Qwen3.5 122B-A10B vs Trinity Large Thinking vs MiniMax-M2.5-highspeed
Qwen3.5 122B-A10B comes out ahead, 58 to 55 and 41 on our weighted score, though Trinity Large Thinking is 2.8× cheaper per token.
- Our pick
Alibaba (Qwen)Qwen3.5 122B-A10B
58/100- ECI—
- Price$0.40 / $3.20
- Context262K
Arcee AITrinity Large Thinking
55/100- ECI—
- Price$0.25 / $0.80
- Context524K
MiniMaxMiniMax-M2.5-highspeed
41/100- ECI—
- Price$0.60 / $2.40
- Context205K
Qwen3.5 122B-A10B is our pick
Qwen3.5 122B-A10B is the better all-round choice, scoring 58/100 against Trinity Large Thinking (55) and MiniMax-M2.5-highspeed (41). It leads on inputs & features. Trinity Large Thinking wins on price and context window. 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 priceTrinity Large ThinkingTrinity Large Thinking $0.388 · MiniMax-M2.5-highspeed $1.05 · Qwen3.5 122B-A10B $1.10 per 1M tokens (3:1 blend)
- Longest contextTrinity Large ThinkingTrinity Large Thinking 524,288 · 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 · Trinity Large Thinking: Text · MiniMax-M2.5-highspeed: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Qwen3.5 122B-A10B | Trinity Large Thinking | MiniMax-M2.5-highspeed |
|---|---|---|---|---|
| Price | 50% | 48 | 69 | 49 |
| Inputs & features | 30% | 90 | 35 | 35 |
| Context window | 20% | 37 | 49 | 32 |
| Overall | 100% | 58/100 | 55/100 | 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) | Trinity Large ThinkingArcee AI | MiniMax-M2.5-highspeedMiniMax |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.40 | $0.25 (best) | $0.60 |
| Output | $3.20 | $0.80 (best) | $2.40 |
| Cached input | — | $0.06 | $0.06 |
| Blended (3:1) | $1.10 | $0.388 (best) | $1.05 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Alibaba API | Official Arcee API | Official MiniMax (minimax.io) API |
| Limits | |||
| Context window | 262,144 tokens | 524,288 tokens (best) | 204,800 tokens |
| Max output | 65,536 tokens | 262,144 tokens (best) | 131,072 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | Yes | No | No |
| Video | Yes | No | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Open | OpenOpenMDW-1.1 | Open |
| API model ID | qwen3.5-122b-a10b | trinity-large-thinking | MiniMax-M2.5-highspeed |
| API providers | 19 (best) | 6 | 7 |
| Released | Feb 23, 2026 | Apr 1, 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
- Trinity Large Thinking$4.10
- MiniMax-M2.5-highspeed$10.80
Which should you choose?
Which is better: Qwen3.5 122B-A10B, Trinity Large Thinking or MiniMax-M2.5-highspeed?
Qwen3.5 122B-A10B is the better all-round choice, scoring 58/100 against Trinity Large Thinking (55) and MiniMax-M2.5-highspeed (41). It leads on inputs & features. Trinity Large Thinking wins on price and context window. 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, Trinity Large Thinking or MiniMax-M2.5-highspeed?
Trinity Large Thinking is cheaper at $0.25 input / $0.80 output per million tokens (official Arcee API price). MiniMax-M2.5-highspeed costs $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). At a typical mix of three input tokens to one output token, that is $0.388 per million tokens for Trinity Large Thinking versus $1.05 for MiniMax-M2.5-highspeed (2.7× as much) and $1.10 for Qwen3.5 122B-A10B (2.8× 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, Trinity Large Thinking 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, Trinity Large Thinking 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?
Trinity Large Thinking has the largest context window at 524,288 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, Trinity Large Thinking up to 262,144, 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; Trinity Large Thinking accepts text; MiniMax-M2.5-highspeed accepts text. Qwen3.5 122B-A10B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (OpenMDW-1.1), so you can self-host them.
Which is newer?
Trinity Large Thinking is the newest, released Apr 1, 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.
