← All comparisons

Gemma 4 26B A4B (Reasoning) vs DeepHermes 3 - Mistral 24B Preview (Non-reasoning)

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

Gemma 4 26B A4B (Reasoning)DeepHermes 3 - Mistral 24B Preview (Non-reasoning)
Intelligence Index31.210.9
Coding Index22.4
Math Index
Output speed (tok/s)0.00.0
Blended price ($/1M)$0.20$0.00
Time to first token (s)0.00s0.00s
aime4.7%
aime 25
artificial analysis coding index22.40
artificial analysis intelligence index31.2010.90
artificial analysis math index
gpqa79.2%38.2%
hle18.3%3.9%
ifbench72.4%
lcr55.7%
livecodebench19.5%
math 50059.5%
mmlu pro58.0%
scicode40.0%22.8%
tau243.6%
terminalbench hard13.6%

Benchmark data from Artificial Analysis.