← All comparisons

GPT-4.1 mini vs Claude 4.1 Opus (Non-reasoning)

OpenAI vs Anthropic — side-by-side benchmark comparison

GPT-4.1 miniClaude 4.1 Opus (Non-reasoning)
Intelligence Index22.936.0
Coding Index18.5
Math Index46.3
Output speed (tok/s)95.144.7
Blended price ($/1M)$0.70$32.81
Time to first token (s)0.59s1.63s
aime43.0%
aime 2546.3%
artificial analysis coding index18.50
artificial analysis intelligence index22.9036.00
artificial analysis math index46.30
gpqa66.4%
hle4.6%
ifbench38.3%
lcr42.3%
livecodebench48.3%
math 50092.5%
mmlu pro78.1%
scicode40.4%
tau252.9%
terminalbench hard7.6%

Benchmark data from Artificial Analysis.