MiniCPM-V 4.7 35B-A3B vs Ling 3.1 Flash vs LightOnOCR-3 0.8B
MiniCPM-V 4.7 35B-A3B comes out ahead, 57 to 36 and 30 on our weighted score.
- Our pick
OpenBMB
MiniCPM-V 4.7 35B-A3B
57/100- ECI—
- Price—
- Context262K
inclusionAILing 3.1 Flash
36/100- ECI—
- Price$0.30 / $0.90
- Context262K
LightOn
LightOnOCR-3 0.8B
30/100- ECI—
- Price—
- Context262K
MiniCPM-V 4.7 35B-A3B is our pick
MiniCPM-V 4.7 35B-A3B is the better all-round choice, scoring 57/100 against Ling 3.1 Flash (36) and LightOnOCR-3 0.8B (30). It leads on inputs & features. 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 3.1 FlashLing 3.1 Flash $0.45 per 1M tokens (3:1 blend) · MiniCPM-V 4.7 35B-A3B and LightOnOCR-3 0.8B unpriced
- Longest contextAbout the sameMiniCPM-V 4.7 35B-A3B 262,144 · Ling 3.1 Flash 262,144 · LightOnOCR-3 0.8B 262,144 tokens
- Widest inputsMiniCPM-V 4.7 35B-A3BMiniCPM-V 4.7 35B-A3B: Text, Images, Video · Ling 3.1 Flash: Text · LightOnOCR-3 0.8B: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | MiniCPM-V 4.7 35B-A3B | Ling 3.1 Flash | LightOnOCR-3 0.8B |
|---|---|---|---|---|
| Inputs & features | 60% | 70 | 35 | 25 |
| Context window | 40% | 37 | 37 | 37 |
| Overall | 100% | 57/100 | 36/100 | 30/100 |
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 | MiniCPM-V 4.7 35B-A3BOpenBMB | Ling 3.1 FlashinclusionAI | LightOnOCR-3 0.8BLightOn |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | — | $0.30 | — |
| Output | — | $0.90 | — |
| Cached input | — | — | — |
| Blended (3:1) | — | $0.45 | — |
| Long-context rate | — | Same rate | — |
| Price source | — | Median of 5 providers | — |
| Limits | |||
| Context window | 262,144 tokens | 262,144 tokens | 262,144 tokens |
| Max output | 262,144 tokens (best) | 32,768 tokens | 16,384 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | Yes | No | No |
| Reasoning | Yes | Yes | No |
| Tool calling | Yes | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenApache-2.0 | Open | Openapache-2.0 |
| API model ID | — | — | — |
| API providers | 1 | 7 (best) | 1 |
| Released | Oct 7, 2026 | Sep 29, 2026 | Oct 8, 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.
- MiniCPM-V 4.7 35B-A3B—
- Ling 3.1 Flash$4.80
- LightOnOCR-3 0.8B—
Which should you choose?
Which is better: MiniCPM-V 4.7 35B-A3B, Ling 3.1 Flash or LightOnOCR-3 0.8B?
MiniCPM-V 4.7 35B-A3B is the better all-round choice, scoring 57/100 against Ling 3.1 Flash (36) and LightOnOCR-3 0.8B (30). It leads on inputs & features. 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, MiniCPM-V 4.7 35B-A3B, Ling 3.1 Flash or LightOnOCR-3 0.8B?
Ling 3.1 Flash is cheaper at $0.30 input / $0.90 output per million tokens (median across 5 API providers). . At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Ling 3.1 Flash versus . MiniCPM-V 4.7 35B-A3B and LightOnOCR-3 0.8B has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MiniCPM-V 4.7 35B-A3B has not been scored yet, Ling 3.1 Flash has not been scored yet and LightOnOCR-3 0.8B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MiniCPM-V 4.7 35B-A3B, Ling 3.1 Flash and LightOnOCR-3 0.8B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that LightOnOCR-3 0.8B does not support tool calling, which most coding agents need.
Which has the bigger context window?
MiniCPM-V 4.7 35B-A3B, Ling 3.1 Flash and LightOnOCR-3 0.8B share the same 262,144-token context window. Maximum output per response: MiniCPM-V 4.7 35B-A3B up to 262,144, Ling 3.1 Flash up to 32,768, LightOnOCR-3 0.8B up to 16,384 tokens.
Which can read images, PDFs, audio or video?
MiniCPM-V 4.7 35B-A3B accepts text, images and video; Ling 3.1 Flash accepts text; LightOnOCR-3 0.8B accepts text and images. MiniCPM-V 4.7 35B-A3B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache-2.0 and apache-2.0), so you can self-host them.
Which is newer?
LightOnOCR-3 0.8B is the newest, released Oct 8, 2026. MiniCPM-V 4.7 35B-A3B came out Oct 7, 2026; Ling 3.1 Flash came out Sep 29, 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.
