Qwen3.5 122B-A10B vs Qwen3.5 35B-A3B Base vs Grok Build 0.1
Too close to call on our weighted score (Qwen3.5 122B-A10B 54, Grok Build 0.1 53, Qwen3.5 35B-A3B Base 45). The right pick depends on what you value most.
Alibaba (Qwen)Qwen3.5 122B-A10B
54/100- ECI—
- Price$0.40 / $3.20
- Context262K
- Alibaba (Qwen)
Qwen3.5 35B-A3B Base
45/100- ECI—
- Price$0.54 / $1.33
- Context262K
xAIGrok Build 0.1
53/100- ECI—
- Price$1.00 / $2.00
- Context256K
Too close to call
It is close. Our weighted score puts them within 1 points (Qwen3.5 122B-A10B 54/100, Grok Build 0.1 53/100, Qwen3.5 35B-A3B Base 45/100), so choose by what matters most for your work: Qwen3.5 35B-A3B Base 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 priceQwen3.5 35B-A3B BaseQwen3.5 35B-A3B Base $0.739 · Qwen3.5 122B-A10B $1.10 · Grok Build 0.1 $1.25 per 1M tokens (3:1 blend)
- Longest contextQwen3.5 122B-A10B and Qwen3.5 35B-A3B BaseQwen3.5 122B-A10B 262,144 · Qwen3.5 35B-A3B Base 262,144 · Grok Build 0.1 256,000 tokens
- Widest inputsSame inputsQwen3.5 122B-A10B: Text, Images, Video · Qwen3.5 35B-A3B Base: Text, Images, Video · Grok Build 0.1: Text, Images, PDFs
- Self-hostingQwen3.5 122B-A10B and Qwen3.5 35B-A3B BasePublishes downloadable weights (Apache-2.0)
| Measure | Weight | Qwen3.5 122B-A10B | Qwen3.5 35B-A3B Base | Grok Build 0.1 |
|---|---|---|---|---|
| Price | 50% | 46 | 54 | 43 |
| Inputs & features | 30% | 80 | 35 | 80 |
| Context window | 20% | 37 | 37 | 36 |
| Overall | 100% | 54/100 | 45/100 | 53/100 |
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) | Qwen3.5 35B-A3B BaseAlibaba (Qwen) | Grok Build 0.1xAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.40 (best) | $0.54 | $1.00 |
| Output | $3.20 | $1.33 (best) | $2.00 |
| Cached input | — | — | $0.20 |
| Blended (3:1) | $1.10 | $0.739 (best) | $1.25 |
| Long-context rate | Same rate | Same rate | Over 200K: $2.00 / $4.00 |
| Price source | Official Alibaba API | Median of 1 providers | Official xAI API |
| Limits | |||
| Context window | 262,144 tokens (best) | 262,144 tokens (best) | 256,000 tokens |
| Max output | 65,536 tokens | 65,536 tokens | 256,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | No |
| Video | Yes | Yes | No |
| Reasoning | Yes | No | Yes |
| Tool calling | Yes | No | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | Open | OpenApache-2.0 | Proprietary |
| API model ID | qwen3.5-122b-a10b | — | grok-build-0.1 |
| API providers | 22 (best) | 1 | 20 |
| Released | Feb 23, 2026 | Feb 24, 2026 | Apr 16, 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
- Qwen3.5 35B-A3B Base$8.07
- Grok Build 0.1$14.00
Which should you choose?
Which is better: Qwen3.5 122B-A10B, Qwen3.5 35B-A3B Base or Grok Build 0.1?
It is close. Our weighted score puts them within 1 points (Qwen3.5 122B-A10B 54/100, Grok Build 0.1 53/100, Qwen3.5 35B-A3B Base 45/100), so choose by what matters most for your work: Qwen3.5 35B-A3B Base 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, Qwen3.5 122B-A10B, Qwen3.5 35B-A3B Base or Grok Build 0.1?
Qwen3.5 35B-A3B Base is cheaper at $0.54 input / $1.33 output per million tokens (median across 1 API provider). Qwen3.5 122B-A10B costs $0.40 input / $3.20 output per million tokens (official Alibaba API price); Grok Build 0.1 costs $1.00 input / $2.00 output per million tokens (official xAI API price). At a typical mix of three input tokens to one output token, that is $0.739 per million tokens for Qwen3.5 35B-A3B Base versus $1.10 for Qwen3.5 122B-A10B (1.5× as much) and $1.25 for Grok Build 0.1 (1.7× 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, Qwen3.5 35B-A3B Base has not been scored yet and Grok Build 0.1 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3.5 122B-A10B, Qwen3.5 35B-A3B Base and Grok Build 0.1 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Qwen3.5 35B-A3B Base does not support tool calling, which most coding agents need.
Which has the bigger context window?
Qwen3.5 122B-A10B and Qwen3.5 35B-A3B Base have the largest context windows (262,144 and 262,144 tokens), against 256,000 for Grok Build 0.1. Maximum output per response: Qwen3.5 122B-A10B up to 65,536, Qwen3.5 35B-A3B Base up to 65,536, Grok Build 0.1 up to 256,000 tokens.
Which can read images, PDFs, audio or video?
Qwen3.5 122B-A10B accepts text, images and video; Qwen3.5 35B-A3B Base accepts text, images and video; Grok Build 0.1 accepts text, images and PDFs. They handle the same number of input types.
Are any of these open source?
Qwen3.5 122B-A10B and Qwen3.5 35B-A3B Base publishes its weights (Apache-2.0) and can be self-hosted; Grok Build 0.1 is proprietary.
Which is newer?
Grok Build 0.1 is the newest, released Apr 16, 2026. Qwen3.5 35B-A3B Base came out Feb 24, 2026; Qwen3.5 122B-A10B came out Feb 23, 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 Nov 2, 2026.
