← All comparisons

Grok 3 mini Reasoning (high) vs Hermes 3 - Llama-3.1 70B

xAI vs Nous Research — side-by-side benchmark comparison

Grok 3 mini Reasoning (high)Hermes 3 - Llama-3.1 70B
Intelligence Index32.110.6
Coding Index25.2
Math Index84.7
Output speed (tok/s)56.833.2
Blended price ($/1M)$0.35$0.30
Time to first token (s)0.42s0.38s
aime93.3%2.3%
aime 2584.7%
artificial analysis coding index25.20
artificial analysis intelligence index32.1010.60
artificial analysis math index84.70
gpqa79.1%40.1%
hle11.1%4.1%
ifbench45.9%
lcr50.3%
livecodebench69.6%18.8%
math 50099.2%53.8%
mmlu pro82.8%57.1%
scicode40.6%23.1%
tau290.4%
terminalbench hard17.4%

Benchmark data from Artificial Analysis.