Llama 3.3 Nemotron Super 49B v1 vs Mistral Small 3.2 24B vs Phi-4-mini
Mistral Small 3.2 24B comes out ahead, 65 to 58 and 56 on our weighted score, though Phi-4-mini is 13% cheaper per token.
NVIDIALlama 3.3 Nemotron Super 49B v1
58/100- ECI—
- Price$0.15 / $0.15
- Context131K
- Our pick
Mistral AIMistral Small 3.2 24B
65/100- ECI—
- Price$0.10 / $0.305
- Context256K
MicrosoftPhi-4-mini
56/100- ECI—
- Price$0.075 / $0.30
- Context128K
Mistral Small 3.2 24B is our pick
Mistral Small 3.2 24B is the better all-round choice, scoring 65/100 against Llama 3.3 Nemotron Super 49B v1 (58) and Phi-4-mini (56). It leads on inputs & features and context window. Phi-4-mini wins on 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 pricePhi-4-miniPhi-4-mini $0.131 · Llama 3.3 Nemotron Super 49B v1 $0.15 · Mistral Small 3.2 24B $0.151 per 1M tokens (3:1 blend)
- Longest contextMistral Small 3.2 24BMistral Small 3.2 24B 256,000 · Llama 3.3 Nemotron Super 49B v1 131,072 · Phi-4-mini 128,000 tokens
- Widest inputsMistral Small 3.2 24BLlama 3.3 Nemotron Super 49B v1: Text · Mistral Small 3.2 24B: Text, Images · Phi-4-mini: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Llama 3.3 Nemotron Super 49B v1 | Mistral Small 3.2 24B | Phi-4-mini |
|---|---|---|---|---|
| Price | 50% | 85 | 85 | 88 |
| Inputs & features | 30% | 35 | 50 | 25 |
| Context window | 20% | 25 | 36 | 24 |
| Overall | 100% | 58/100 | 65/100 | 56/100 |
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 | Llama 3.3 Nemotron Super 49B v1NVIDIA | Mistral Small 3.2 24BMistral AI | Phi-4-miniMicrosoft |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.15 | $0.10 | $0.075 (best) |
| Output | $0.15 (best) | $0.305 | $0.30 |
| Cached input | — | — | — |
| Blended (3:1) | $0.15 | $0.151 | $0.131 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 8 providers | Official Azure API |
| Limits | |||
| Context window | 131,072 tokens | 256,000 tokens (best) | 128,000 tokens |
| Max output | 131,072 tokens (best) | 16,384 tokens | 4,096 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | — | — | phi-4-mini |
| API providers | 1 | 8 (best) | 2 |
| Released | Mar 18, 2025 | Jun 20, 2025 | Feb 26, 2025 |
| Knowledge cutoff | — | Oct 31, 2023 | Jun 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Llama 3.3 Nemotron Super 49B v1$1.80
- Mistral Small 3.2 24B$1.61
- Phi-4-mini$1.35
Which should you choose?
Which is better: Llama 3.3 Nemotron Super 49B v1, Mistral Small 3.2 24B or Phi-4-mini?
Mistral Small 3.2 24B is the better all-round choice, scoring 65/100 against Llama 3.3 Nemotron Super 49B v1 (58) and Phi-4-mini (56). It leads on inputs & features and context window. Phi-4-mini wins on 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, Llama 3.3 Nemotron Super 49B v1, Mistral Small 3.2 24B or Phi-4-mini?
Phi-4-mini is cheaper at $0.075 input / $0.30 output per million tokens (official Azure API price). Llama 3.3 Nemotron Super 49B v1 costs $0.15 input / $0.15 output per million tokens (median across 1 API provider); Mistral Small 3.2 24B costs $0.10 input / $0.305 output per million tokens (median across 8 API providers). At a typical mix of three input tokens to one output token, that is $0.131 per million tokens for Phi-4-mini versus $0.15 for Llama 3.3 Nemotron Super 49B v1 (1.1× as much) and $0.151 for Mistral Small 3.2 24B (1.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Llama 3.3 Nemotron Super 49B v1 has not been scored yet, Mistral Small 3.2 24B has not been scored yet and Phi-4-mini has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Llama 3.3 Nemotron Super 49B v1, Mistral Small 3.2 24B and Phi-4-mini 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 Llama 3.3 Nemotron Super 49B v1 and 128,000 for Phi-4-mini. Maximum output per response: Llama 3.3 Nemotron Super 49B v1 up to 131,072, Mistral Small 3.2 24B up to 16,384, Phi-4-mini up to 4,096 tokens.
Which can read images, PDFs, audio or video?
Llama 3.3 Nemotron Super 49B v1 accepts text; Mistral Small 3.2 24B accepts text and images; Phi-4-mini 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, so you can self-host them.
Which is newer?
Mistral Small 3.2 24B is the newest, released Jun 20, 2025. Llama 3.3 Nemotron Super 49B v1 came out Mar 18, 2025; Phi-4-mini came out Feb 26, 2025. Knowledge cutoff: Mistral Small 3.2 24B Oct 31, 2023, Phi-4-mini Jun 2024.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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 2, 2026.
