readable AI benchmarks (simplified)

readable AI benchmarks

DeepSeek

DeepSeek R1 0528 (May '25)

reasoning · open weights · May 28, 2025

DeepSeek R1 0528 (May '25) has a Quality Score of 28.2, ranking 267th among 551 scored models. Per 1M tokens, pricing is $1.35 input, $3.00 output, and $1.35 cached input. It accepts text input, outputs text, and has a 128k token context window. Its Reliability Score is 36.3, ranking 250th among 553 scored models, above average (total average: 35.6). Its Value Score is 18.8, low compared with the total Value average of 30.7.

Quality Score28.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score18.8
Factual reliability36.3
Cache Discount0%

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
128k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$1.35
Output
$3.00
Cached Input
$1.35
Cache write
not available
Cost per task
not available

Capability

Intelligence
13.1
Coding
not available
Agentic
not available
Omniscience
-27.4
Correct
30.5%
Blended price
$1.52

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 88.5%

Correct 30.5%Incorrect 58.0%Partial / not attempted 11.5%

Artificial Analysis benchmarks

Humanity’s Last Exam
16%
GPQA Diamond
81%
CritPt
1%
AA-Omniscience
36%
AA-LCR
56%

Similar models

Support me! Patreon