← DeepSeek V4 Pro · API · Max effort
Evidenceacceptedthird_party_leaderboard
Artificial Analysis API latency / throughput
Artificial Analysis — DeepSeek V4 Pro (max) · DeepSeek provider
ev_2026_07_dsv4pro_aa_speed
Result
54.5
Confidence B
- Tested
- 2026-07-11
- Runs
- 1
Configuration
How it was measured
- Exact model
- deepseek-v4-pro
- Reasoning
- max
- Agent harness
- none
- Tool access
- none
- Prompting
- AA latency suite
Caveats
Known limitations
- Decode speed is not end-to-end task latency under max reasoning.
- AA notes model is very verbose (token cost can dominate).
- normalisedScore is curator tempo seed.
Weighting
Evidence weight factors
The engine weights each evidence row by these factors (0–1) when fusing scores — higher is more trusted.
relevance0.95
quality0.85
recency1.00
health0.90
comparability0.85
reliability0.75
Benchmark
Artificial Analysis API latency / throughput
Third-party measurements of output tokens/sec and time-to-first-token across API providers for a given model configuration.
Benchmark source →