readable AI benchmarks (simplified)

readable AI benchmarks

DeepSeek

DeepSeek V3.1 Terminus (Non-reasoning)

non-reasoning · open weights · Sep 22, 2025

DeepSeek V3.1 Terminus (Non-reasoning) has a Quality Score of 24.8, ranking 311th among 551 scored models. Per 1M tokens, pricing is $0.270 input, $1.00 output, and $0.135 cached input. It has a 128k token context window. Its Reliability Score is 28.3, ranking 328th among 553 scored models, below average (total average: 35.6). Its Value Score is 20.5, low compared with the total Value average of 30.7.

Quality Score24.8coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score20.5
Factual reliability28.3
Cache Discount50%

Model specification

Reasoning
non-reasoning
Input modalities
none
Output modalities
none
Context window
128k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.270
Output
$1.00
Cached Input
$0.135
Cache write
not available
Cost per task
not available

Capability

Intelligence
13.9
Coding
not available
Agentic
not available
Omniscience
-43.5
Correct
23.5%
Blended price
$0.249

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 90.5%

Correct 23.5%Incorrect 67.0%Partial / not attempted 9.5%

Artificial Analysis benchmarks

Humanity’s Last Exam
9%
GPQA Diamond
75%
CritPt
0%
AA-Omniscience
28%
AA-LCR
45%

Similar models

Support me! Patreon