← All comparisons

Claude Sonnet 4.6 (Non-reasoning, Low Effort) vs Hermes 3 - Llama-3.1 70B

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

Claude Sonnet 4.6 (Non-reasoning, Low Effort)Hermes 3 - Llama-3.1 70B
Intelligence Index42.610.6
Coding Index43.0
Math Index
Output speed (tok/s)54.933.2
Blended price ($/1M)$6.56$0.30
Time to first token (s)1.13s0.38s
aime2.3%
aime 25
artificial analysis coding index43.00
artificial analysis intelligence index42.6010.60
artificial analysis math index
gpqa79.7%40.1%
hle10.8%4.1%
ifbench42.4%
lcr58.7%
livecodebench18.8%
math 50053.8%
mmlu pro57.1%
scicode44.1%23.1%
tau278.9%
terminalbench hard42.4%

Benchmark data from Artificial Analysis.