readable AI benchmarks (simplified)

readable AI benchmarks

Meta

Llama 3 Instruct 70B

non-reasoning · open weights · Apr 18, 2024

Llama 3 Instruct 70B has a Quality Score of 15.6, ranking 470th among 551 scored models. Per 1M tokens, pricing is $0.650 input and $2.75 output. It has a 8,192 token context window. Its Reliability Score is 22.8, ranking 417th among 553 scored models, below average (total average: 35.6).

Quality Score15.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability22.8
Cache Discountnot available

Model specification

Reasoning
non-reasoning
Input modalities
none
Output modalities
none
Context window
8,192 tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.650
Output
$2.75
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
5.5
Coding
not available
Agentic
not available
Omniscience
-54.3
Correct
17.7%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 89.8%

Correct 17.7%Incorrect 72.0%Partial / not attempted 10.2%

Artificial Analysis benchmarks

Humanity’s Last Exam
5%
GPQA Diamond
38%
CritPt
0%
AA-Omniscience
23%
AA-LCR
0%

Similar models

Support me! Patreon