← All benchmarks

Claude 4.5 Haiku (Non-reasoning)

Anthropic · Released 2025-10-15 · Independent benchmark scores from Artificial Analysis

Intelligence Index
23.7
Output speed
129.1
tokens/sec
Blended price
$2.00
per 1M tokens
Time to first token
0.61s

Model metadata

Model IDc2b1e769-7aee-4669-8076-73918bdebf6c
Slugclaude-4-5-haiku
Release date2025-10-15
ProviderAnthropic
Provider sluganthropic
Output speed129.1 tok/s
Time to first token0.61s
Time to first answer0.61s
Blended price ($/1M)$2.00
Input price ($/1M)$1.00
Output price ($/1M)$5.00

All evaluation scores (17)

aime
aime 2539.0%
artificial analysis coding index
artificial analysis intelligence index23.70
artificial analysis math index39.00
gpqa64.6%
hle4.3%
ifbench42.0%
lcr43.7%
livecodebench51.1%
math 500
mmlu pro80.0%
scicode34.4%
tau banking
tau232.5%
terminalbench hard27.3%
terminalbench v2 1

Source: artificialanalysis.ai/models/claude-4-5-haiku

Benchmark data from Artificial Analysis.