Skip to main content

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

meo rank
#10
of 22
Accuracy
52.2%
overall
๐• index (top=100)
0.17
raw ๐• 0.0001 ยท N=10
$ / correct
$0.0473
327s each

Per-domain accuracy

Theory of mind
100%
Regex automaton
100%
CSP (unsatisfiable)
94%
Tape machine
93%
Framework bias
67%
Watson-Glaser
25%
Long arithmetic
13%
Logic / math / CS
8%
Base-rate bias
5%
State tracking
0%

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.