ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Hermes 3 70B Instruct vs Nemotron VoiceChat vs Nova 2 Pro

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. Nous Research

    Hermes 3 70B Instruct

    Released Aug 18, 2024

    34/100
    • ECI—
    • Price$0.70 / $0.70
    • Context131K
  2. NVIDIA

    Nemotron VoiceChat

    Released Mar 16, 2026

    67/100
    • ECI—
    • PriceFree / Free
    • Context128K
  3. Amazon

    Nova 2 Pro

    Released Dec 3, 2025

    87/100
    • ECI—
    • PriceFree / Free
    • Context1M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Nova 2 Pro 87/100, Nemotron VoiceChat 67/100, Hermes 3 70B Instruct 34/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceNemotron VoiceChat and Nova 2 ProNemotron VoiceChat Free · Nova 2 Pro Free · Hermes 3 70B Instruct $0.70 per 1M tokens (3:1 blend)
  • Longest contextNova 2 ProNova 2 Pro 1,000,000 · Hermes 3 70B Instruct 131,072 · Nemotron VoiceChat 128,000 tokens
  • Widest inputsNova 2 ProHermes 3 70B Instruct: Text · Nemotron VoiceChat: Text, Audio · Nova 2 Pro: Text, Images, PDFs, Video
  • Self-hostingHermes 3 70B Instruct and Nemotron VoiceChatPublishes downloadable weights
How the score is built
MeasureWeightHermes 3 70B InstructNemotron VoiceChatNova 2 Pro
Price50%55100100
Inputs & features30%03580
Context window20%323264
Specs & price only100%34/10067/10087/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Hermes 3 70B Instruct vs Nemotron VoiceChat vs Nova 2 Pro specifications side by side
SpecificationHermes 3 70B InstructNous ResearchNemotron VoiceChatNVIDIANova 2 ProAmazon
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.70Free (best)Free (best)
Output$0.70Free (best)Free (best)
Cached input———
Blended (3:1)$0.70Free (best)Free (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersOfficial Nvidia APIOfficial Nova API
Limits
Context window131,072 tokens128,000 tokens1,000,000 tokens (best)
Max output16,384 tokens8,192 tokens64,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoYes
AudioNoYesNo
VideoNoNoYes
ReasoningNoNoYes
Tool callingNoYesYes
Structured outputNoNoNo
Availability
WeightsOpenOpenProprietary
API model ID—nvidia/nemotron-voicechatnova-2-pro-v1
API providers111
ReleasedAug 18, 2024Mar 16, 2026Dec 3, 2025
Knowledge cutoffDec 31, 2023——
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Hermes 3 70B Instruct$8.40
  • Nemotron VoiceChatFree
  • Nova 2 ProFree
04 — Questions

Which should you choose?

Which is better: Hermes 3 70B Instruct, Nemotron VoiceChat or Nova 2 Pro?

There is not enough shared capability evidence to name an overall winner. The scores (Nova 2 Pro 87/100, Nemotron VoiceChat 67/100, Hermes 3 70B Instruct 34/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Hermes 3 70B Instruct, Nemotron VoiceChat or Nova 2 Pro?

Nemotron VoiceChat is cheaper at Free input / Free output per million tokens (official Nvidia API price). Nova 2 Pro costs Free input / Free output per million tokens (official Nova API price); Hermes 3 70B Instruct costs $0.70 input / $0.70 output per million tokens (median across 1 API provider). Nemotron VoiceChat is listed as free.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Hermes 3 70B Instruct has not been scored yet, Nemotron VoiceChat has not been scored yet and Nova 2 Pro has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Hermes 3 70B Instruct, Nemotron VoiceChat and Nova 2 Pro yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Hermes 3 70B Instruct does not support tool calling, which most coding agents need.

Which has the bigger context window?

Nova 2 Pro has the largest context window at 1,000,000 tokens, against 131,072 for Hermes 3 70B Instruct and 128,000 for Nemotron VoiceChat. Maximum output per response: Hermes 3 70B Instruct up to 16,384, Nemotron VoiceChat up to 8,192, Nova 2 Pro up to 64,000 tokens.

Which can read images, PDFs, audio or video?

Hermes 3 70B Instruct accepts text; Nemotron VoiceChat accepts text and audio; Nova 2 Pro accepts text, images, PDFs and video. Nova 2 Pro handles the widest range of inputs.

Are any of these open source?

Hermes 3 70B Instruct and Nemotron VoiceChat publishes its weights and can be self-hosted; Nova 2 Pro is proprietary.

Which is newer?

Nemotron VoiceChat is the newest, released Mar 16, 2026. Nova 2 Pro came out Dec 3, 2025; Hermes 3 70B Instruct came out Aug 18, 2024. Knowledge cutoff: Hermes 3 70B Instruct Dec 31, 2023.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.