Laguna M.1 vs Qwen2.5 72B Instruct vs North Mini Code
Too close to call on our weighted score (North Mini Code 71, Laguna M.1 68, Qwen2.5 72B Instruct 28). The right pick depends on what you value most.
PoolsideLaguna M.1
68/100- ECI—
- PriceFree / Free
- Context262K
Alibaba (Qwen)Qwen2.5 72B Instruct
28/100- ECI129.0
- Price$1.40 / $5.60
- Context131K
CohereNorth Mini Code
71/100- ECI—
- PriceFree / Free
- Context256K
Too close to call
It is close. Our weighted score puts them within 3 points (North Mini Code 71/100, Laguna M.1 68/100, Qwen2.5 72B Instruct 28/100), so choose by what matters most for your work: Laguna M.1 on price and Laguna M.1 for long inputs. 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 priceLaguna M.1 and North Mini CodeLaguna M.1 Free · North Mini Code Free · Qwen2.5 72B Instruct $2.45 per 1M tokens (3:1 blend)
- Longest contextLaguna M.1Laguna M.1 262,144 · North Mini Code 256,000 · Qwen2.5 72B Instruct 131,072 tokens
- Widest inputsSame inputsLaguna M.1: Text · Qwen2.5 72B Instruct: Text · North Mini Code: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Laguna M.1 | Qwen2.5 72B Instruct | North Mini Code |
|---|---|---|---|---|
| Price | 50% | 100 | 31 | 100 |
| Inputs & features | 30% | 35 | 25 | 45 |
| Context window | 20% | 37 | 24 | 36 |
| Overall | 100% | 68/100 | 28/100 | 71/100 |
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 | Laguna M.1Poolside | Qwen2.5 72B InstructAlibaba (Qwen) | North Mini CodeCohere |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 129.0 | — |
| ECI rank | — | #128 of 148 | — |
| GPQA DiamondGraduate-level science questions | — | 49.2% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 8.1% | — |
| Price per million tokens | |||
| Input | Free (best) | $1.40 | Free (best) |
| Output | Free (best) | $5.60 | Free (best) |
| Cached input | — | — | — |
| Blended (3:1) | Free (best) | $2.45 | Free (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Poolside API | Official Alibaba API | Official Cohere API |
| Limits | |||
| Context window | 262,144 tokens (best) | 131,072 tokens | 256,000 tokens |
| Max output | 32,768 tokens | 8,192 tokens | 64,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | Yeshigh |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | poolside/laguna-m.1 | qwen2-5-72b-instruct | north-mini-code-1-0 |
| API providers | 2 (best) | 1 | 2 (best) |
| Released | Apr 28, 2026 | Sep 19, 2024 | Jun 9, 2026 |
| Knowledge cutoff | — | Apr 2024 | Sep 23, 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Laguna M.1Free
- Qwen2.5 72B Instruct$25.20
- North Mini CodeFree
Which should you choose?
Which is better: Laguna M.1, Qwen2.5 72B Instruct or North Mini Code?
It is close. Our weighted score puts them within 3 points (North Mini Code 71/100, Laguna M.1 68/100, Qwen2.5 72B Instruct 28/100), so choose by what matters most for your work: Laguna M.1 on price and Laguna M.1 for long inputs. 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, Laguna M.1, Qwen2.5 72B Instruct or North Mini Code?
Laguna M.1 is cheaper at Free input / Free output per million tokens (official Poolside API price). North Mini Code costs Free input / Free output per million tokens (official Cohere API price); Qwen2.5 72B Instruct costs $1.40 input / $5.60 output per million tokens (official Alibaba API price). Laguna M.1 is listed as free.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Laguna M.1 has not been scored yet, Qwen2.5 72B Instruct has an ECI of 129.0 and North Mini Code has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Laguna M.1, Qwen2.5 72B Instruct and North Mini Code 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?
Laguna M.1 has the largest context window at 262,144 tokens, against 256,000 for North Mini Code and 131,072 for Qwen2.5 72B Instruct. Maximum output per response: Laguna M.1 up to 32,768, Qwen2.5 72B Instruct up to 8,192, North Mini Code up to 64,000 tokens.
Which can read images, PDFs, audio or video?
Laguna M.1 accepts text; Qwen2.5 72B Instruct accepts text; North Mini Code accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
North Mini Code is the newest, released Jun 9, 2026. Laguna M.1 came out Apr 28, 2026; Qwen2.5 72B Instruct came out Sep 19, 2024. Knowledge cutoff: Qwen2.5 72B Instruct Apr 2024, North Mini Code Sep 23, 2025.
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.
