Nova Pro vs North Mini Code vs Qwen2.5 32B Instruct
North Mini Code comes out ahead, 71 to 50 and 35 on our weighted score, and it is the cheaper option too.
AmazonNova Pro
50/100- ECI123.8
- Price$0.80 / $3.20
- Context300K
- Our pick
CohereNorth Mini Code
71/100- ECI—
- PriceFree / Free
- Context256K
Alibaba (Qwen)Qwen2.5 32B Instruct
35/100- ECI128.5
- Price$0.70 / $2.80
- Context131K
North Mini Code is our pick
North Mini Code is the better all-round choice, scoring 71/100 against Nova Pro (50) and Qwen2.5 32B Instruct (35). It leads on price. Nova Pro wins on inputs & features and context window. 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 priceNorth Mini CodeNorth Mini Code Free · Qwen2.5 32B Instruct $1.23 · Nova Pro $1.40 per 1M tokens (3:1 blend)
- Longest contextNova ProNova Pro 300,000 · North Mini Code 256,000 · Qwen2.5 32B Instruct 131,072 tokens
- Widest inputsNova ProNova Pro: Text, Images, PDFs, Video · North Mini Code: Text · Qwen2.5 32B Instruct: Text
- Self-hostingNorth Mini Code and Qwen2.5 32B InstructPublishes downloadable weights
| Measure | Weight | Nova Pro | North Mini Code | Qwen2.5 32B Instruct |
|---|---|---|---|---|
| Price | 50% | 43 | 100 | 46 |
| Inputs & features | 30% | 70 | 45 | 25 |
| Context window | 20% | 39 | 36 | 24 |
| Overall | 100% | 50/100 | 71/100 | 35/100 |
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 | Nova ProAmazon | North Mini CodeCohere | Qwen2.5 32B InstructAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 123.8 | — | 128.5 (best) |
| ECI rank | #137 of 148 | — | #131 of 148 (best) |
| GPQA DiamondGraduate-level science questions | — | — | 46.1% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | — | 7.4% |
| Price per million tokens | |||
| Input | $0.80 | Free (best) | $0.70 |
| Output | $3.20 | Free (best) | $2.80 |
| Cached input | $0.20 | — | — |
| Blended (3:1) | $1.40 | Free (best) | $1.23 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Amazon Bedrock API | Official Cohere API | Official Alibaba API |
| Limits | |||
| Context window | 300,000 tokens (best) | 256,000 tokens | 131,072 tokens |
| Max output | 10,000 tokens | 64,000 tokens (best) | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | Yes | No | No |
| Audio | No | No | No |
| Video | Yes | No | No |
| Reasoning | No | Yeshigh | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | amazon.nova-pro-v1:0 | north-mini-code-1-0 | qwen2-5-32b-instruct |
| API providers | 3 (best) | 2 | 1 |
| Released | Dec 3, 2024 | Jun 9, 2026 | Sep 17, 2024 |
| Knowledge cutoff | Oct 2024 | Sep 23, 2025 | Apr 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Nova Pro$14.40
- North Mini CodeFree
- Qwen2.5 32B Instruct$12.60
Which should you choose?
Which is better: Nova Pro, North Mini Code or Qwen2.5 32B Instruct?
North Mini Code is the better all-round choice, scoring 71/100 against Nova Pro (50) and Qwen2.5 32B Instruct (35). It leads on price. Nova Pro wins on inputs & features and context window. 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, Nova Pro, North Mini Code or Qwen2.5 32B Instruct?
North Mini Code is cheaper at Free input / Free output per million tokens (official Cohere API price). Qwen2.5 32B Instruct costs $0.70 input / $2.80 output per million tokens (official Alibaba API price); Nova Pro costs $0.80 input / $3.20 output per million tokens (official Amazon Bedrock API price). North Mini Code is listed as free.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Nova Pro has an ECI of 123.8, North Mini Code has not been scored yet and Qwen2.5 32B Instruct has an ECI of 128.5.
Which is better for coding?
There are no published SWE-bench Verified results for Nova Pro, North Mini Code and Qwen2.5 32B 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 Pro has the largest context window at 300,000 tokens, against 256,000 for North Mini Code and 131,072 for Qwen2.5 32B Instruct. Maximum output per response: Nova Pro up to 10,000, North Mini Code up to 64,000, Qwen2.5 32B Instruct up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Nova Pro accepts text, images, PDFs and video; North Mini Code accepts text; Qwen2.5 32B Instruct accepts text. Nova Pro handles the widest range of inputs.
Are any of these open source?
North Mini Code and Qwen2.5 32B Instruct publishes its weights and can be self-hosted; Nova Pro is proprietary.
Which is newer?
North Mini Code is the newest, released Jun 9, 2026. Nova Pro came out Dec 3, 2024; Qwen2.5 32B Instruct came out Sep 17, 2024. Knowledge cutoff: Nova Pro Oct 2024, North Mini Code Sep 23, 2025, Qwen2.5 32B Instruct Apr 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 Oct 4, 2026.
