← All comparisons

Claude 3.5 Haiku vs DeepSeek R1 0528 Qwen3 8B

Anthropic vs DeepSeek — side-by-side benchmark comparison

Claude 3.5 HaikuDeepSeek R1 0528 Qwen3 8B
Intelligence Index18.716.4
Coding Index10.77.8
Math Index63.7
Output speed (tok/s)0.00.0
Blended price ($/1M)$1.75$0.00
Time to first token (s)0.00s0.00s
aime3.3%65.0%
aime 2563.7%
artificial analysis coding index10.707.80
artificial analysis intelligence index18.7016.40
artificial analysis math index63.70
gpqa40.8%61.2%
hle3.5%5.6%
ifbench42.8%19.9%
lcr23.3%13.0%
livecodebench31.4%51.3%
math 50072.1%93.2%
mmlu pro63.4%73.9%
scicode27.4%20.4%
tau224.6%0.0%
terminalbench hard2.3%1.5%

Benchmark data from Artificial Analysis.