readable AI benchmarks (simplified)

readable AI benchmarks

DeepSeek

DeepSeek V4 Flash 0420 (Reasoning, Max Effort)

reasoning · open weights · Apr 24, 2026

DeepSeek V4 Flash 0420 (Reasoning, Max Effort) has a Quality Score of 37.6, ranking 194th among 553 scored models. Per 1M tokens, pricing is $0.130 input, $0.280 output, and $0.028 cached input. It has a 1M token context window. Its Reliability Score is 38.0, ranking 238th among 555 scored models, above average (total average: 35.7). Its Value Score is 34.5, around average compared with the total Value average of 30.7.

Quality Score37.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score34.5
Factual reliability38.0
Cache Discount78%

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
1M tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.130
Output
$0.280
Cached Input
$0.028
Cache write
not available
Cost per task
$0.118

Capability

Intelligence
24.2
Coding
not available
Agentic
not available
Omniscience
-23.9
Correct
36.8%
Blended price
$0.074

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 97.5%

Correct 36.8%Incorrect 60.7%Partial / not attempted 2.5%

Artificial Analysis benchmarks

GDPval-AA v2
26%
τ³-Banking
31%
SciCode
45%
Humanity’s Last Exam
35%
GPQA Diamond
89%
CritPt
7%
AA-Omniscience
38%
AA-LCR
74%

Similar models

Support me! Patreon