readable AI benchmarks

DeepSeek

DeepSeek V4 Pro (Reasoning, Max Effort)

reasoning · open weights · Apr 24, 2026

Quality Score52.0
Value Score47.6
Reliability44.6
Cache Discount99%

Model specification

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

Token prices USD per 1M tokens

Input
$0.435
Output
$0.870
Cached Input
$0.0036
Cached Output
not available
Cost per task
$0.047

Capability

Intelligence
45.3
Coding
59.4
Agentic
37.8
Omniscience
-10.7
Correct
43.0%
Blended price
$0.177

Answer outcomes

Correct 43.0%Incorrect 53.7%Abstained 3.4%

Artificial Analysis benchmarks

GDPval-AA v2
40%
τ³-Banking
30%
Terminal-Bench v2.1
64%
SciCode
50%
Humanity’s Last Exam
38%
GPQA Diamond
89%
CritPt
13%
AA-Omniscience
45%
AA-LCR
70%

Similar models