Compare/Nova Pro vs Hermes 4 - Llama-3.1 405B (Reasoning)

Nova ProvsHermes 4 - Llama-3.1 405B (Reasoning)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Amazon

Nova Pro

Input
$0.8/M
Output
$3.2/M
Speed
TTFT
Nous Research

Hermes 4 - Llama-3.1 405B (Reasoning)

Input
$1/M
Output
$3/M
Speed
38 tok/s
TTFT
0.80s

Winner by Category

Cheaper
Nova Pro
Faster (tok/s)
Hermes 4 - Llama-3.1 405B (Reasoning)
Lower Latency
Nova Pro
Benchmarks (2-9)
Hermes 4 - Llama-3.1 405B (Reasoning)

Pricing Comparison

MetricNova ProHermes 4 - Llama-3.1 405B (Reasoning)
Input ($/M tokens)$0.8$1
Output ($/M tokens)$3.2$3
Cost for 1M input + 100K output tokens:
Nova Pro$1.12
Hermes 4 - Llama-3.1 405B (Reasoning)$1.30

Speed Comparison

Output Speed (tokens/s) — higher is better
Nova Pro
Hermes 4 - Llama-3.1 405B (Reasoning)
38 tok/s
Time to First Token (seconds) — lower is better
Nova Pro
Hermes 4 - Llama-3.1 405B (Reasoning)
0.80s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
7.79.0
Coding Index
Math Index
7.069.7
GPQA Diamond
49.9%72.7%
MMLU-Pro
69.1%82.9%
LiveCodeBench
23.3%68.6%
AIME 2025
7.0%69.7%
MATH-500
78.6%
Humanity's Last Exam
3.4%10.3%
SciCode
20.8%25.2%
IFBench
38.1%32.7%
TerminalBench
6.1%11.4%
Nova Pro2 wins
9 winsHermes 4 - Llama-3.1 405B (Reasoning)

Frequently Asked Questions

Which is cheaper, Nova Pro or Hermes 4 - Llama-3.1 405B (Reasoning)?

Nova Pro is cheaper overall. Its blended price (3:1 input/output ratio) is $1.40/M tokens vs $1.50/M for Hermes 4 - Llama-3.1 405B (Reasoning).

Which model performs better on benchmarks?

Hermes 4 - Llama-3.1 405B (Reasoning) wins 9 out of 12 benchmarks compared to 2 for Nova Pro. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Hermes 4 - Llama-3.1 405B (Reasoning) generates tokens faster at 38 tok/s vs 0 tok/s. Nova Pro also has lower time-to-first-token (0.00s vs 0.80s).

When should I use Nova Pro vs Hermes 4 - Llama-3.1 405B (Reasoning)?

Choose based on your priorities: Nova Pro for lower cost, Hermes 4 - Llama-3.1 405B (Reasoning) for stronger benchmark performance, and Hermes 4 - Llama-3.1 405B (Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.