readable AI benchmarks (simplified)

readable AI benchmarks

ByteDance Seed

Seed-OSS-36B-Instruct

reasoning · open weights · Aug 20, 2025

Seed-OSS-36B-Instruct has a Quality Score of 21.2, ranking 358th among 551 scored models. Per 1M tokens, pricing is $0.210 input and $0.570 output. It has a 512k token context window. Its Reliability Score is 23.8, ranking 400th among 553 scored models, below average (total average: 35.6).

Quality Score21.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability23.8
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
512k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.210
Output
$0.570
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
12.1
Coding
not available
Agentic
not available
Omniscience
-52.5
Correct
18.2%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 88.9%

Correct 18.2%Incorrect 70.7%Partial / not attempted 11.1%

Artificial Analysis benchmarks

Humanity’s Last Exam
10%
GPQA Diamond
73%
CritPt
0%
AA-Omniscience
24%
AA-LCR
61%

Similar models

Support me! Patreon