Apertus 8B vs Baichuan M2 32B vs Granite-4.0-H-Small
Too close to call on our weighted score (Granite-4.0-H-Small 61, Baichuan M2 32B 58, Apertus 8B 54). The right pick depends on what you value most.
Swiss AI
Apertus 8B
54/100- ECI—
- Price$0.10 / $0.20
- Context66K
BaichuanBaichuan M2 32B
58/100- ECI—
- Price$0.07 / $0.07
- Context131K
IBMGranite-4.0-H-Small
61/100- ECI—
- Price$0.064 / $0.265
- Context131K
Too close to call
It is close. Our weighted score puts them within 3 points (Granite-4.0-H-Small 61/100, Baichuan M2 32B 58/100, Apertus 8B 54/100), so choose by what matters most for your work: Baichuan M2 32B on price. The score weighs price 50%, inputs & features 30%, context window 20%. 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 priceBaichuan M2 32BBaichuan M2 32B $0.07 · Granite-4.0-H-Small $0.114 · Apertus 8B $0.125 per 1M tokens (3:1 blend)
- Longest contextBaichuan M2 32B and Granite-4.0-H-SmallBaichuan M2 32B 131,072 · Granite-4.0-H-Small 131,072 · Apertus 8B 65,536 tokens
- Widest inputsSame inputsApertus 8B: Text · Baichuan M2 32B: Text · Granite-4.0-H-Small: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Apertus 8B | Baichuan M2 32B | Granite-4.0-H-Small |
|---|---|---|---|---|
| Price | 50% | 89 | 100 | 91 |
| Inputs & features | 30% | 25 | 10 | 35 |
| Context window | 20% | 12 | 25 | 25 |
| Overall | 100% | 54/100 | 58/100 | 61/100 |
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 | Apertus 8BSwiss AI | Baichuan M2 32BBaichuan | Granite-4.0-H-SmallIBM |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.10 | $0.07 | $0.064 (best) |
| Output | $0.20 | $0.07 (best) | $0.265 |
| Cached input | — | — | — |
| Blended (3:1) | $0.125 | $0.07 (best) | $0.114 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 1 providers | Official watsonx.ai API |
| Limits | |||
| Context window | 65,536 tokens | 131,072 tokens (best) | 131,072 tokens (best) |
| Max output | 8,192 tokens | 131,072 tokens (best) | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | No |
| Tool calling | Yes | No | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | OpenApache-2.0 | OpenApache-2.0 | Open |
| API model ID | — | — | ibm/granite-4-h-small |
| API providers | 1 | 1 | 1 |
| Released | Sep 2, 2025 | Aug 13, 2025 | Oct 2, 2025 |
| Knowledge cutoff | Sep 2025 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Apertus 8B$1.40
- Baichuan M2 32B$0.84
- Granite-4.0-H-Small$1.17
Which should you choose?
Which is better: Apertus 8B, Baichuan M2 32B or Granite-4.0-H-Small?
It is close. Our weighted score puts them within 3 points (Granite-4.0-H-Small 61/100, Baichuan M2 32B 58/100, Apertus 8B 54/100), so choose by what matters most for your work: Baichuan M2 32B on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Apertus 8B, Baichuan M2 32B or Granite-4.0-H-Small?
Baichuan M2 32B is cheaper at $0.07 input / $0.07 output per million tokens (median across 1 API provider). Granite-4.0-H-Small costs $0.064 input / $0.265 output per million tokens (official watsonx.ai API price); Apertus 8B costs $0.10 input / $0.20 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.07 per million tokens for Baichuan M2 32B versus $0.114 for Granite-4.0-H-Small (1.6× as much) and $0.125 for Apertus 8B (1.8× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Apertus 8B has not been scored yet, Baichuan M2 32B has not been scored yet and Granite-4.0-H-Small has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Apertus 8B, Baichuan M2 32B and Granite-4.0-H-Small yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Baichuan M2 32B does not support tool calling, which most coding agents need.
Which has the bigger context window?
Baichuan M2 32B and Granite-4.0-H-Small have the largest context windows (131,072 and 131,072 tokens), against 65,536 for Apertus 8B. Maximum output per response: Apertus 8B up to 8,192, Baichuan M2 32B up to 131,072, Granite-4.0-H-Small up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Apertus 8B accepts text; Baichuan M2 32B accepts text; Granite-4.0-H-Small accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights (Apache-2.0), so you can self-host them.
Which is newer?
Granite-4.0-H-Small is the newest, released Oct 2, 2025. Apertus 8B came out Sep 2, 2025; Baichuan M2 32B came out Aug 13, 2025. Knowledge cutoff: Apertus 8B Sep 2025.
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.
