The AI arena is free today

Open Superagent

Hermes 3 405B vs Phi 4

Hermes 3 405B and Phi 4 are closely matched at 4.3 and 5.4 on the LLM Stats Score. Phi 4 is 11.4x cheaper per token.

Nous Research · Microsoft · Updated for 2026

Which is better?

Hermes 3 405B and Phi 4 are closely matched on the overall LLM Stats Score at 4.3 and 5.4.

The models split the 2 individual benchmarks reported for both models evenly.

On price, Phi 4 is roughly 11.4x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Hermes 3 405B also accepts a larger context window (131,072 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Hermes 3 405B

  • you process long inputs — it offers a 131,072 token context window

Choose Phi 4

  • cost matters — it's about 11.4x cheaper per token
  • you want the most recent training data — it shipped Dec 2024

At a glance

The differences that matter most.

Core performance indexes
4.3
#301
5.4
#296
3.7
#299
6.5
#287
Cost, coverage & limits
Benchmark wins
1 of 2
1 of 2
Input price
$1.00 / M
$0.07 / M
Output price
$1.00 / M
$0.14 / M
Context window
131,072
16,384

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
Hermes 3 405B
Phi 4
6.7#268
12.8#230
7.5#159
12.9#137
8.7#138
12.9#120
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

13 reported for Hermes 3 405B · 13 for Phi 4

2 shared

Hermes 3 405B outperforms in 1 benchmarks (MMLU), while Phi 4 is better at 1 benchmark (MMLU-Pro).

Both models are evenly matched across the benchmarks.

Fri Sep 18 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Phi 4 costs less

For input processing, Hermes 3 405B ($1.00/1M tokens) is 14.3x more expensive than Phi 4 ($0.07/1M tokens).

For output processing, Hermes 3 405B ($1.00/1M tokens) is 7.1x more expensive than Phi 4 ($0.14/1M tokens).

In conclusion, Hermes 3 405B is more expensive than Phi 4.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Fri Sep 18 2026 • llm-stats.com
Nous Research
Hermes 3 405B
Input tokens$1.00
Output tokens$1.00
Best providerDeepinfra
Microsoft
Phi 4
Input tokens$0.07
Output tokens$0.14
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

390.3B diff

Hermes 3 405B has 390.3B more parameters than Phi 4, making it 2655.1% larger.

Nous Research
Hermes 3 405B
405.0Bparameters
Microsoft
Phi 4
14.7Bparameters
405.0B
Hermes 3 405B
14.7B
Phi 4

Context Window

Maximum input and output token capacity

Hermes 3 405B accepts 131,072 input tokens compared to Phi 4's 16,384 tokens. Hermes 3 405B can generate longer responses up to 131,072 tokens, while Phi 4 is limited to 16,384 tokens.

Nous Research
Hermes 3 405B
Input131,072 tokens
Output131,072 tokens
Microsoft
Phi 4
Input16,384 tokens
Output16,384 tokens
Fri Sep 18 2026 • llm-stats.com

License

Usage and distribution terms

Hermes 3 405B is licensed under Apache 2.0, while Phi 4 uses MIT.

License differences may affect how you can use these models in commercial or open-source projects.

Hermes 3 405B

Apache 2.0

Open weights

Phi 4

MIT

Open weights

Release Timeline

When each model was launched

Hermes 3 405B was released on 2024-10-09, while Phi 4 was released on 2024-12-12.

Phi 4 is 2 months newer than Hermes 3 405B.

Hermes 3 405B

Oct 9, 2024

1.9 years ago

Phi 4

Dec 12, 2024

1.8 years ago

2mo newer

Knowledge Cutoff

When training data ends

Phi 4 has a documented knowledge cutoff of 2024-06-01, while Hermes 3 405B's cutoff date is not specified.

We can confirm Phi 4's training data extends to 2024-06-01, but cannot make a direct comparison without Hermes 3 405B's cutoff date.

Hermes 3 405B

Phi 4

Jun 2024

Provider Availability

Hermes 3 405B is available from DeepInfra. Phi 4 is available from DeepInfra.

Hermes 3 405B

deepinfra logo
Deepinfra
Input Price:Input: $1.00/1MOutput Price:Output: $1.00/1M

Phi 4

deepinfra logo
Deepinfra
Input Price:Input: $0.07/1MOutput Price:Output: $0.14/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Hermes 3 405B and Phi 4 side-by-side, then vote on the output you prefer.

Hermes 3 405B
✓ Preferred
Phi 4
Open in Playground

FAQ

Common questions about Hermes 3 405B vs Phi 4.

Which is better, Hermes 3 405B or Phi 4?

Hermes 3 405B and Phi 4 are closely matched on the LLM Stats Score at 4.3 and 5.4. Hermes 3 405B is made by Nous Research and Phi 4 is made by Microsoft. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Hermes 3 405B compare to Phi 4 in benchmarks?

Hermes 3 405B scores HellaSwag: 90.2%, MT-Bench: 89.3%, BoolQ: 88.9%, Winogrande: 86.3%, ARC-E: 86.2%. Phi 4 scores MMLU: 84.8%, HumanEval+: 82.8%, HumanEval: 82.6%, MGSM: 80.6%, MATH: 80.4%.

Is Hermes 3 405B cheaper than Phi 4?

Phi 4 is 14.3x cheaper for input tokens. Hermes 3 405B costs $1.00/M input and $1.00/M output via deepinfra. Phi 4 costs $0.07/M input and $0.14/M output via deepinfra.

What are the context window sizes for Hermes 3 405B and Phi 4?

Hermes 3 405B supports 131K tokens and Phi 4 supports 16K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Hermes 3 405B and Phi 4?

Key differences include LLM Stats Score (4.3 vs 5.4), context window (131K vs 16K), input pricing ($1.00 vs $0.07/M), licensing (Apache 2.0 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Hermes 3 405B and Phi 4?

Hermes 3 405B is developed by Nous Research and Phi 4 is developed by Microsoft.