← All comparisons

DeepSeek V4 Flash (Reasoning, High Effort) vs Claude 4.1 Opus (Non-reasoning)

DeepSeek vs Anthropic — side-by-side benchmark comparison

DeepSeek V4 Flash (Reasoning, High Effort)Claude 4.1 Opus (Non-reasoning)
Intelligence Index46.036.0
Coding Index39.8
Math Index
Output speed (tok/s)0.044.7
Blended price ($/1M)$0.17$32.81
Time to first token (s)0.00s1.63s
aime
aime 25
artificial analysis coding index39.80
artificial analysis intelligence index46.0036.00
artificial analysis math index
gpqa86.7%
hle27.8%
ifbench73.5%
lcr62.7%
livecodebench
math 500
mmlu pro
scicode42.0%
tau295.6%
terminalbench hard38.6%

Benchmark data from Artificial Analysis.