Qwen3.5 122B-A10B vs Step 5 Preview vs MiniMax-M2.5-highspeed
Too close to call on our weighted score (Qwen3.5 122B-A10B 58, Step 5 Preview 57, MiniMax-M2.5-highspeed 41). The right pick depends on what you value most.
Alibaba (Qwen)Qwen3.5 122B-A10B
58/100- ECI—
- Price$0.40 / $3.20
- Context262K
StepFunStep 5 Preview
57/100- ECI—
- Price$1.00 / $2.70
- Context1M
MiniMaxMiniMax-M2.5-highspeed
41/100- ECI—
- Price$0.60 / $2.40
- Context205K
Too close to call
It is close. Our weighted score puts them within 1 points (Qwen3.5 122B-A10B 58/100, Step 5 Preview 57/100, MiniMax-M2.5-highspeed 41/100), so choose by what matters most for your work: MiniMax-M2.5-highspeed on price and Step 5 Preview for long inputs. 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 priceMiniMax-M2.5-highspeedMiniMax-M2.5-highspeed $1.05 · Qwen3.5 122B-A10B $1.10 · Step 5 Preview $1.43 per 1M tokens (3:1 blend)
- Longest contextStep 5 PreviewStep 5 Preview 1,000,000 · Qwen3.5 122B-A10B 262,144 · MiniMax-M2.5-highspeed 204,800 tokens
- Widest inputsQwen3.5 122B-A10BQwen3.5 122B-A10B: Text, Images, Audio, Video · Step 5 Preview: Text, Images, Video · MiniMax-M2.5-highspeed: Text
- Self-hostingQwen3.5 122B-A10B and MiniMax-M2.5-highspeedPublishes downloadable weights
| Measure | Weight | Qwen3.5 122B-A10B | Step 5 Preview | MiniMax-M2.5-highspeed |
|---|---|---|---|---|
| Price | 50% | 48 | 43 | 49 |
| Inputs & features | 30% | 90 | 80 | 35 |
| Context window | 20% | 37 | 60 | 32 |
| Overall | 100% | 58/100 | 57/100 | 41/100 |
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 | Qwen3.5 122B-A10BAlibaba (Qwen) | Step 5 PreviewStepFun | MiniMax-M2.5-highspeedMiniMax |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.40 (best) | $1.00 | $0.60 |
| Output | $3.20 | $2.70 | $2.40 (best) |
| Cached input | — | $0.05 (best) | $0.06 |
| Blended (3:1) | $1.10 | $1.43 | $1.05 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Alibaba API | Official StepFun (Global) API | Official MiniMax (minimax.io) API |
| Limits | |||
| Context window | 262,144 tokens | 1,000,000 tokens (best) | 204,800 tokens |
| Max output | 65,536 tokens | 1,000,000 tokens (best) | 131,072 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | No | No |
| Audio | Yes | No | No |
| Video | Yes | Yes | No |
| Reasoning | Yes | Yeslow · medium · high | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | qwen3.5-122b-a10b | step-5-preview | MiniMax-M2.5-highspeed |
| API providers | 19 (best) | 7 | 7 |
| Released | Feb 23, 2026 | Sep 16, 2026 | Feb 13, 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.
- Qwen3.5 122B-A10B$10.40
- Step 5 Preview$15.40
- MiniMax-M2.5-highspeed$10.80
Which should you choose?
Which is better: Qwen3.5 122B-A10B, Step 5 Preview or MiniMax-M2.5-highspeed?
It is close. Our weighted score puts them within 1 points (Qwen3.5 122B-A10B 58/100, Step 5 Preview 57/100, MiniMax-M2.5-highspeed 41/100), so choose by what matters most for your work: MiniMax-M2.5-highspeed on price and Step 5 Preview for long inputs. 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, Qwen3.5 122B-A10B, Step 5 Preview or MiniMax-M2.5-highspeed?
MiniMax-M2.5-highspeed is cheaper at $0.60 input / $2.40 output per million tokens (official MiniMax (minimax.io) API price). Qwen3.5 122B-A10B costs $0.40 input / $3.20 output per million tokens (official Alibaba API price); Step 5 Preview costs $1.00 input / $2.70 output per million tokens (official StepFun (Global) API price). At a typical mix of three input tokens to one output token, that is $1.05 per million tokens for MiniMax-M2.5-highspeed versus $1.10 for Qwen3.5 122B-A10B (1× as much) and $1.43 for Step 5 Preview (1.4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Qwen3.5 122B-A10B has not been scored yet, Step 5 Preview has not been scored yet and MiniMax-M2.5-highspeed has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3.5 122B-A10B, Step 5 Preview and MiniMax-M2.5-highspeed 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?
Step 5 Preview has the largest context window at 1,000,000 tokens, against 262,144 for Qwen3.5 122B-A10B and 204,800 for MiniMax-M2.5-highspeed. Maximum output per response: Qwen3.5 122B-A10B up to 65,536, Step 5 Preview up to 1,000,000, MiniMax-M2.5-highspeed up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Qwen3.5 122B-A10B accepts text, images, audio and video; Step 5 Preview accepts text, images and video; MiniMax-M2.5-highspeed accepts text. Qwen3.5 122B-A10B handles the widest range of inputs.
Are any of these open source?
Qwen3.5 122B-A10B and MiniMax-M2.5-highspeed publishes its weights and can be self-hosted; Step 5 Preview is proprietary.
Which is newer?
Step 5 Preview is the newest, released Sep 16, 2026. Qwen3.5 122B-A10B came out Feb 23, 2026; MiniMax-M2.5-highspeed came out Feb 13, 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.
