← All comparisons

DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) vs Qwen3.5 2B (Reasoning)

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

DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)Qwen3.5 2B (Reasoning)
Intelligence Index7.616.3
Coding Index3.5
Math Index
Output speed (tok/s)0.00.0
Blended price ($/1M)$0.00$0.04
Time to first token (s)0.00s0.00s
aime0.0%
aime 25
artificial analysis coding index3.50
artificial analysis intelligence index7.6016.30
artificial analysis math index
gpqa27.0%45.6%
hle4.3%2.1%
ifbench31.5%
lcr23.7%
livecodebench8.5%
math 50021.8%
mmlu pro36.5%
scicode9.1%2.8%
tau269.0%
terminalbench hard3.8%

Benchmark data from Artificial Analysis.