readable AI benchmarks (simplified)

readable AI benchmarks

Alibaba

Qwen2.5 Instruct 72B

non-reasoning · open weights · Sep 19, 2024

Qwen2.5 Instruct 72B has a Quality Score of 17.7, ranking 433rd among 551 scored models. Per 1M tokens, pricing is $0.475 input, $0.495 output, and $0.355 cached input. It has a 131,072 token context window. Its Reliability Score is 23.5, ranking 406th among 553 scored models, below average (total average: 35.6). Its Value Score is 13.8, low compared with the total Value average of 30.7.

Quality Score17.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score13.8
Factual reliability23.5
Cache Discount25%

Model specification

Reasoning
non-reasoning
Input modalities
none
Output modalities
none
Context window
131,072 tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.475
Output
$0.495
Cached Input
$0.355
Cache write
not available
Cost per task
not available

Capability

Intelligence
7.7
Coding
not available
Agentic
not available
Omniscience
-53.1
Correct
17.5%
Blended price
$0.393

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 88.0%

Correct 17.5%Incorrect 70.5%Partial / not attempted 12.0%

Artificial Analysis benchmarks

Humanity’s Last Exam
4%
GPQA Diamond
49%
CritPt
0%
AA-Omniscience
23%

Similar models

Support me! Patreon