Mistral Small 3.1 24B vs Nova Lite vs Llama-3.3-70B-Instruct
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 3.1 24B
54/100- ECI—
- Price$0.351 / $0.555
- Context128K
Amazon
Nova Lite
76/100- ECI—
- Price$0.06 / $0.24
- Context300K
Meta
Llama-3.3-70B-Instruct
42/100- ECI126.2
- Price$0.59 / $0.745
- Context128K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Nova Lite 76/100, Mistral Small 3.1 24B 54/100, Llama-3.3-70B-Instruct 42/100) 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 priceNova LiteNova Lite $0.105 · Mistral Small 3.1 24B $0.402 · Llama-3.3-70B-Instruct $0.629 per 1M tokens (3:1 blend)
- Longest contextNova LiteNova Lite 300,000 · Mistral Small 3.1 24B 128,000 · Llama-3.3-70B-Instruct 128,000 tokens
- Widest inputsNova LiteMistral Small 3.1 24B: Text, Images · Nova Lite: Text, Images, PDFs, Video · Llama-3.3-70B-Instruct: Text
- Self-hostingMistral Small 3.1 24B and Llama-3.3-70B-InstructPublishes downloadable weights
| Measure | Weight | Mistral Small 3.1 24B | Nova Lite | Llama-3.3-70B-Instruct |
|---|---|---|---|---|
| Price | 50% | 66 | 92 | 57 |
| Inputs & features | 30% | 50 | 70 | 25 |
| Context window | 20% | 32 | 45 | 32 |
| Specs & price only | 100% | 54/100 | 76/100 | 42/100 |
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) | — | — | 126.2 |
| ECI rank | — | — | #144 of 158 |
| GPQA DiamondGraduate-level science questions | 47.5% (best) | — | 47.4% |
| OTIS Mock AIME 2024–2025Competition mathematics | 5.8% (best) | — | 5.1% |
| Price per million tokens | |||
| Input | $0.351 | $0.06 (best) | $0.59 |
| Output | $0.555 | $0.24 (best) | $0.745 |
| Cached input | — | $0.015 | — |
| Blended (3:1) | $0.402 | $0.105 (best) | $0.629 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 9 providers | Official Amazon Bedrock API | Median of 40 providers |
| Limits | |||
| Context window | 128,000 tokens | 300,000 tokens (best) | 128,000 tokens |
| Max output | 16,384 tokens (best) | 10,000 tokens | 4,096 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | — | amazon.nova-lite-v1:0 | — |
| API providers | 9 | 8 | 43 (best) |
| Released | Mar 17, 2025 | Dec 3, 2024 | Dec 6, 2024 |
| Knowledge cutoff | Jun 2024 | Oct 2024 | Dec 2023 |
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 3.1 24B$4.62
Nova Lite$1.08
Llama-3.3-70B-Instruct$7.39
Which should you choose?
Which is better: Mistral Small 3.1 24B, Nova Lite or Llama-3.3-70B-Instruct?
There is not enough shared capability evidence to name an overall winner. The scores (Nova Lite 76/100, Mistral Small 3.1 24B 54/100, Llama-3.3-70B-Instruct 42/100) 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 3.1 24B, Nova Lite or Llama-3.3-70B-Instruct?
Nova Lite is cheaper at $0.06 input / $0.24 output per million tokens (official Amazon Bedrock API price). Mistral Small 3.1 24B costs $0.351 input / $0.555 output per million tokens (median across 9 API providers); Llama-3.3-70B-Instruct costs $0.59 input / $0.745 output per million tokens (median across 40 API providers). At a typical mix of three input tokens to one output token, that is $0.105 per million tokens for Nova Lite versus $0.402 for Mistral Small 3.1 24B (3.8× as much) and $0.629 for Llama-3.3-70B-Instruct (6× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Mistral Small 3.1 24B has not been scored yet, Nova Lite has not been scored yet and Llama-3.3-70B-Instruct has an ECI of 126.2.
Which is better for coding?
There are no published SWE-bench Verified results for Mistral Small 3.1 24B, Nova Lite and Llama-3.3-70B-Instruct 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 Lite has the largest context window at 300,000 tokens, against 128,000 for Mistral Small 3.1 24B and 128,000 for Llama-3.3-70B-Instruct. Maximum output per response: Mistral Small 3.1 24B up to 16,384, Nova Lite up to 10,000, Llama-3.3-70B-Instruct up to 4,096 tokens.
Which can read images, PDFs, audio or video?
Mistral Small 3.1 24B accepts text and images; Nova Lite accepts text, images, PDFs and video; Llama-3.3-70B-Instruct accepts text. Nova Lite handles the widest range of inputs.
Are any of these open source?
Mistral Small 3.1 24B and Llama-3.3-70B-Instruct publishes its weights and can be self-hosted; Nova Lite is proprietary.
Which is newer?
Mistral Small 3.1 24B is the newest, released Mar 17, 2025. Llama-3.3-70B-Instruct came out Dec 6, 2024; Nova Lite came out Dec 3, 2024. Knowledge cutoff: Mistral Small 3.1 24B Jun 2024, Nova Lite Oct 2024, Llama-3.3-70B-Instruct Dec 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.