LightOnOCR-3 0.8B vs Muse Wonder Full vs MiniCPM-V 4.7 35B-A3B
Muse Wonder Full comes out ahead, 72 to 57 and 30 on our weighted score.
LightOn
LightOnOCR-3 0.8B
30/100- ECI—
- Price—
- Context262K
- Our pick
MetaMuse Wonder Full
72/100- ECI—
- Price—
- Context1.05M
OpenBMB
MiniCPM-V 4.7 35B-A3B
57/100- ECI—
- Price—
- Context262K
Muse Wonder Full is our pick
Muse Wonder Full is the better all-round choice, scoring 72/100 against MiniCPM-V 4.7 35B-A3B (57) and LightOnOCR-3 0.8B (30). It leads on inputs & features and 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
- Longest contextMuse Wonder FullMuse Wonder Full 1,048,576 · LightOnOCR-3 0.8B 262,144 · MiniCPM-V 4.7 35B-A3B 262,144 tokens
- Widest inputsMuse Wonder FullLightOnOCR-3 0.8B: Text, Images · Muse Wonder Full: Text, Images, Audio, Video · MiniCPM-V 4.7 35B-A3B: Text, Images, Video
- Self-hostingLightOnOCR-3 0.8B and MiniCPM-V 4.7 35B-A3BPublishes downloadable weights (apache-2.0 and Apache-2.0)
| Measure | Weight | LightOnOCR-3 0.8B | Muse Wonder Full | MiniCPM-V 4.7 35B-A3B |
|---|---|---|---|---|
| Inputs & features | 60% | 25 | 80 | 70 |
| Context window | 40% | 37 | 61 | 37 |
| Overall | 100% | 30/100 | 72/100 | 57/100 |
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 | LightOnOCR-3 0.8BLightOn | Muse Wonder FullMeta | MiniCPM-V 4.7 35B-A3BOpenBMB |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | — | — | — |
| Output | — | — | — |
| Cached input | — | — | — |
| Blended (3:1) | — | — | — |
| Long-context rate | — | — | — |
| Price source | — | — | — |
| Limits | |||
| Context window | 262,144 tokens | 1,048,576 tokens (best) | 262,144 tokens |
| Max output | 16,384 tokens | — | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | Yes | No |
| Video | No | Yes | Yes |
| Reasoning | No | Yes | Yes |
| Tool calling | No | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Openapache-2.0 | Proprietary | OpenApache-2.0 |
| API model ID | — | — | — |
| API providers | 1 | — | 1 |
| Released | Oct 8, 2026 | Oct 12, 2026 | Oct 7, 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.
- LightOnOCR-3 0.8B—
- Muse Wonder Full—
- MiniCPM-V 4.7 35B-A3B—
Which should you choose?
Which is better: LightOnOCR-3 0.8B, Muse Wonder Full or MiniCPM-V 4.7 35B-A3B?
Muse Wonder Full is the better all-round choice, scoring 72/100 against MiniCPM-V 4.7 35B-A3B (57) and LightOnOCR-3 0.8B (30). It leads on inputs & features and 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, LightOnOCR-3 0.8B, Muse Wonder Full or MiniCPM-V 4.7 35B-A3B?
None of these models has a published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. LightOnOCR-3 0.8B has not been scored yet, Muse Wonder Full has not been scored yet and MiniCPM-V 4.7 35B-A3B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for LightOnOCR-3 0.8B, Muse Wonder Full and MiniCPM-V 4.7 35B-A3B 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?
Muse Wonder Full has the largest context window at 1,048,576 tokens, against 262,144 for LightOnOCR-3 0.8B and 262,144 for MiniCPM-V 4.7 35B-A3B. Maximum output per response: LightOnOCR-3 0.8B up to 16,384, MiniCPM-V 4.7 35B-A3B up to 262,144 tokens.
Which can read images, PDFs, audio or video?
LightOnOCR-3 0.8B accepts text and images; Muse Wonder Full accepts text, images, audio and video; MiniCPM-V 4.7 35B-A3B accepts text, images and video. Muse Wonder Full handles the widest range of inputs.
Are any of these open source?
LightOnOCR-3 0.8B and MiniCPM-V 4.7 35B-A3B publishes its weights (apache-2.0 and Apache-2.0) and can be self-hosted; Muse Wonder Full is proprietary.
Which is newer?
Muse Wonder Full is the newest, released Oct 12, 2026. LightOnOCR-3 0.8B came out Oct 8, 2026; MiniCPM-V 4.7 35B-A3B came out Oct 7, 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.
