Hardest reasoning tasks
Choose Qwen3.7-Plus
Qwen3.7-Plus scores 25.2 on the Artificial Analysis Intelligence Index, against 9.9 for North Mini Code.
North Mini Code vs Qwen3.7-Plus: price, context and capabilities
Choose North Mini Code for the latest release. Choose Qwen3.7-Plus for the hardest reasoning tasks, agentic coding, tool use and support agents, reasoning over long documents and images as input.
In short
- A price comparison is not possible: one of them has no comparable published price.
- Only Qwen3.7-Plus offers vision, reasoning.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Agentic coding
Choose Qwen3.7-Plus
Qwen3.7-Plus scores 47% on Terminal-Bench Hard, against 31.1% for North Mini Code.
Tool use and support agents
Choose Qwen3.7-Plus
Qwen3.7-Plus scores 93% on τ²-Bench (agentic tool use), against 37.4% for North Mini Code.
Reasoning over long documents
Choose Qwen3.7-Plus
Qwen3.7-Plus scores 73% on Long-context reasoning (AA-LCR), against 37.3% for North Mini Code.
Images as input
Choose Qwen3.7-Plus
Qwen3.7-Plus accepts images as input; North Mini Code does not.
Latest release
Choose North Mini Code
North Mini Code is the newer release (Jun 9, 2026, against Jun 1, 2026 for Qwen3.7-Plus).
Specifications side by side
| North Mini Code | Qwen3.7-Plus | |
|---|---|---|
| Provider | Cohere | Alibaba Cloud (Qwen) |
| Category | Language models | Language models |
| Status | Generally available | Generally available |
| Headline price | No data | No data |
| Input | No data | No data |
| Output | No data | No data |
| Cached input | No data | No data |
| Context window | 256k | No data |
| Max output | 64k | No data |
| Released | Jun 9, 2026 | Jun 1, 2026 |
| Knowledge cutoff | No data | No data |
| Licence | Proprietary | Proprietary |
| Capabilities | Tool calling | Vision, Reasoning, Tool calling |
| API model id | north-mini-code-1-0 | qwen3.7-plus |
Benchmarks side by side
Leader in bold.
| Benchmark | North Mini Code | Qwen3.7-Plus |
|---|---|---|
| Intelligence Index | 9.9 | 25.2 |
| Terminal-Bench Hard | 31.1% | 47% |
| SciCode | 38.8% | 46.1% |
| GPQA Diamond | 75.7% | 90% |
| Humanity's Last Exam | 11.1% | 35.6% |
| IFBench (instruction following) | 57.6% | 78% |
| τ²-Bench (agentic tool use) | 37.4% | 93% |
| Long-context reasoning (AA-LCR) | 37.3% | 73% |
| MMMU-Pro (visual reasoning) | No data | 80.5% |
Independent evaluations by Artificial Analysis, run the same way for every model, at the reasoning setting shown. Percentages unless marked as an index.
Frequently asked questions
Should I choose North Mini Code or Qwen3.7-Plus?
Choose North Mini Code for the latest release. Choose Qwen3.7-Plus for the hardest reasoning tasks, agentic coding, tool use and support agents, reasoning over long documents and images as input.
Which is cheaper, North Mini Code or Qwen3.7-Plus?
A price comparison is not possible: one of them has no comparable published price.
What is the difference between North Mini Code and Qwen3.7-Plus?
North Mini Code is made by Cohere and Qwen3.7-Plus by Alibaba Cloud (Qwen). A price comparison is not possible: one of them has no comparable published price. Only Qwen3.7-Plus offers vision, reasoning.
Which is better for coding, North Mini Code or Qwen3.7-Plus?
Qwen3.7-Plus scores 47% on Terminal-Bench Hard, against 31.1% for North Mini Code.
Which is newer, North Mini Code or Qwen3.7-Plus?
North Mini Code was released on Jun 9, 2026 and Qwen3.7-Plus on Jun 1, 2026.