Mistral Small 3.2 24B vs Nemotron 3 Super 120B A12B vs ERNIE 4.5 21B A3B
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Mistral AI
Mistral Small 3.2 24B
68/100- ECI—
- Price$0.087 / $0.231
- Context256K
NVIDIA
Nemotron 3 Super 120B A12B
56/100- ECI—
- Price$0.135 / $0.625
- Context262K
Baidu
ERNIE 4.5 21B A3B
59/100- ECI—
- Price$0.07 / $0.28
- Context131K
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 24BMistral Small 3.2 24B: Text, Images · Nemotron 3 Super 120B A12B: Text · ERNIE 4.5 21B A3B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Mistral Small 3.2 24B | Nemotron 3 Super 120B A12B | ERNIE 4.5 21B A3B |
|---|---|---|---|---|
| Price | 50% | 89 | 74 | 89 |
| Inputs & features | 30% | 50 | 35 | 25 |
| Context window | 20% | 43 | 43 | 32 |
| Specs & price only | 100% | 68/100 | 56/100 | 59/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.087 | $0.135 | $0.07 (best) |
| Output | $0.231 (best) | $0.625 | $0.28 |
| Cached input | — | — | — |
| Blended (3:1) | $0.123 | $0.258 | $0.122 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 8 providers | Median of 16 providers | Median of 1 providers |
| Limits | |||
| Context window | 256,000 tokens | 262,144 tokens (best) | 131,072 tokens |
| Max output | 16,384 tokens | 262,144 tokens (best) | 8,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | OpenApache-2.0 |
| API model ID | — | — | — |
| API providers | 8 | 18 (best) | 1 |
| Released | Jun 20, 2025 | Mar 11, 2026 | Jun 30, 2025 |
| Knowledge cutoff | Oct 31, 2023 | Jun 2025 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Mistral Small 3.2 24B$1.33
Nemotron 3 Super 120B A12B$2.60
ERNIE 4.5 21B A3B$1.26
Which should you choose?
Which is better: Mistral Small 3.2 24B, Nemotron 3 Super 120B A12B or ERNIE 4.5 21B A3B?
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, Mistral Small 3.2 24B, Nemotron 3 Super 120B A12B or ERNIE 4.5 21B A3B?
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. Mistral Small 3.2 24B has not been scored yet, Nemotron 3 Super 120B A12B has not been scored yet and ERNIE 4.5 21B A3B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Mistral Small 3.2 24B, Nemotron 3 Super 120B A12B and ERNIE 4.5 21B A3B 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: Mistral Small 3.2 24B up to 16,384, Nemotron 3 Super 120B A12B up to 262,144, ERNIE 4.5 21B A3B up to 8,000 tokens.
Which can read images, PDFs, audio or video?
Mistral Small 3.2 24B accepts text and images; Nemotron 3 Super 120B A12B accepts text; ERNIE 4.5 21B A3B 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.