LightOnOCR-3 0.8B vs MiniCPM-V 4.7 35B-A3B vs Nemotron 3.5 Super 120B A12B
MiniCPM-V 4.7 35B-A3B comes out ahead, 57 to 45 and 30 on our weighted score.
LightOn
LightOnOCR-3 0.8B
30/100- ECI—
- Price—
- Context262K
- Our pick
OpenBMB
MiniCPM-V 4.7 35B-A3B
57/100- ECI—
- Price—
- Context262K
NVIDIANemotron 3.5 Super 120B A12B
45/100- ECI—
- Price$0.20 / $0.50
- Context1.05M
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 Nemotron 3.5 Super 120B A12B (45) and LightOnOCR-3 0.8B (30). It leads on inputs & features. Nemotron 3.5 Super 120B A12B wins 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 priceNemotron 3.5 Super 120B A12BNemotron 3.5 Super 120B A12B $0.275 per 1M tokens (3:1 blend) · LightOnOCR-3 0.8B and MiniCPM-V 4.7 35B-A3B unpriced
- Longest contextNemotron 3.5 Super 120B A12BNemotron 3.5 Super 120B A12B 1,048,576 · LightOnOCR-3 0.8B 262,144 · MiniCPM-V 4.7 35B-A3B 262,144 tokens
- Widest inputsMiniCPM-V 4.7 35B-A3BLightOnOCR-3 0.8B: Text, Images · MiniCPM-V 4.7 35B-A3B: Text, Images, Video · Nemotron 3.5 Super 120B A12B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | LightOnOCR-3 0.8B | MiniCPM-V 4.7 35B-A3B | Nemotron 3.5 Super 120B A12B |
|---|---|---|---|---|
| Inputs & features | 60% | 25 | 70 | 35 |
| Context window | 40% | 37 | 37 | 61 |
| Overall | 100% | 30/100 | 57/100 | 45/100 |
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 | MiniCPM-V 4.7 35B-A3BOpenBMB | Nemotron 3.5 Super 120B A12BNVIDIA |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | — | — | $0.20 |
| Output | — | — | $0.50 |
| Cached input | — | — | — |
| Blended (3:1) | — | — | $0.275 |
| Long-context rate | — | — | Same rate |
| Price source | — | — | Median of 1 providers |
| Limits | |||
| Context window | 262,144 tokens | 262,144 tokens | 1,048,576 tokens (best) |
| Max output | 16,384 tokens | 262,144 tokens (best) | 131,072 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | No | Yes | Yes |
| Tool calling | No | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Openapache-2.0 | OpenApache-2.0 | Open |
| API model ID | — | — | — |
| API providers | 1 | 1 | 1 |
| Released | Oct 8, 2026 | Oct 7, 2026 | Oct 15, 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—
- MiniCPM-V 4.7 35B-A3B—
- Nemotron 3.5 Super 120B A12B$3.00
Which should you choose?
Which is better: LightOnOCR-3 0.8B, MiniCPM-V 4.7 35B-A3B or Nemotron 3.5 Super 120B A12B?
MiniCPM-V 4.7 35B-A3B is the better all-round choice, scoring 57/100 against Nemotron 3.5 Super 120B A12B (45) and LightOnOCR-3 0.8B (30). It leads on inputs & features. Nemotron 3.5 Super 120B A12B wins 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, LightOnOCR-3 0.8B, MiniCPM-V 4.7 35B-A3B or Nemotron 3.5 Super 120B A12B?
Nemotron 3.5 Super 120B A12B is cheaper at $0.20 input / $0.50 output per million tokens (median across 1 API provider). . At a typical mix of three input tokens to one output token, that is $0.275 per million tokens for Nemotron 3.5 Super 120B A12B versus . LightOnOCR-3 0.8B and MiniCPM-V 4.7 35B-A3B has no 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, MiniCPM-V 4.7 35B-A3B has not been scored yet and Nemotron 3.5 Super 120B A12B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for LightOnOCR-3 0.8B, MiniCPM-V 4.7 35B-A3B and Nemotron 3.5 Super 120B A12B 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?
Nemotron 3.5 Super 120B A12B 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, Nemotron 3.5 Super 120B A12B up to 131,072 tokens.
Which can read images, PDFs, audio or video?
LightOnOCR-3 0.8B accepts text and images; MiniCPM-V 4.7 35B-A3B accepts text, images and video; Nemotron 3.5 Super 120B A12B accepts text. 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?
Nemotron 3.5 Super 120B A12B is the newest, released Oct 15, 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.
