DeepSeek OCR 2 vs MiniMax-M3 vs Qwen3.7 Plus
Too close to call on our weighted score (MiniMax-M3 65, Qwen3.7 Plus 65, DeepSeek OCR 2 32). The right pick depends on what you value most.
DeepSeekDeepSeek OCR 2
32/100- ECI—
- Price$0.89 / $1.47
- Context8K
MiniMaxMiniMax-M3
65/100- ECI147.0
- Price$0.30 / $1.20
- Context1.05M
Alibaba (Qwen)Qwen3.7 Plus
65/100- ECI147.4
- Price$0.40 / $1.60
- Context1M
Too close to call
It is close. Our weighted score puts them within a point (MiniMax-M3 65/100, Qwen3.7 Plus 65/100, DeepSeek OCR 2 32/100), so choose by what matters most for your work: MiniMax-M3 on price and MiniMax-M3 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-M3MiniMax-M3 $0.525 · Qwen3.7 Plus $0.70 · DeepSeek OCR 2 $1.03 per 1M tokens (3:1 blend)
- Longest contextMiniMax-M3MiniMax-M3 1,048,576 · Qwen3.7 Plus 1,000,000 · DeepSeek OCR 2 8,192 tokens
- Widest inputsMiniMax-M3 and Qwen3.7 PlusDeepSeek OCR 2: Text, Images · MiniMax-M3: Text, Images, Video · Qwen3.7 Plus: Text, Images, Video
- Self-hostingDeepSeek OCR 2 and MiniMax-M3Publishes downloadable weights
| Measure | Weight | DeepSeek OCR 2 | MiniMax-M3 | Qwen3.7 Plus |
|---|---|---|---|---|
| Price | 50% | 49 | 63 | 57 |
| Inputs & features | 30% | 25 | 70 | 80 |
| Context window | 20% | 0 | 61 | 60 |
| Overall | 100% | 32/100 | 65/100 | 65/100 |
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 | DeepSeek OCR 2DeepSeek | MiniMax-M3MiniMax | Qwen3.7 PlusAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 147.0 | 147.4 (best) |
| ECI rank | — | #62 of 148 | #61 of 148 (best) |
| GPQA DiamondGraduate-level science questions | — | 90.9% (best) | 87.9% |
| FrontierMath Tiers 1–3Research-level mathematics | — | — | 34.4% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 71.1% | 93.3% (best) |
| Price per million tokens | |||
| Input | $0.89 | $0.30 (best) | $0.40 |
| Output | $1.47 | $1.20 (best) | $1.60 |
| Cached input | — | $0.06 | $0.04 (best) |
| Blended (3:1) | $1.03 | $0.525 (best) | $0.70 |
| Long-context rate | Same rate | Over 512K: $0.60 / $2.40 | Over 256K: $1.20 / $4.80 |
| Price source | Median of 1 providers | Official MiniMax (minimax.io) API | Official Alibaba API |
| Limits | |||
| Context window | 8,192 tokens | 1,048,576 tokens (best) | 1,000,000 tokens |
| Max output | 8,192 tokens | 512,000 tokens (best) | 64,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | Yes | Yes |
| Reasoning | No | Yes | Yes |
| Tool calling | No | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | — | MiniMax-M3 | qwen3.7-plus |
| API providers | 2 | 42 (best) | 25 |
| Released | Jan 27, 2026 | Jun 1, 2026 | Jun 2, 2026 |
| Knowledge cutoff | — | — | Apr 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- DeepSeek OCR 2$11.83
- MiniMax-M3$5.40
- Qwen3.7 Plus$7.20
Which should you choose?
Which is better: DeepSeek OCR 2, MiniMax-M3 or Qwen3.7 Plus?
It is close. Our weighted score puts them within a point (MiniMax-M3 65/100, Qwen3.7 Plus 65/100, DeepSeek OCR 2 32/100), so choose by what matters most for your work: MiniMax-M3 on price and MiniMax-M3 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, DeepSeek OCR 2, MiniMax-M3 or Qwen3.7 Plus?
MiniMax-M3 is cheaper at $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price). Qwen3.7 Plus costs $0.40 input / $1.60 output per million tokens (official Alibaba API price); DeepSeek OCR 2 costs $0.89 input / $1.47 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-M3 versus $0.70 for Qwen3.7 Plus (1.3× as much) and $1.03 for DeepSeek OCR 2 (2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. DeepSeek OCR 2 has not been scored yet, MiniMax-M3 has an ECI of 147.0 and Qwen3.7 Plus has an ECI of 147.4.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek OCR 2, MiniMax-M3 and Qwen3.7 Plus yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that DeepSeek OCR 2 does not support tool calling, which most coding agents need.
Which has the bigger context window?
MiniMax-M3 has the largest context window at 1,048,576 tokens, against 1,000,000 for Qwen3.7 Plus and 8,192 for DeepSeek OCR 2. Maximum output per response: DeepSeek OCR 2 up to 8,192, MiniMax-M3 up to 512,000, Qwen3.7 Plus up to 64,000 tokens.
Which can read images, PDFs, audio or video?
DeepSeek OCR 2 accepts text and images; MiniMax-M3 accepts text, images and video; Qwen3.7 Plus accepts text, images and video. MiniMax-M3 handles the widest range of inputs.
Are any of these open source?
DeepSeek OCR 2 and MiniMax-M3 publishes its weights and can be self-hosted; Qwen3.7 Plus is proprietary.
Which is newer?
Qwen3.7 Plus is the newest, released Jun 2, 2026. MiniMax-M3 came out Jun 1, 2026; DeepSeek OCR 2 came out Jan 27, 2026. Knowledge cutoff: Qwen3.7 Plus Apr 2025.
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.
