readable AI benchmarks

DeepSeek

DeepSeek V4 Pro 0813 (Reasoning, Max Effort)

reasoning · open weights · Aug 13, 2026

Quality Score63.3
Value Score47.9
Reliability50.4
Cache Discount97%

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
1M tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$1.32
Output
$3.96
Cached Input
$0.044
Cached Output
not available
Cost per task
$0.252

Capability

Intelligence
53.2
Coding
68.8
Agentic
49.6
Omniscience
0.8
Correct
49.1%
Blended price
$0.691

Answer outcomes

Correct 49.1%Incorrect 48.3%Abstained 2.6%

Artificial Analysis benchmarks

GDPval-AA v2
55%
τ³-Banking
40%
Terminal-Bench v2.1
79%
SciCode
49%
Humanity’s Last Exam
41%
GPQA Diamond
93%
CritPt
18%
AA-Omniscience
50%
AA-LCR
75%

Similar models