Kimi K2 Thinking vs MiniMax-M2.5-highspeed vs Qwen3.5 122B-A10B
Qwen3.5 122B-A10B comes out ahead, 58 to 42 and 41 on our weighted score.
Moonshot AIKimi K2 Thinking
42/100- ECI146.0
- Price$0.60 / $2.50
- Context262K
MiniMaxMiniMax-M2.5-highspeed
41/100- ECI—
- Price$0.60 / $2.40
- Context205K
- Our pick
Alibaba (Qwen)Qwen3.5 122B-A10B
58/100- ECI—
- Price$0.40 / $3.20
- Context262K
Qwen3.5 122B-A10B is our pick
Qwen3.5 122B-A10B is the better all-round choice, scoring 58/100 against Kimi K2 Thinking (42) and MiniMax-M2.5-highspeed (41). It leads on inputs & features. 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 · Kimi K2 Thinking $1.07 · Qwen3.5 122B-A10B $1.10 per 1M tokens (3:1 blend)
- Longest contextKimi K2 Thinking and Qwen3.5 122B-A10BKimi K2 Thinking 262,144 · Qwen3.5 122B-A10B 262,144 · MiniMax-M2.5-highspeed 204,800 tokens
- Widest inputsQwen3.5 122B-A10BKimi K2 Thinking: Text · MiniMax-M2.5-highspeed: Text · Qwen3.5 122B-A10B: Text, Images, Audio, Video
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Kimi K2 Thinking | MiniMax-M2.5-highspeed | Qwen3.5 122B-A10B |
|---|---|---|---|---|
| Price | 50% | 48 | 49 | 48 |
| Inputs & features | 30% | 35 | 35 | 90 |
| Context window | 20% | 37 | 32 | 37 |
| Overall | 100% | 42/100 | 41/100 | 58/100 |
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 | Kimi K2 ThinkingMoonshot AI | MiniMax-M2.5-highspeedMiniMax | Qwen3.5 122B-A10BAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 146.0 | — | — |
| ECI rank | #72 of 148 | — | — |
| GPQA DiamondGraduate-level science questions | 84.2% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 83.1% | — | — |
| Price per million tokens | |||
| Input | $0.60 | $0.60 | $0.40 (best) |
| Output | $2.50 | $2.40 (best) | $3.20 |
| Cached input | — | $0.06 | — |
| Blended (3:1) | $1.07 | $1.05 (best) | $1.10 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 10 providers | Official MiniMax (minimax.io) API | Official Alibaba API |
| Limits | |||
| Context window | 262,144 tokens (best) | 204,800 tokens | 262,144 tokens (best) |
| Max output | 262,144 tokens (best) | 131,072 tokens | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | Yes |
| Video | No | No | Yes |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | — | MiniMax-M2.5-highspeed | qwen3.5-122b-a10b |
| API providers | 10 | 7 | 19 (best) |
| Released | Nov 6, 2025 | Feb 13, 2026 | Feb 23, 2026 |
| Knowledge cutoff | Aug 2024 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Kimi K2 Thinking$11.00
- MiniMax-M2.5-highspeed$10.80
- Qwen3.5 122B-A10B$10.40
Which should you choose?
Which is better: Kimi K2 Thinking, MiniMax-M2.5-highspeed or Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B is the better all-round choice, scoring 58/100 against Kimi K2 Thinking (42) and MiniMax-M2.5-highspeed (41). It leads on inputs & features. 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, Kimi K2 Thinking, MiniMax-M2.5-highspeed or Qwen3.5 122B-A10B?
MiniMax-M2.5-highspeed is cheaper at $0.60 input / $2.40 output per million tokens (official MiniMax (minimax.io) API price). Kimi K2 Thinking costs $0.60 input / $2.50 output per million tokens (median across 10 API providers); 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 $1.05 per million tokens for MiniMax-M2.5-highspeed versus $1.07 for Kimi K2 Thinking (1× as much) and $1.10 for Qwen3.5 122B-A10B (1× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Kimi K2 Thinking has an ECI of 146.0, MiniMax-M2.5-highspeed has not been scored yet and Qwen3.5 122B-A10B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Kimi K2 Thinking, MiniMax-M2.5-highspeed and Qwen3.5 122B-A10B 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?
Kimi K2 Thinking and Qwen3.5 122B-A10B have the largest context windows (262,144 and 262,144 tokens), against 204,800 for MiniMax-M2.5-highspeed. Maximum output per response: Kimi K2 Thinking up to 262,144, MiniMax-M2.5-highspeed up to 131,072, Qwen3.5 122B-A10B up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Kimi K2 Thinking accepts text; MiniMax-M2.5-highspeed accepts text; Qwen3.5 122B-A10B accepts text, images, audio and video. Qwen3.5 122B-A10B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Qwen3.5 122B-A10B is the newest, released Feb 23, 2026. MiniMax-M2.5-highspeed came out Feb 13, 2026; Kimi K2 Thinking came out Nov 6, 2025. Knowledge cutoff: Kimi K2 Thinking Aug 2024.
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.
Related comparisons
- Kimi K2 Thinking vs Qwen3.5 PlusAlibaba (Qwen) · ECI 146.8
- Kimi K2 Thinking vs GLM-4.7Z.ai (Zhipu) · ECI 143.5
- Kimi K2 Thinking vs Nemotron 3 Ultra 550B A55BNVIDIA · ECI 146.2
- Kimi K2 Thinking vs GPT-5 MiniOpenAI · ECI 145.5
- MiniMax-M2.5-highspeed vs DeepSeek OCR 2DeepSeek
- MiniMax-M2.5-highspeed vs Seed 2.0 CodeByteDance Seed
