Granite-4.0-H-Micro vs MinerU2.5 2509 1.2B vs Qwen3.5 2B
No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.
Price in rating: Excluded · Include price
IBM
Granite-4.0-H-Micro
28/100- ECI—
- Price$0.017 / $0.112
- Context131K
Opendatalab
MinerU2.5 2509 1.2B
15/100- ECI—
- Price$0.024 / $0.071
- Context16K
Alibaba (Qwen)
Qwen3.5 2B
59/100- ECI—
- Price$0.02 / $0.10
- Context262K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.5 2B 59/100, Granite-4.0-H-Micro 28/100, MinerU2.5 2509 1.2B 15/100) compare the available specifications only. 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 priceMinerU2.5 2509 1.2BMinerU2.5 2509 1.2B $0.036 · Qwen3.5 2B $0.04 · Granite-4.0-H-Micro $0.041 per 1M tokens (3:1 blend)
- Longest contextQwen3.5 2BQwen3.5 2B 262,144 · Granite-4.0-H-Micro 131,072 · MinerU2.5 2509 1.2B 16,384 tokens
- Widest inputsQwen3.5 2BGranite-4.0-H-Micro: Text · MinerU2.5 2509 1.2B: Text, Images · Qwen3.5 2B: Text, Images, Video
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Granite-4.0-H-Micro | MinerU2.5 2509 1.2B | Qwen3.5 2B |
|---|---|---|---|---|
| Inputs & features | 60% | 25 | 25 | 70 |
| Context window | 40% | 32 | 0 | 43 |
| Specs only | 100% | 28/100 | 15/100 | 59/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | MinerU2.5 2509 1.2BOpendatalab | ||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.017 (best) | $0.024 | $0.02 |
| Output | $0.112 | $0.071 (best) | $0.10 |
| Cached input | — | — | — |
| Blended (3:1) | $0.041 | $0.036 (best) | $0.04 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 1 providers | Median of 1 providers |
| Limits | |||
| Context window | 131,072 tokens | 16,384 tokens | 262,144 tokens (best) |
| Max output | 131,072 tokens (best) | — | 81,920 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | No | No | Yes |
| Tool calling | Yes | No | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | OpenAGPL-3.0 | OpenApache-2.0 |
| API model ID | — | — | — |
| API providers | 1 | 1 | 2 (best) |
| Released | Oct 2, 2025 | Sep 17, 2025 | Mar 2, 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.
Granite-4.0-H-Micro$0.394
- MinerU2.5 2509 1.2B$0.381
Qwen3.5 2B$0.40
Which should you choose?
Which is better: Granite-4.0-H-Micro, MinerU2.5 2509 1.2B or Qwen3.5 2B?
There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.5 2B 59/100, Granite-4.0-H-Micro 28/100, MinerU2.5 2509 1.2B 15/100) compare the available specifications only. 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, Granite-4.0-H-Micro, MinerU2.5 2509 1.2B or Qwen3.5 2B?
MinerU2.5 2509 1.2B is cheaper at $0.024 input / $0.071 output per million tokens (median across 1 API provider). Qwen3.5 2B costs $0.02 input / $0.10 output per million tokens (median across 1 API provider); Granite-4.0-H-Micro costs $0.017 input / $0.112 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.036 per million tokens for MinerU2.5 2509 1.2B versus $0.04 for Qwen3.5 2B (1.1× as much) and $0.041 for Granite-4.0-H-Micro (1.1× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Granite-4.0-H-Micro has not been scored yet, MinerU2.5 2509 1.2B has not been scored yet and Qwen3.5 2B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Granite-4.0-H-Micro, MinerU2.5 2509 1.2B and Qwen3.5 2B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that MinerU2.5 2509 1.2B does not support tool calling, which most coding agents need.
Which has the bigger context window?
Qwen3.5 2B has the largest context window at 262,144 tokens, against 131,072 for Granite-4.0-H-Micro and 16,384 for MinerU2.5 2509 1.2B. Maximum output per response: Granite-4.0-H-Micro up to 131,072, Qwen3.5 2B up to 81,920 tokens.
Which can read images, PDFs, audio or video?
Granite-4.0-H-Micro accepts text; MinerU2.5 2509 1.2B accepts text and images; Qwen3.5 2B accepts text, images and video. Qwen3.5 2B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (AGPL-3.0 and Apache-2.0), so you can self-host them.
Which is newer?
Qwen3.5 2B is the newest, released Mar 2, 2026. Granite-4.0-H-Micro came out Oct 2, 2025; MinerU2.5 2509 1.2B came out Sep 17, 2025.
How do you decide the winner?
This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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 18, 2026.