← All comparisons

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) vs Mi:dm K 2.5 Pro Preview

Anthropic vs Korea Telecom — side-by-side benchmark comparison

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)Mi:dm K 2.5 Pro Preview
Intelligence Index51.7
Coding Index50.911.9
Math Index78.7
Output speed (tok/s)68.20.0
Blended price ($/1M)$6.56$0.00
Time to first token (s)55.35s0.00s
aime
aime 2578.7%
artificial analysis coding index50.9011.90
artificial analysis intelligence index51.70
artificial analysis math index78.70
gpqa87.5%72.2%
hle30.0%8.8%
ifbench56.6%45.6%
lcr70.7%11.0%
livecodebench57.6%
math 500
mmlu pro81.3%
scicode46.8%29.7%
tau275.7%49.4%
terminalbench hard53.0%3.0%

Benchmark data from Artificial Analysis.