Gemma 4 31B IT vs MiniCPM5-2B vs Qwen3.8 Flash Next
Too close to call on our weighted score (Gemma 4 31B IT 70, Qwen3.8 Flash Next 70, MiniCPM5-2B 53). The right pick depends on what you value most.
GoogleGemma 4 31B IT
70/100- ECI142.8
- Price$0.14 / $0.40
- Context262K
OpenBMB
MiniCPM5-2B
53/100- ECI—
- Price$0.124 / $0.743
- Context131K
Alibaba (Qwen)Qwen3.8 Flash Next
70/100- ECI—
- Price$0.20 / $0.50
- Context262K
Too close to call
It is close. Our weighted score puts them within a point (Gemma 4 31B IT 70/100, Qwen3.8 Flash Next 70/100, MiniCPM5-2B 53/100), so choose by what matters most for your work: Gemma 4 31B IT 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 priceGemma 4 31B ITGemma 4 31B IT $0.205 · Qwen3.8 Flash Next $0.275 · MiniCPM5-2B $0.279 per 1M tokens (3:1 blend)
- Longest contextGemma 4 31B IT and Qwen3.8 Flash NextGemma 4 31B IT 262,144 · Qwen3.8 Flash Next 262,144 · MiniCPM5-2B 131,072 tokens
- Widest inputsQwen3.8 Flash NextGemma 4 31B IT: Text, Images · MiniCPM5-2B: Text · Qwen3.8 Flash Next: Text, Images, Video
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Gemma 4 31B IT | MiniCPM5-2B | Qwen3.8 Flash Next |
|---|---|---|---|---|
| Price | 50% | 83 | 76 | 76 |
| Inputs & features | 30% | 70 | 35 | 80 |
| Context window | 20% | 37 | 24 | 37 |
| Overall | 100% | 70/100 | 53/100 | 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 | Gemma 4 31B ITGoogle | MiniCPM5-2BOpenBMB | Qwen3.8 Flash NextAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 142.8 | — | — |
| ECI rank | #86 of 148 | — | — |
| GPQA DiamondGraduate-level science questions | 75.8% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 73.3% | — | — |
| SimpleQA VerifiedShort factual questions | 10.4% | — | — |
| Price per million tokens | |||
| Input | $0.14 | $0.124 (best) | $0.20 |
| Output | $0.40 (best) | $0.743 | $0.50 |
| Cached input | — | — | — |
| Blended (3:1) | $0.205 (best) | $0.279 | $0.275 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 30 providers | Median of 1 providers | Median of 5 providers |
| Limits | |||
| Context window | 262,144 tokens (best) | 131,072 tokens | 262,144 tokens (best) |
| Max output | 32,768 tokens | 131,072 tokens (best) | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | Open | Openapache-2.0 | Openqwen-community-1.0 |
| API model ID | gemma-4-31b-it | — | — |
| API providers | 38 (best) | 1 | 5 |
| Released | Apr 2, 2026 | Sep 6, 2026 | Aug 27, 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.
- Gemma 4 31B IT$2.20
- MiniCPM5-2B$2.73
- Qwen3.8 Flash Next$3.00
Which should you choose?
Which is better: Gemma 4 31B IT, MiniCPM5-2B or Qwen3.8 Flash Next?
It is close. Our weighted score puts them within a point (Gemma 4 31B IT 70/100, Qwen3.8 Flash Next 70/100, MiniCPM5-2B 53/100), so choose by what matters most for your work: Gemma 4 31B IT 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, Gemma 4 31B IT, MiniCPM5-2B or Qwen3.8 Flash Next?
Gemma 4 31B IT is cheaper at $0.14 input / $0.40 output per million tokens (median across 30 API providers). Qwen3.8 Flash Next costs $0.20 input / $0.50 output per million tokens (median across 5 API providers); MiniCPM5-2B costs $0.124 input / $0.743 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.205 per million tokens for Gemma 4 31B IT versus $0.275 for Qwen3.8 Flash Next (1.3× as much) and $0.279 for MiniCPM5-2B (1.4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Gemma 4 31B IT has an ECI of 142.8, MiniCPM5-2B has not been scored yet and Qwen3.8 Flash Next has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Gemma 4 31B IT, MiniCPM5-2B and Qwen3.8 Flash Next 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?
Gemma 4 31B IT and Qwen3.8 Flash Next have the largest context windows (262,144 and 262,144 tokens), against 131,072 for MiniCPM5-2B. Maximum output per response: Gemma 4 31B IT up to 32,768, MiniCPM5-2B up to 131,072, Qwen3.8 Flash Next up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Gemma 4 31B IT accepts text and images; MiniCPM5-2B accepts text; Qwen3.8 Flash Next accepts text, images and video. Qwen3.8 Flash Next handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (apache-2.0 and qwen-community-1.0), so you can self-host them.
Which is newer?
MiniCPM5-2B is the newest, released Sep 6, 2026. Qwen3.8 Flash Next came out Aug 27, 2026; Gemma 4 31B IT came out Apr 2, 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 Oct 4, 2026.
