Hermes 4 405B
| Released | 2025-08-26 |
|---|---|
| Price per 1M | $1.00 in · $3.00 out |
| Overall score | 47.6 (early, few results) |
| Context window | 131,072 tokens |
| Provider | Nousresearch |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 47.6 | 3 | |
| Overall: Coding | 46.6 | 1 | |
| Overall: Reasoning | 46.6 | 1 | |
| Overall: Agentic work | 46.6 | 1 | |
| Reasoning | 46.6 | 1 | |
| General | 49.0 | 2 | |
| Value vs price | −1.4 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 49.0 ±6.4 | 2 |
| Non-reasoning | 34.6 ±9.4 | 1 |
| Thinking | 46.6 ±9.4 | 1 |
Evidence
Reasoning 46.6 ±7.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Kagi Reasoning Benchmark | 55.8% | Kagi | 2026-11-11 |
General 49.0 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| EQ-Bench Creative Writing v3 | 1,421 | EQ-Bench | 2026-11-11 |
| EQ-Bench Longform Creative Writing | 51.2% | EQ-Bench | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| Kagi Reasoning Benchmark | 30.1% | Kagi | A stronger configuration result was used |
Names matched to this model
hermes-4-405b