4-Pro-Max — GPQA Diamond
ev_2026_07_dsv4pro_gpqa
Result
90.1%
Confidence B
- Tested
- 2026-04-24
- Runs
- 1
Configuration
How it was measured
- Exact model
- deepseek-v4-pro
- Reasoning
- max
- Agent harness
- none
- Tool access
- none
- Prompting
- vendor standard GPQA
SUPERSEDED by independent AA GPQA (ev_2026_07_dsv4pro_aa_gpqa). Kept for audit trail.
Caveats
Known limitations
- Vendor-reported; cannot receive confidence S.
- Superseded by independent AA float for scoring.
Weighting
Evidence weight factors
The engine weights each evidence row by these factors (0–1) when fusing scores — higher is more trusted.
relevance0.95
quality0.55
recency0.90
health0.70
comparability0.85
reliability0.70
Benchmark
GPQA Diamond
Graduate-level science questions (biology, physics, chemistry) designed to be Google-proof; Diamond is the hardest subset where PhD experts score ~65%.
Benchmark source →