MiniCPM5-2B vs Nemotron 3 Nano Omni 30B A3B Reasoning vs Step 3.7 Flash
Nemotron 3 Nano Omni 30B A3B Reasoning comes out ahead, 69 to 62 and 53 on our weighted score, though MiniCPM5-2B is 30% cheaper per token.
OpenBMB
MiniCPM5-2B
53/100- ECI—
- Price$0.124 / $0.743
- Context131K
- Our pick
NVIDIANemotron 3 Nano Omni 30B A3B Reasoning
69/100- ECI—
- Price$0.25 / $0.85
- Context256K
StepFunStep 3.7 Flash
62/100- ECI—
- Price$0.185 / $1.11
- Context256K
Nemotron 3 Nano Omni 30B A3B Reasoning is our pick
Nemotron 3 Nano Omni 30B A3B Reasoning is the better all-round choice, scoring 69/100 against Step 3.7 Flash (62) and MiniCPM5-2B (53). It leads on inputs & features. MiniCPM5-2B 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 priceMiniCPM5-2BMiniCPM5-2B $0.279 · Nemotron 3 Nano Omni 30B A3B Reasoning $0.40 · Step 3.7 Flash $0.416 per 1M tokens (3:1 blend)
- Longest contextNemotron 3 Nano Omni 30B A3B Reasoning and Step 3.7 FlashNemotron 3 Nano Omni 30B A3B Reasoning 256,000 · Step 3.7 Flash 256,000 · MiniCPM5-2B 131,072 tokens
- Widest inputsNemotron 3 Nano Omni 30B A3B ReasoningMiniCPM5-2B: Text · Nemotron 3 Nano Omni 30B A3B Reasoning: Text, Images, Audio, Video · Step 3.7 Flash: Text, Images, Video
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | MiniCPM5-2B | Nemotron 3 Nano Omni 30B A3B Reasoning | Step 3.7 Flash |
|---|---|---|---|---|
| Price | 50% | 76 | 69 | 68 |
| Inputs & features | 30% | 35 | 90 | 70 |
| Context window | 20% | 24 | 36 | 36 |
| Overall | 100% | 53/100 | 69/100 | 62/100 |
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 | MiniCPM5-2BOpenBMB | Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA | Step 3.7 FlashStepFun |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.124 (best) | $0.25 | $0.185 |
| Output | $0.743 (best) | $0.85 | $1.11 |
| Cached input | — | — | $0.037 |
| Blended (3:1) | $0.279 (best) | $0.40 | $0.416 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 4 providers | Official StepFun (Global) API |
| Limits | |||
| Context window | 131,072 tokens | 256,000 tokens (best) | 256,000 tokens (best) |
| Max output | 131,072 tokens | 65,536 tokens | 256,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | Yes | No |
| Video | No | Yes | Yes |
| Reasoning | Yes | Yes | Yeslow · medium · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Openapache-2.0 | Open | Open |
| API model ID | — | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning | step-3.7-flash |
| API providers | 1 | 8 | 18 (best) |
| Released | Sep 6, 2026 | Apr 28, 2026 | May 29, 2026 |
| Knowledge cutoff | — | — | Mar 1, 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- MiniCPM5-2B$2.73
- Nemotron 3 Nano Omni 30B A3B Reasoning$4.20
- Step 3.7 Flash$4.07
Which should you choose?
Which is better: MiniCPM5-2B, Nemotron 3 Nano Omni 30B A3B Reasoning or Step 3.7 Flash?
Nemotron 3 Nano Omni 30B A3B Reasoning is the better all-round choice, scoring 69/100 against Step 3.7 Flash (62) and MiniCPM5-2B (53). It leads on inputs & features. MiniCPM5-2B 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, MiniCPM5-2B, Nemotron 3 Nano Omni 30B A3B Reasoning or Step 3.7 Flash?
MiniCPM5-2B is cheaper at $0.124 input / $0.743 output per million tokens (median across 1 API provider). Nemotron 3 Nano Omni 30B A3B Reasoning costs $0.25 input / $0.85 output per million tokens (median across 4 API providers; free on Nvidia); Step 3.7 Flash costs $0.185 input / $1.11 output per million tokens (official StepFun (Global) API price). At a typical mix of three input tokens to one output token, that is $0.279 per million tokens for MiniCPM5-2B versus $0.40 for Nemotron 3 Nano Omni 30B A3B Reasoning (1.4× as much) and $0.416 for Step 3.7 Flash (1.5× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MiniCPM5-2B has not been scored yet, Nemotron 3 Nano Omni 30B A3B Reasoning has not been scored yet and Step 3.7 Flash has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MiniCPM5-2B, Nemotron 3 Nano Omni 30B A3B Reasoning and Step 3.7 Flash 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?
Nemotron 3 Nano Omni 30B A3B Reasoning and Step 3.7 Flash have the largest context windows (256,000 and 256,000 tokens), against 131,072 for MiniCPM5-2B. Maximum output per response: MiniCPM5-2B up to 131,072, Nemotron 3 Nano Omni 30B A3B Reasoning up to 65,536, Step 3.7 Flash up to 256,000 tokens.
Which can read images, PDFs, audio or video?
MiniCPM5-2B accepts text; Nemotron 3 Nano Omni 30B A3B Reasoning accepts text, images, audio and video; Step 3.7 Flash accepts text, images and video. Nemotron 3 Nano Omni 30B A3B Reasoning 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?
MiniCPM5-2B is the newest, released Sep 6, 2026. Step 3.7 Flash came out May 29, 2026; Nemotron 3 Nano Omni 30B A3B Reasoning came out Apr 28, 2026. Knowledge cutoff: Step 3.7 Flash Mar 1, 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.
