ERNIE 4.5 21B A3B vs Rnj-1 Instruct vs Mistral Small 3.2 24B
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Baidu
ERNIE 4.5 21B A3B
59/100- ECI—
- Price$0.07 / $0.28
- Context131K
Essential AI
Rnj-1 Instruct
52/100- ECI—
- Price$0.15 / $0.15
- Context33K
Mistral AI
Mistral Small 3.2 24B
68/100- ECI—
- Price$0.087 / $0.231
- Context256K
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, Rnj-1 Instruct 52/100) 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 · Rnj-1 Instruct $0.15 per 1M tokens (3:1 blend)
- Longest contextMistral Small 3.2 24BMistral Small 3.2 24B 256,000 · ERNIE 4.5 21B A3B 131,072 · Rnj-1 Instruct 32,768 tokens
- Widest inputsMistral Small 3.2 24BERNIE 4.5 21B A3B: Text · Rnj-1 Instruct: Text · Mistral Small 3.2 24B: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | ERNIE 4.5 21B A3B | Rnj-1 Instruct | Mistral Small 3.2 24B |
|---|---|---|---|---|
| Price | 50% | 89 | 85 | 89 |
| Inputs & features | 30% | 25 | 25 | 50 |
| Context window | 20% | 32 | 11 | 43 |
| Specs & price only | 100% | 59/100 | 52/100 | 68/100 |
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 | Rnj-1 InstructEssential AI | ||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.07 (best) | $0.15 | $0.087 |
| Output | $0.28 | $0.15 (best) | $0.231 |
| Cached input | — | — | — |
| Blended (3:1) | $0.122 (best) | $0.15 | $0.123 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 1 providers | Median of 8 providers |
| Limits | |||
| Context window | 131,072 tokens | 32,768 tokens | 256,000 tokens (best) |
| Max output | 8,000 tokens | 32,768 tokens (best) | 16,384 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenApache-2.0 | OpenApache 2.0 | Open |
| API model ID | — | — | — |
| API providers | 1 | 1 | 8 (best) |
| Released | Jun 30, 2025 | Dec 4, 2025 | Jun 20, 2025 |
| Knowledge cutoff | — | — | Oct 31, 2023 |
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
- Rnj-1 Instruct$1.80
Mistral Small 3.2 24B$1.33
Which should you choose?
Which is better: ERNIE 4.5 21B A3B, Rnj-1 Instruct or Mistral Small 3.2 24B?
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, Rnj-1 Instruct 52/100) 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, Rnj-1 Instruct or Mistral Small 3.2 24B?
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); Rnj-1 Instruct costs $0.15 input / $0.15 output per million tokens (median across 1 API provider). 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 $0.15 for Rnj-1 Instruct (1.2× 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, Rnj-1 Instruct has not been scored yet and Mistral Small 3.2 24B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for ERNIE 4.5 21B A3B, Rnj-1 Instruct and Mistral Small 3.2 24B 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?
Mistral Small 3.2 24B has the largest context window at 256,000 tokens, against 131,072 for ERNIE 4.5 21B A3B and 32,768 for Rnj-1 Instruct. Maximum output per response: ERNIE 4.5 21B A3B up to 8,000, Rnj-1 Instruct up to 32,768, Mistral Small 3.2 24B up to 16,384 tokens.
Which can read images, PDFs, audio or video?
ERNIE 4.5 21B A3B accepts text; Rnj-1 Instruct accepts text; Mistral Small 3.2 24B accepts text and images. 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 and Apache 2.0), so you can self-host them.
Which is newer?
Rnj-1 Instruct is the newest, released Dec 4, 2025. 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.
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.