Benched.ai
View
About
Command Palette
Search for a command to run...
Models
Claude 3.5 Haiku
Anthropic
Vision Model
Proprietary
Context
Release Date
Oct 22, 2024
Knowledge Cutoff
Jul 01, 2024
Window
200k
Pricing
Per 1M tokens
Input
$0.8
Output
$4
Blended 3:1
$1.6
Capabilities
Speed
64 t/s
Input
Output
Reasoning tokens
Latency
TTFT
1.16 ms
500 token response
8.95 s
Benchmarks
Intelligence
●●○○○
Math
●●○○○
Coding
●○○○○
MMLU Pro
63.4%
GPQA
40.8%
HLE
3.5%
SciCode
27.4%
AIME
3.3%
MATH 500
72.1%
LiveCodeBench
31.4%
HumanEval
85.9%
Claude
3.5 Haiku