Compare AI Models
Select up to 4 models to compare side by side.
Hermes 4 – Llama-3.1 405B (Reasoning)
|
|
|---|---|
| Overview | |
| Provider | Nous Research |
| Our Score | 41 |
| Performance Tier | Efficient |
| Best For | — |
| Released | Aug 2025 |
| Knowledge Cutoff | — |
| Dimension Scores | |
| Intelligence | 4.1 / 10 |
| Technical | 2.9 / 10 |
| Content | 3.5 / 10 |
| Value | 6.0 / 10 |
| Pricing | |
| Input / 1M tokens | $1.00 |
| Output / 1M tokens | $3.00 |
| Performance | |
| Context Window | 0 |
| Throughput (tok/s) | — |
| Latency (TTFT ms) | — |
| Parameters | — |
| Intelligence Indices (Artificial Analysis) | |
| Intelligence | 18.6 |
| Coding | 16 |
| Math | 69.7 |
| Agentic | 16.8 |
| Benchmarks | |
| MMLU-Pro | 0.8 |
| MMLU | — |
| GPQA Diamond | 0.7 |
| GPQA (HF) | — |
| LiveCodeBench | 0.7 |
| HumanEval | — |
| MATH-500 | — |
| AIME '25 | 0.7 |
| AIME | — |
| MATH (HF) | — |
| Humanity's Last Exam | 0.1 |
| SWE-bench | — |
| IFBench | 0.3 |
| IFEval | — |
Looking for the full rankings? View the AI Model Leaderboard or try the Price Calculator to estimate monthly costs.
