Laguna S 2.1 vs Ling 3.0 Flash Fin vs MiniCPM5-2B
Laguna S 2.1 comes out ahead, 45 to 36 and 31 on our weighted score.
- Our pick
PoolsideLaguna S 2.1
45/100- ECI—
- Price$0.09 / $0.18
- Context1.05M
inclusionAILing 3.0 Flash Fin
36/100- ECI—
- Price$0.075 / $0.22
- Context262K
OpenBMB
MiniCPM5-2B
31/100- ECI—
- Price—
- Context131K
Laguna S 2.1 is our pick
Laguna S 2.1 is the better all-round choice, scoring 45/100 against Ling 3.0 Flash Fin (36) and MiniCPM5-2B (31). It leads on context window. The score weighs inputs & features 60%, context window 40%. 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 priceLing 3.0 Flash FinLing 3.0 Flash Fin $0.111 · Laguna S 2.1 $0.113 per 1M tokens (3:1 blend) · MiniCPM5-2B unpriced
- Longest contextLaguna S 2.1Laguna S 2.1 1,048,576 · Ling 3.0 Flash Fin 262,144 · MiniCPM5-2B 131,072 tokens
- Widest inputsSame inputsLaguna S 2.1: Text · Ling 3.0 Flash Fin: Text · MiniCPM5-2B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Laguna S 2.1 | Ling 3.0 Flash Fin | MiniCPM5-2B |
|---|---|---|---|---|
| Inputs & features | 60% | 35 | 35 | 35 |
| Context window | 40% | 61 | 37 | 25 |
| Overall | 100% | 45/100 | 36/100 | 31/100 |
Left out because at least one model lacks the data: capability and price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Laguna S 2.1Poolside | Ling 3.0 Flash FininclusionAI | MiniCPM5-2BOpenBMB |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.09 | $0.075 (best) | — |
| Output | $0.18 (best) | $0.22 | — |
| Cached input | — | — | — |
| Blended (3:1) | $0.113 | $0.111 (best) | — |
| Long-context rate | Same rate | Same rate | — |
| Price source | Median of 2 providers | Median of 2 providers | — |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 262,144 tokens | 131,072 tokens |
| Max output | 32,768 tokens | 32,768 tokens | 131,072 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 | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | OpenMIT | Openapache-2.0 |
| API model ID | poolside/laguna-s-2.1 | — | — |
| API providers | 4 (best) | 3 | 1 |
| Released | Jul 21, 2026 | Aug 27, 2026 | Sep 6, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Laguna S 2.1$1.26
- Ling 3.0 Flash Fin$1.19
- MiniCPM5-2B—
Which should you choose?
Which is better: Laguna S 2.1, Ling 3.0 Flash Fin or MiniCPM5-2B?
Laguna S 2.1 is the better all-round choice, scoring 45/100 against Ling 3.0 Flash Fin (36) and MiniCPM5-2B (31). It leads on context window. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Laguna S 2.1, Ling 3.0 Flash Fin or MiniCPM5-2B?
Ling 3.0 Flash Fin is cheaper at $0.075 input / $0.22 output per million tokens (median across 2 API providers). Laguna S 2.1 costs $0.09 input / $0.18 output per million tokens (median across 2 API providers; free on Poolside). At a typical mix of three input tokens to one output token, that is $0.111 per million tokens for Ling 3.0 Flash Fin versus $0.113 for Laguna S 2.1 (1× as much). MiniCPM5-2B has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Laguna S 2.1 has not been scored yet, Ling 3.0 Flash Fin has not been scored yet and MiniCPM5-2B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Laguna S 2.1, Ling 3.0 Flash Fin and MiniCPM5-2B 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 S 2.1 has the largest context window at 1,048,576 tokens, against 262,144 for Ling 3.0 Flash Fin and 131,072 for MiniCPM5-2B. Maximum output per response: Laguna S 2.1 up to 32,768, Ling 3.0 Flash Fin up to 32,768, MiniCPM5-2B up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Laguna S 2.1 accepts text; Ling 3.0 Flash Fin accepts text; MiniCPM5-2B accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights (MIT and apache-2.0), so you can self-host them.
Which is newer?
MiniCPM5-2B is the newest, released Sep 6, 2026. Ling 3.0 Flash Fin came out Aug 27, 2026; Laguna S 2.1 came out Jul 21, 2026.
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.
