ZMIME
Comparison · 3 models · Updated Nov 18, 2026

ERNIE 4.5 21B A3B vs Mistral Small 3.2 24B vs Nemotron 3 Super 120B A12B

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. Baidu

    ERNIE 4.5 21B A3B

    Released Jun 30, 2025

    59/100
    • ECI—
    • Price$0.07 / $0.28
    • Context131K
  2. Mistral AI

    Mistral Small 3.2 24B

    Released Jun 20, 2025

    68/100
    • ECI—
    • Price$0.087 / $0.231
    • Context256K
  3. NVIDIA

    Nemotron 3 Super 120B A12B

    Released Mar 11, 2026

    56/100
    • ECI—
    • Price$0.135 / $0.625
    • Context262K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Mistral Small 3.2 24B 68/100, ERNIE 4.5 21B A3B 59/100, Nemotron 3 Super 120B A12B 56/100) 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 priceERNIE 4.5 21B A3BERNIE 4.5 21B A3B $0.122 · Mistral Small 3.2 24B $0.123 · Nemotron 3 Super 120B A12B $0.258 per 1M tokens (3:1 blend)
  • Longest contextNemotron 3 Super 120B A12BNemotron 3 Super 120B A12B 262,144 · Mistral Small 3.2 24B 256,000 · ERNIE 4.5 21B A3B 131,072 tokens
  • Widest inputsMistral Small 3.2 24BERNIE 4.5 21B A3B: Text · Mistral Small 3.2 24B: Text, Images · Nemotron 3 Super 120B A12B: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightERNIE 4.5 21B A3BMistral Small 3.2 24BNemotron 3 Super 120B A12B
Price50%898974
Inputs & features30%255035
Context window20%324343
Specs & price only100%59/10068/10056/100

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 21B A3B vs Mistral Small 3.2 24B vs Nemotron 3 Super 120B A12B specifications side by side
SpecificationERNIE 4.5 21B A3BBaiduMistral Small 3.2 24BMistral AINemotron 3 Super 120B A12BNVIDIA
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.07 (best)$0.087$0.135
Output$0.28$0.231 (best)$0.625
Cached input———
Blended (3:1)$0.122 (best)$0.123$0.258
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 8 providersMedian of 16 providers
Limits
Context window131,072 tokens256,000 tokens262,144 tokens (best)
Max output8,000 tokens16,384 tokens262,144 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoYes
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenApache-2.0OpenOpen
API model ID———
API providers1818 (best)
ReleasedJun 30, 2025Jun 20, 2025Mar 11, 2026
Knowledge cutoff—Oct 31, 2023Jun 2025
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 21B A3B$1.26
  • Mistral Small 3.2 24B$1.33
  • Nemotron 3 Super 120B A12B$2.60
04 — Questions

Which should you choose?

Which is better: ERNIE 4.5 21B A3B, Mistral Small 3.2 24B or Nemotron 3 Super 120B A12B?

There is not enough shared capability evidence to name an overall winner. The scores (Mistral Small 3.2 24B 68/100, ERNIE 4.5 21B A3B 59/100, Nemotron 3 Super 120B A12B 56/100) 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, ERNIE 4.5 21B A3B, Mistral Small 3.2 24B or Nemotron 3 Super 120B A12B?

ERNIE 4.5 21B A3B is cheaper at $0.07 input / $0.28 output per million tokens (median across 1 API provider). Mistral Small 3.2 24B costs $0.087 input / $0.231 output per million tokens (median across 8 API providers); Nemotron 3 Super 120B A12B costs $0.135 input / $0.625 output per million tokens (median across 16 API providers). At a typical mix of three input tokens to one output token, that is $0.122 per million tokens for ERNIE 4.5 21B A3B versus $0.123 for Mistral Small 3.2 24B (1× as much) and $0.258 for Nemotron 3 Super 120B A12B (2.1× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. ERNIE 4.5 21B A3B has not been scored yet, Mistral Small 3.2 24B has not been scored yet and Nemotron 3 Super 120B A12B has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for ERNIE 4.5 21B A3B, Mistral Small 3.2 24B and Nemotron 3 Super 120B A12B 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?

Nemotron 3 Super 120B A12B has the largest context window at 262,144 tokens, against 256,000 for Mistral Small 3.2 24B and 131,072 for ERNIE 4.5 21B A3B. Maximum output per response: ERNIE 4.5 21B A3B up to 8,000, Mistral Small 3.2 24B up to 16,384, Nemotron 3 Super 120B A12B up to 262,144 tokens.

Which can read images, PDFs, audio or video?

ERNIE 4.5 21B A3B accepts text; Mistral Small 3.2 24B accepts text and images; Nemotron 3 Super 120B A12B accepts text. Mistral Small 3.2 24B handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights (Apache-2.0), so you can self-host them.

Which is newer?

Nemotron 3 Super 120B A12B is the newest, released Mar 11, 2026. ERNIE 4.5 21B A3B came out Jun 30, 2025; Mistral Small 3.2 24B came out Jun 20, 2025. Knowledge cutoff: Mistral Small 3.2 24B Oct 31, 2023, Nemotron 3 Super 120B A12B Jun 2025.

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.