readable AI benchmarks (simplified)

readable AI benchmarks

Anthropic

Claude 3 Haiku

non-reasoning · closed weights · Mar 4, 2024

Claude 3 Haiku has a Quality Score of 17.1, ranking 444th among 551 scored models. Per 1M tokens, pricing is $0.250 input and $1.25 output. It has a 200k token context window. Its Reliability Score is 25.7, ranking 369th among 553 scored models, below average (total average: 35.6).

Quality Score17.1coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability25.7
Cache Discountnot available

Model specification

Reasoning
non-reasoning
Input modalities
none
Output modalities
none
Context window
200k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.250
Output
$1.25
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
5.6
Coding
not available
Agentic
not available
Omniscience
-48.6
Correct
17.6%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 83.9%

Correct 17.6%Incorrect 66.3%Partial / not attempted 16.1%

Artificial Analysis benchmarks

Humanity’s Last Exam
4%
GPQA Diamond
37%
CritPt
0%
AA-Omniscience
26%
AA-LCR
28%

Similar models

Support me! Patreon