Skip to content
aiqbench

Nous-Research · model passport

Nous: Hermes 3 70B Instruct

hermes-3-llama-3-1-70b
  • Open weights
  • 70.6B params
  • 131,072 context
  • Released 2024-07-29(HF repo created)
3/27axes covered
Best percentile
25.8LiveBench
Cohort standing
37.2median 36.6

What the data says

Benchmarked on 3 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 2.6 percentile points between its best and worst axis — 25.8 pct on LiveBench versus 23.2 pct on MMLU-Pro (Artificial Analysis).

  • LiveBench25.8 pct39.6%Verify →
  • LiveCodeBench (Artificial Analysis)24.4 pct18.8%Verify →
  • MMLU-Pro (Artificial Analysis)23.2 pct57.1%Verify →
  • OverallNot benchmarked
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • IFBench (Artificial Analysis)Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked
  • CodingNot benchmarked
  • Instruction followingNot benchmarked
  • Hard promptsNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Run it yourself

RepositoryNousResearch/Hermes-3-Llama-3.1-70B
Parameters70.6B
ArchitectureLlamaForCausalLM

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "NousResearch/Hermes-3-Llama-3.1-70B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Ollama

We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →

Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →

Use it hosted

API model IDnousresearch/hermes-3-llama-3.1-70b
Context length131,072 tokens
Max output16,384 tokens
Input price$0.70 per 1M tokens
Output price$0.70 per 1M tokens

API parameters this endpoint supports

Frequency penaltyLogit biasMax tokensMin-pPresence penaltyRepetition penaltySeedStop sequencesStructured outputsTemperatureTop-kTop-p

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nousresearch/hermes-3-llama-3.1-70b","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • hermes-3-llama-3.1-70b stands at 37.2 (raw mean 24.5) — measured on 3 of 27 axes.

    standingtemplateVerify →

  • hermes-3-llama-3.1-70b stands at 37.2 versus a cohort median of 36.6 across 130 models released within 180 days — above the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →