← All comparisons

Claude Opus 4.8 (Adaptive Reasoning, Max Effort) vs DeepSeek R1 Distill Qwen 32B

Anthropic vs DeepSeek — side-by-side benchmark comparison

Claude Opus 4.8 (Adaptive Reasoning, Max Effort)DeepSeek R1 Distill Qwen 32B
Intelligence Index61.417.2
Coding Index56.7
Math Index63.0
Output speed (tok/s)66.90.0
Blended price ($/1M)$10.94$0.00
Time to first token (s)7.91s0.00s
aime68.7%
aime 2563.0%
artificial analysis coding index56.70
artificial analysis intelligence index61.4017.20
artificial analysis math index63.00
gpqa92.0%61.5%
hle45.7%5.5%
ifbench62.2%22.9%
lcr67.7%9.7%
livecodebench27.0%
math 50094.1%
mmlu pro73.9%
scicode53.5%37.6%
tau294.4%
terminalbench hard58.3%

Benchmark data from Artificial Analysis.