← All comparisons

Claude Opus 4.5 (Non-reasoning) vs DeepSeek R1 Distill Qwen 1.5B

Anthropic vs DeepSeek — side-by-side benchmark comparison

Claude Opus 4.5 (Non-reasoning)DeepSeek R1 Distill Qwen 1.5B
Intelligence Index43.19.1
Coding Index42.9
Math Index62.722.0
Output speed (tok/s)57.00.0
Blended price ($/1M)$10.94$0.00
Time to first token (s)0.93s0.00s
aime17.7%
aime 2562.7%22.0%
artificial analysis coding index42.90
artificial analysis intelligence index43.109.10
artificial analysis math index62.7022.00
gpqa81.0%9.8%
hle12.9%3.3%
ifbench43.0%13.2%
lcr65.3%0.3%
livecodebench73.8%7.0%
math 50068.7%
mmlu pro88.9%26.9%
scicode47.0%6.6%
tau286.3%
terminalbench hard40.9%

Benchmark data from Artificial Analysis.