GLM-4.7-FlashX vs Granite-4.0-H-Small vs Ministral 3 8B
Ministral 3 8B comes out ahead, 70 to 63 and 61 on our weighted score, though Granite-4.0-H-Small is 24% cheaper per token.
Z.ai (Zhipu)GLM-4.7-FlashX
61/100- ECI—
- Price$0.07 / $0.40
- Context200K
IBMGranite-4.0-H-Small
63/100- ECI—
- Price$0.064 / $0.265
- Context131K
- Our pick
Mistral AIMinistral 3 8B
70/100- ECI—
- Price$0.15 / $0.15
- Context262K
Ministral 3 8B is our pick
Ministral 3 8B is the better all-round choice, scoring 70/100 against Granite-4.0-H-Small (63) and GLM-4.7-FlashX (61). It leads on inputs & features and context window. Granite-4.0-H-Small wins 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 priceGranite-4.0-H-SmallGranite-4.0-H-Small $0.114 · Ministral 3 8B $0.15 · GLM-4.7-FlashX $0.152 per 1M tokens (3:1 blend)
- Longest contextMinistral 3 8BMinistral 3 8B 262,144 · GLM-4.7-FlashX 200,000 · Granite-4.0-H-Small 131,072 tokens
- Widest inputsMinistral 3 8BGLM-4.7-FlashX: Text · Granite-4.0-H-Small: Text · Ministral 3 8B: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | GLM-4.7-FlashX | Granite-4.0-H-Small | Ministral 3 8B |
|---|---|---|---|---|
| Price | 50% | 89 | 95 | 89 |
| Inputs & features | 30% | 35 | 35 | 60 |
| Context window | 20% | 32 | 24 | 37 |
| Overall | 100% | 61/100 | 63/100 | 70/100 |
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 | GLM-4.7-FlashXZ.ai (Zhipu) | Granite-4.0-H-SmallIBM | Ministral 3 8BMistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.07 | $0.064 (best) | $0.15 |
| Output | $0.40 | $0.265 | $0.15 (best) |
| Cached input | $0.01 | — | — |
| Blended (3:1) | $0.152 | $0.114 (best) | $0.15 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Z.AI API | Official watsonx.ai API | Median of 1 providers |
| Limits | |||
| Context window | 200,000 tokens | 131,072 tokens | 262,144 tokens (best) |
| Max output | 131,072 tokens | 131,072 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | Open | Open | OpenApache 2.0 |
| API model ID | glm-4.7-flashx | ibm/granite-4-h-small | — |
| API providers | 8 (best) | 1 | 1 |
| Released | Jan 19, 2026 | Oct 2, 2025 | Dec 2, 2025 |
| Knowledge cutoff | Apr 2025 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- GLM-4.7-FlashX$1.50
- Granite-4.0-H-Small$1.17
- Ministral 3 8B$1.80
Which should you choose?
Which is better: GLM-4.7-FlashX, Granite-4.0-H-Small or Ministral 3 8B?
Ministral 3 8B is the better all-round choice, scoring 70/100 against Granite-4.0-H-Small (63) and GLM-4.7-FlashX (61). It leads on inputs & features and context window. Granite-4.0-H-Small wins 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, GLM-4.7-FlashX, Granite-4.0-H-Small or Ministral 3 8B?
Granite-4.0-H-Small is cheaper at $0.064 input / $0.265 output per million tokens (official watsonx.ai API price). Ministral 3 8B costs $0.15 input / $0.15 output per million tokens (median across 1 API provider); GLM-4.7-FlashX costs $0.07 input / $0.40 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $0.114 per million tokens for Granite-4.0-H-Small versus $0.15 for Ministral 3 8B (1.3× as much) and $0.152 for GLM-4.7-FlashX (1.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. GLM-4.7-FlashX has not been scored yet, Granite-4.0-H-Small has not been scored yet and Ministral 3 8B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for GLM-4.7-FlashX, Granite-4.0-H-Small and Ministral 3 8B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Ministral 3 8B has the largest context window at 262,144 tokens, against 200,000 for GLM-4.7-FlashX and 131,072 for Granite-4.0-H-Small. Maximum output per response: GLM-4.7-FlashX up to 131,072, Granite-4.0-H-Small up to 131,072, Ministral 3 8B up to 262,144 tokens.
Which can read images, PDFs, audio or video?
GLM-4.7-FlashX accepts text; Granite-4.0-H-Small accepts text; Ministral 3 8B accepts text and images. Ministral 3 8B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache 2.0), so you can self-host them.
Which is newer?
GLM-4.7-FlashX is the newest, released Jan 19, 2026. Ministral 3 8B came out Dec 2, 2025; Granite-4.0-H-Small came out Oct 2, 2025. Knowledge cutoff: GLM-4.7-FlashX Apr 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 Oct 4, 2026.
