Beam 1.0 501B A23B vs LightOnOCR-3 0.8B vs MiniCPM-V 4.7 1B
MiniCPM-V 4.7 1B comes out ahead, 57 to 45 and 30 on our weighted score.
Reflection AIBeam 1.0 501B A23B
45/100- ECI—
- Price$0.30 / $1.00
- Context1.05M
LightOn
LightOnOCR-3 0.8B
30/100- ECI—
- Price—
- Context262K
- Our pick
OpenBMB
MiniCPM-V 4.7 1B
57/100- ECI—
- Price—
- Context262K
MiniCPM-V 4.7 1B is our pick
MiniCPM-V 4.7 1B is the better all-round choice, scoring 57/100 against Beam 1.0 501B A23B (45) and LightOnOCR-3 0.8B (30). It leads on inputs & features. Beam 1.0 501B A23B 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 priceBeam 1.0 501B A23BBeam 1.0 501B A23B $0.475 per 1M tokens (3:1 blend) · LightOnOCR-3 0.8B and MiniCPM-V 4.7 1B unpriced
- Longest contextBeam 1.0 501B A23BBeam 1.0 501B A23B 1,048,576 · LightOnOCR-3 0.8B 262,144 · MiniCPM-V 4.7 1B 262,144 tokens
- Widest inputsMiniCPM-V 4.7 1BBeam 1.0 501B A23B: Text · LightOnOCR-3 0.8B: Text, Images · MiniCPM-V 4.7 1B: Text, Images, Video
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Beam 1.0 501B A23B | LightOnOCR-3 0.8B | MiniCPM-V 4.7 1B |
|---|---|---|---|---|
| Inputs & features | 60% | 35 | 25 | 70 |
| Context window | 40% | 61 | 37 | 37 |
| Overall | 100% | 45/100 | 30/100 | 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 | Beam 1.0 501B A23BReflection AI | LightOnOCR-3 0.8BLightOn | MiniCPM-V 4.7 1BOpenBMB |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 | — | — |
| Output | $1.00 | — | — |
| Cached input | — | — | — |
| Blended (3:1) | $0.475 | — | — |
| Long-context rate | Same rate | — | — |
| Price source | Median of 7 providers | — | — |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 262,144 tokens | 262,144 tokens |
| Max output | 131,072 tokens | 16,384 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | Yes | No | Yes |
| Tool calling | Yes | No | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenApache-2.0 | Openapache-2.0 | OpenApache-2.0 |
| API model ID | — | — | — |
| API providers | 12 (best) | 1 | 1 |
| Released | Oct 5, 2026 | Oct 8, 2026 | Oct 6, 2026 |
| Knowledge cutoff | Jun 30, 2026 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Beam 1.0 501B A23B$5.00
- LightOnOCR-3 0.8B—
- MiniCPM-V 4.7 1B—
Which should you choose?
Which is better: Beam 1.0 501B A23B, LightOnOCR-3 0.8B or MiniCPM-V 4.7 1B?
MiniCPM-V 4.7 1B is the better all-round choice, scoring 57/100 against Beam 1.0 501B A23B (45) and LightOnOCR-3 0.8B (30). It leads on inputs & features. Beam 1.0 501B A23B 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, Beam 1.0 501B A23B, LightOnOCR-3 0.8B or MiniCPM-V 4.7 1B?
Beam 1.0 501B A23B is cheaper at $0.30 input / $1.00 output per million tokens (median across 7 API providers). . At a typical mix of three input tokens to one output token, that is $0.475 per million tokens for Beam 1.0 501B A23B versus . LightOnOCR-3 0.8B and MiniCPM-V 4.7 1B has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Beam 1.0 501B A23B has not been scored yet, LightOnOCR-3 0.8B has not been scored yet and MiniCPM-V 4.7 1B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Beam 1.0 501B A23B, LightOnOCR-3 0.8B and MiniCPM-V 4.7 1B 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?
Beam 1.0 501B A23B 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 1B. Maximum output per response: Beam 1.0 501B A23B up to 131,072, LightOnOCR-3 0.8B up to 16,384, MiniCPM-V 4.7 1B up to 262,144 tokens.
Which can read images, PDFs, audio or video?
Beam 1.0 501B A23B accepts text; LightOnOCR-3 0.8B accepts text and images; MiniCPM-V 4.7 1B accepts text, images and video. MiniCPM-V 4.7 1B 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 1B came out Oct 6, 2026; Beam 1.0 501B A23B came out Oct 5, 2026. Knowledge cutoff: Beam 1.0 501B A23B Jun 30, 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.
