← All comparisons

Claude 4.5 Haiku (Non-reasoning) vs DeepSeek R1 Distill Llama 8B

Anthropic vs DeepSeek — side-by-side benchmark comparison

Claude 4.5 Haiku (Non-reasoning)DeepSeek R1 Distill Llama 8B
Intelligence Index31.012.1
Coding Index29.6
Math Index39.041.3
Output speed (tok/s)105.80.0
Blended price ($/1M)$2.19$0.00
Time to first token (s)0.65s0.00s
aime33.3%
aime 2539.0%41.3%
artificial analysis coding index29.60
artificial analysis intelligence index31.0012.10
artificial analysis math index39.0041.30
gpqa64.6%30.2%
hle4.3%4.2%
ifbench42.0%17.6%
lcr43.7%0.0%
livecodebench51.1%23.3%
math 50085.3%
mmlu pro80.0%54.3%
scicode34.4%11.9%
tau232.5%
terminalbench hard27.3%

Benchmark data from Artificial Analysis.