readable AI benchmarks (simplified)

readable AI benchmarks

DeepSeek

DeepSeek V4 Flash 0420 (Reasoning, High Effort)

reasoning · open weights · Apr 24, 2026

DeepSeek V4 Flash 0420 (Reasoning, High Effort) has a Quality Score of 39.2, ranking 177th among 551 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 38.5, ranking 232nd among 553 scored models, above average (total average: 35.6). Its Value Score is 36.0, high compared with the total Value average of 30.7.

Quality Score39.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score36.0
Factual reliability38.5
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
not available

Capability

Intelligence
26.0
Coding
not available
Agentic
not available
Omniscience
-23.1
Correct
34.9%
Blended price
$0.074

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 92.8%

Correct 34.9%Incorrect 58.0%Partial / not attempted 7.2%

Artificial Analysis benchmarks

τ³-Banking
26%
SciCode
40%
Humanity’s Last Exam
30%
GPQA Diamond
87%
CritPt
3%
AA-Omniscience
38%
AA-LCR
72%

Similar models

Support me! Patreon