DeepSeek: DeepSeek V4 Pro
DeepSeek: DeepSeek V4 Pro is deepseek's model. On the un-leaked meo benchmark it ranks #10 of 22 with 52.2% accuracy and an Effective Value (๐) of 0.0001 โ earning a correct answer for about $0.0473 in 327s each.
as of 2026-06-08
Per-domain accuracy
Efficiency
- Cost per correct
- $0.0473
- Seconds per correct
- 327
- Tokens per correct
- 15,478
- Correct answers
- 58 / 151
- Total benchmark cost
- $2.74
- Avg tokens / item
- 5,945
Aggregated third-party benchmarks
Artificial Analysis (artificialanalysis.ai). Redistribution requires an AA commercial license.
Model details
- Lab
- deepseek
- Released
- 2026-04-24
- Weights
- Open
- Context
- 1.0M
- Max output
- 384K
- Knowledge cutoff
- โ
- Price in
- $0.43/M
- Price out
- $0.87/M
- Modality
- text->text
Sources: openrouter ยท artificial_analysis ยท meo
FAQ
How accurate is DeepSeek: DeepSeek V4 Pro?
DeepSeek: DeepSeek V4 Pro scores 52.2% overall on the meo benchmark (rank #10 of 22), an un-leaked private holdout graded objective-first.
What is DeepSeek: DeepSeek V4 Pro's Effective Value?
Its Effective Value (๐) is 0.0001 at N=10, ฯ=1, ฮด=1.5 โ a fused metric of accuracy, speed, cost, and error-cascade. ๐ rankings shift with task depth.
How much does DeepSeek: DeepSeek V4 Pro cost per correct answer?
About $0.0473 per correct answer (15,478 tokens, 327 seconds each) at benchmark-time pricing via OpenRouter.
Is DeepSeek: DeepSeek V4 Pro open weights?
Yes โ DeepSeek: DeepSeek V4 Pro is released with open weights.