# Hermes 4 405B vs Muse Spark

> Muse Spark has enough public results to be ranked (#46); Hermes 4 405B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/hermes-4-405b-vs-muse-spark
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in writing & preference, where Muse Spark leads 66.0 to 52.9.
- Hermes 4 405B has downloadable open weights; the other is API-only.

## Snapshot

| | Hermes 4 405B | Muse Spark |
|---|---|---|
| Provider | Nous Research | Meta |
| Noometry Index | 37.6 | 50.6 |
| Rank | — | 46 |
| Context | 131K | — |
| Input $/M | $1 | — |
| Output $/M | $3 | — |
| Weights | Open | Proprietary |

## Coding

- Hermes 4 405B: —
- Muse Spark: 46.2 (#69)

| Benchmark | Hermes 4 405B | Muse Spark |
|---|---|---|
| SciCode | — | 51.5% |
| LMArena Coding | — | 1481 |

## Reasoning

- Hermes 4 405B: 26.1
- Muse Spark: 35.9 (#67)

| Benchmark | Hermes 4 405B | Muse Spark |
|---|---|---|
| Kagi LLM Benchmark | 55.8% | — |
| CritPt | — | 11.3% |
| LMArena Hard Prompts | — | 1474 |
| Epoch Capabilities Index | — | 152.04 |

## Math

- Hermes 4 405B: —
- Muse Spark: 47.8 (#66)

| Benchmark | Hermes 4 405B | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 17% |
| LMArena Math | — | 1455 |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |

## Knowledge

- Hermes 4 405B: —
- Muse Spark: 65.7 (#13)

| Benchmark | Hermes 4 405B | Muse Spark |
|---|---|---|
| GPQA Diamond | — | 89.8% |
| Humanity's Last Exam | — | 40.6% |
| LMArena Expert | — | 1457 |

## Multimodal

- Hermes 4 405B: —
- Muse Spark: 43.4 (#24)

| Benchmark | Hermes 4 405B | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |

## Multilingual

- Hermes 4 405B: —
- Muse Spark: 56.1 (#24)

| Benchmark | Hermes 4 405B | Muse Spark |
|---|---|---|
| LMArena Non-English | — | 1464 |
| LMArena Chinese | — | 1509 |
| LMArena French | — | 1497 |
| LMArena German | — | 1497 |
| LMArena Korean | — | 1459 |
| LMArena Russian | — | 1466 |
| LMArena Spanish | — | 1472 |

## Instruction Following

- Hermes 4 405B: —
- Muse Spark: 75.9 (#51)

| Benchmark | Hermes 4 405B | Muse Spark |
|---|---|---|
| LMArena Instruction Following | — | 1442 |

## Long Context

- Hermes 4 405B: —
- Muse Spark: 44.4 (#69)

| Benchmark | Hermes 4 405B | Muse Spark |
|---|---|---|
| LMArena Longer Query | — | 1451 |

## Writing & Preference

- Hermes 4 405B: 52.9
- Muse Spark: 66.0 (#39)

| Benchmark | Hermes 4 405B | Muse Spark |
|---|---|---|
| LMArena Text | — | 1474 |
| LMArena Creative Writing | — | 1459 |
| EQ-Bench Creative Writing | 1421 | — |
| LMArena Multi-Turn | — | 1477 |

## FAQ

### Is Hermes 4 405B better than Muse Spark?

Muse Spark has enough public results to be ranked (#46); Hermes 4 405B does not yet, so treat this comparison as directional.

### How many benchmarks do Hermes 4 405B and Muse Spark share?

0 benchmarks have published results for both models. Hermes 4 405B has 2 scored results on Noometry and Muse Spark has 27.
