Nous Researchopen-weight
Released: 2025-08-27Artificial Analysis

Hermes 4 - Llama-3.1 70B

Hermes 4 - Llama-3.1 70B from Nous Research, tracked on the Artificial Analysis Intelligence Index.

Intelligence Index
—/ 100
Artificial Analysis Intelligence Index (independent composite)
Throughput Speed
—tok/sec
Output streaming throughput
Time to First Answer
—ms
Time to first answer token, including any thinking
Cost to Run the Index
—USD
Artificial Analysis cost of the full Index run

Measured results · Artificial Analysis

Independent evaluations of Hermes 4 - Llama-3.1 70B (Non-reasoning configuration). Values are reported as published; nothing here is estimated or derived. Snapshot 2026-11-15.

Intelligence Index
—
Cost to run the Index
—
Time per task
—
Omniscience index
—
Reasoning model
No
Cached-input price
—

Reasoning & knowledge

Coding & terminal agents

Agentic work

Long context & documents

Reasoning-effort variants evaluated

VariantIntelligence IndexCost to run IndexOutput speed (tok/s)
Non-reasoning———
Reasoning———
Full analysis on Artificial Analysis

Headline Evaluation Breakdown

Six independently measured evaluations (Artificial Analysis)
Math · AIME 202511.3%
Long context · AA-LCR4.7%
Knowledge · Humanity's Last Exam3.6%
Instruction following · IFBench29.0%

Sourced Benchmark Evaluations (9)

Verified performance across authoritative benchmarks with provenance tracking.
BenchmarkStatusScoreTrustDateSource TypeProvenance
AIMENearing Saturation11.3%
75
2026-11-15independentSource ↗
GPQANearing Saturation49.1%
78
2026-11-15independentSource ↗
Humanity's Last ExamActive3.6%
93
2026-11-15independentSource ↗
LiveCodeBenchSaturated26.9%
39
2026-11-15independentSource ↗
IFBenchActive29%
93
2026-11-15independentSource ↗
τ²-Bench TelecomActive21.6%
93
2026-11-15independentSource ↗
Terminal-Bench HardActive0%
93
2026-11-15independentSource ↗
AA-LCR (Long Context Reasoning)Active4.7%
93
2026-11-15independentSource ↗
CritPtActive0%
93
2026-11-15independentSource ↗
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run nous-research-hermes-4-llama-3-1-70b

# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nous-research-hermes-4-llama-3-1-70b",
    "messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
  }'

Evaluation & Sourcing Notes

Scores listed for Hermes 4 - Llama-3.1 70B represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.

All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.