readable AI benchmarks (simplified)

readable AI benchmarks

DeepSeek V3.1 (Reasoning) has a Quality Score of 24.3, ranking 178th among 238 scored models. Per 1M tokens, pricing is $0.580 input, $1.68 output, and $0.580 cached input. It has a 128k token context window. Its Reliability Score is 35.2, ranking 181st among 245 scored models, below average (total average: 46.4). Its Value Score is 17.8, low compared with the total Value average of 28.3.

Quality Score24.3coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available

Value Score17.8

Factual reliability35.2

Cache Discount0%

Model specification

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

Token prices USD per 1M tokens

Input: $0.580
Output: $1.68
Cached Input: $0.580
Cache write: not available
Cost per task: not available

Capability

Intelligence: 13.5
Omniscience (native net): -29.6
Correct: 29.0%
Blended price: $0.690

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 87.6%

Correct 29.0%Incorrect 58.6%Partial / not attempted 12.4%

Artificial Analysis benchmarks legacy records

Humanity’s Last Exam: 14%
GPQA Diamond: 78%
CritPt: 2%
AA-LCR: 57%

Similar models

Graph Open on Artificial Analysis