ZMIME
Comparison · 3 models · Updated Nov 18, 2026

ERNIE 4.5 300B A47B vs Llama 3.1 Nemotron 70B Instruct vs Nova 2 Pro

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

Price in rating: Excluded · Include price

  1. Baidu

    ERNIE 4.5 300B A47B

    Released Jun 30, 2025

    28/100
    • ECI—
    • Price$0.28 / $1.10
    • Context131K
  2. NVIDIA

    Llama 3.1 Nemotron 70B Instruct

    Released Apr 15, 2025Deprecated

    28/100
    • ECI—
    • Price$0.478 / $0.504
    • Context128K
  3. Amazon

    Nova 2 Pro

    Released Dec 3, 2025

    74/100
    • 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 74/100, ERNIE 4.5 300B A47B 28/100, Llama 3.1 Nemotron 70B Instruct 28/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. 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 priceNova 2 ProNova 2 Pro Free · Llama 3.1 Nemotron 70B Instruct $0.485 · ERNIE 4.5 300B A47B $0.485 per 1M tokens (3:1 blend)
  • Longest contextNova 2 ProNova 2 Pro 1,000,000 · ERNIE 4.5 300B A47B 131,072 · Llama 3.1 Nemotron 70B Instruct 128,000 tokens
  • Widest inputsNova 2 ProERNIE 4.5 300B A47B: Text · Llama 3.1 Nemotron 70B Instruct: Text · Nova 2 Pro: Text, Images, PDFs, Video
  • Self-hostingERNIE 4.5 300B A47B and Llama 3.1 Nemotron 70B InstructPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightERNIE 4.5 300B A47BLlama 3.1 Nemotron 70B InstructNova 2 Pro
Inputs & features60%252580
Context window40%323264
Specs only100%28/10028/10074/100

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.

ERNIE 4.5 300B A47B vs Llama 3.1 Nemotron 70B Instruct vs Nova 2 Pro specifications side by side
SpecificationERNIE 4.5 300B A47BBaiduLlama 3.1 Nemotron 70B InstructNVIDIANova 2 ProAmazon
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.28$0.478Free (best)
Output$1.10$0.504Free (best)
Cached input———
Blended (3:1)$0.485$0.485Free (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 2 providersOfficial Nova API
Limits
Context window131,072 tokens128,000 tokens1,000,000 tokens (best)
Max output12,000 tokens8,192 tokens64,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoYes
AudioNoNoNo
VideoNoNoYes
ReasoningNoNoYes
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenApache-2.0OpenProprietary
API model ID—nvidia/llama-3.1-nemotron-70b-instructnova-2-pro-v1
API providers13 (best)1
ReleasedJun 30, 2025Apr 15, 2025Dec 3, 2025
Knowledge cutoff———
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.

  • ERNIE 4.5 300B A47B$5.00
  • Llama 3.1 Nemotron 70B Instruct$5.79
  • Nova 2 ProFree
04 — Questions

Which should you choose?

Which is better: ERNIE 4.5 300B A47B, Llama 3.1 Nemotron 70B Instruct or Nova 2 Pro?

There is not enough shared capability evidence to name an overall winner. The scores (Nova 2 Pro 74/100, ERNIE 4.5 300B A47B 28/100, Llama 3.1 Nemotron 70B Instruct 28/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, ERNIE 4.5 300B A47B, Llama 3.1 Nemotron 70B Instruct or Nova 2 Pro?

Nova 2 Pro is cheaper at Free input / Free output per million tokens (official Nova API price). Llama 3.1 Nemotron 70B Instruct costs $0.478 input / $0.504 output per million tokens (median across 2 API providers; free on Nvidia); ERNIE 4.5 300B A47B costs $0.28 input / $1.10 output per million tokens (median across 1 API provider). Nova 2 Pro is listed as free.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. ERNIE 4.5 300B A47B has not been scored yet, Llama 3.1 Nemotron 70B Instruct 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 ERNIE 4.5 300B A47B, Llama 3.1 Nemotron 70B Instruct and Nova 2 Pro yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

Nova 2 Pro has the largest context window at 1,000,000 tokens, against 131,072 for ERNIE 4.5 300B A47B and 128,000 for Llama 3.1 Nemotron 70B Instruct. Maximum output per response: ERNIE 4.5 300B A47B up to 12,000, Llama 3.1 Nemotron 70B Instruct up to 8,192, Nova 2 Pro up to 64,000 tokens.

Which can read images, PDFs, audio or video?

ERNIE 4.5 300B A47B accepts text; Llama 3.1 Nemotron 70B Instruct accepts text; Nova 2 Pro accepts text, images, PDFs and video. Nova 2 Pro handles the widest range of inputs.

Are any of these open source?

ERNIE 4.5 300B A47B and Llama 3.1 Nemotron 70B Instruct publishes its weights (Apache-2.0) and can be self-hosted; Nova 2 Pro is proprietary.

Which is newer?

Nova 2 Pro is the newest, released Dec 3, 2025. ERNIE 4.5 300B A47B came out Jun 30, 2025; Llama 3.1 Nemotron 70B Instruct came out Apr 15, 2025.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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.