Codesota · Models · NousResearch/Hermes-3-Llama-3.2-3BNousResearch5 results · 1 benchmarks
Model card

NousResearch/Hermes-3-Llama-3.2-3B.

NousResearchopen-source3.21B params
§ 01 · Benchmarks

Every benchmark NousResearch/Hermes-3-Llama-3.2-3B has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01CPTU-BenchNatural Language Processing · Polish Text Understandingphraseology2.8%#69/93source ↗
02CPTU-BenchNatural Language Processing · Polish Text Understandinglanguage-understanding2.7%#80/93source ↗
03CPTU-BenchNatural Language Processing · Polish Text Understandingaverage2.3%#81/93source ↗
04CPTU-BenchNatural Language Processing · Polish Text Understandingtricky-questions1.1%#81/93source ↗
05CPTU-BenchNatural Language Processing · Polish Text Understandingsentiment2.6%#87/93source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where NousResearch/Hermes-3-Llama-3.2-3B actually performs.

Natural Language Processing
1
benchmark
avg rank #79.6
§ 04 · Related models

Other NousResearch models scored on Codesota.

Hermes-2-Pro-Llama-3-8B
0 results
Hermes-2-Theta-Llama-3-8B
0 results
Hermes-3-Llama-3.1-8B
0 results
Nous-Hermes-2-SOLAR-10.7B
0 results
§ 05 · Sources & freshness

Where these numbers come from.

SpeakLeash/CPTU-Bench
5
results
5 of 5 rows marked verified.