MiniMax-M2 Her vs Qwen3.5 35B-A3B Base vs DeepSeek OCR 2
Too close to call on our weighted score (Qwen3.5 35B-A3B Base 45, MiniMax-M2 Her 43, DeepSeek OCR 2 38). The right pick depends on what you value most.
MiniMaxMiniMax-M2 Her
43/100- ECI—
- Price$0.30 / $1.20
- Context66K
Alibaba (Qwen)Qwen3.5 35B-A3B Base
45/100- ECI—
- Price$0.54 / $1.33
- Context262K
DeepSeekDeepSeek OCR 2
38/100- ECI—
- Price$0.46 / $0.749
- Context8K
Too close to call
It is close. Our weighted score puts them within 1 points (Qwen3.5 35B-A3B Base 45/100, MiniMax-M2 Her 43/100, DeepSeek OCR 2 38/100), so choose by what matters most for your work: MiniMax-M2 Her on price and Qwen3.5 35B-A3B Base 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 HerMiniMax-M2 Her $0.525 · DeepSeek OCR 2 $0.532 · Qwen3.5 35B-A3B Base $0.739 per 1M tokens (3:1 blend)
- Longest contextQwen3.5 35B-A3B BaseQwen3.5 35B-A3B Base 262,144 · MiniMax-M2 Her 65,536 · DeepSeek OCR 2 8,192 tokens
- Widest inputsQwen3.5 35B-A3B BaseMiniMax-M2 Her: Text · Qwen3.5 35B-A3B Base: Text, Images, Video · DeepSeek OCR 2: Text, Images
- Self-hostingQwen3.5 35B-A3B Base and DeepSeek OCR 2Publishes downloadable weights (Apache-2.0)
| Measure | Weight | MiniMax-M2 Her | Qwen3.5 35B-A3B Base | DeepSeek OCR 2 |
|---|---|---|---|---|
| Price | 50% | 60 | 54 | 60 |
| Inputs & features | 30% | 35 | 35 | 25 |
| Context window | 20% | 12 | 37 | 0 |
| Overall | 100% | 43/100 | 45/100 | 38/100 |
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 | MiniMax-M2 HerMiniMax | Qwen3.5 35B-A3B BaseAlibaba (Qwen) | DeepSeek OCR 2DeepSeek |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 (best) | $0.54 | $0.46 |
| Output | $1.20 | $1.33 | $0.749 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.525 (best) | $0.739 | $0.532 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 3 providers | Median of 1 providers | Median of 2 providers |
| Limits | |||
| Context window | 65,536 tokens | 262,144 tokens (best) | 8,192 tokens |
| Max output | 2,048 tokens | 65,536 tokens (best) | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | Yes | No | No |
| Tool calling | Yes | No | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | OpenApache-2.0 | Open |
| API model ID | — | — | — |
| API providers | 3 (best) | 1 | 3 (best) |
| Released | Jan 23, 2026 | Feb 24, 2026 | Jan 27, 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.
- MiniMax-M2 Her$5.40
- Qwen3.5 35B-A3B Base$8.07
- DeepSeek OCR 2$6.10
Which should you choose?
Which is better: MiniMax-M2 Her, Qwen3.5 35B-A3B Base or DeepSeek OCR 2?
It is close. Our weighted score puts them within 1 points (Qwen3.5 35B-A3B Base 45/100, MiniMax-M2 Her 43/100, DeepSeek OCR 2 38/100), so choose by what matters most for your work: MiniMax-M2 Her on price and Qwen3.5 35B-A3B Base 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, MiniMax-M2 Her, Qwen3.5 35B-A3B Base or DeepSeek OCR 2?
MiniMax-M2 Her is cheaper at $0.30 input / $1.20 output per million tokens (median across 3 API providers). DeepSeek OCR 2 costs $0.46 input / $0.749 output per million tokens (median across 2 API providers); Qwen3.5 35B-A3B Base costs $0.54 input / $1.33 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.525 per million tokens for MiniMax-M2 Her versus $0.532 for DeepSeek OCR 2 (1× as much) and $0.739 for Qwen3.5 35B-A3B Base (1.4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MiniMax-M2 Her has not been scored yet, Qwen3.5 35B-A3B Base has not been scored yet and DeepSeek OCR 2 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MiniMax-M2 Her, Qwen3.5 35B-A3B Base and DeepSeek OCR 2 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 and DeepSeek OCR 2 does not support tool calling, which most coding agents need.
Which has the bigger context window?
Qwen3.5 35B-A3B Base has the largest context window at 262,144 tokens, against 65,536 for MiniMax-M2 Her and 8,192 for DeepSeek OCR 2. Maximum output per response: MiniMax-M2 Her up to 2,048, Qwen3.5 35B-A3B Base up to 65,536, DeepSeek OCR 2 up to 8,192 tokens.
Which can read images, PDFs, audio or video?
MiniMax-M2 Her accepts text; Qwen3.5 35B-A3B Base accepts text, images and video; DeepSeek OCR 2 accepts text and images. Qwen3.5 35B-A3B Base handles the widest range of inputs.
Are any of these open source?
Qwen3.5 35B-A3B Base and DeepSeek OCR 2 publishes its weights (Apache-2.0) and can be self-hosted; MiniMax-M2 Her is proprietary.
Which is newer?
Qwen3.5 35B-A3B Base is the newest, released Feb 24, 2026. DeepSeek OCR 2 came out Jan 27, 2026; MiniMax-M2 Her came out Jan 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.
