modelbenchmark.io

Claude 3.5 Haiku

anthropic-claude-3-5-haiku

Compare

Legacy model retained for compatibility with older integrations

Specification

most-agreed values

Context
200K
Max output
8K
Released
2024-11-05
Knowledge cutoff
2024-07
Retires
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.80
Output
$4.00
Cache read
$0.08
Cache write
$1.00

Quality

2 benchmarks · 2 sources

Composite
26th
percentile of 334 scored models
Rank
249 / 334
±0.08 sd
Evidence
2 × 2
one source, or fewer than 3 benchmarks
Effort range
one configuration only
coding23rd2/3 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
SWE-Bench verified40.6default · ToolsSWE-bench
Aider polyglot28.0default · aider diffAider2024-12-21

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
digitalocean$0.80$4.00$0.08$1.00200K8K
gradient_ai · gradient-ai$0.80$4.00200K1K

Other listings of this model

this page is one of them

The corpus files Claude 3.5 Haiku under several keys. This page is the anthropic-claude-3-5-haiku listing. The full record — every host, every price and every benchmark score — is on the main Claude 3.5 Haiku page.