Qwen3.7 Plus vs Qwen3.8 2.4T A95B vs MiniMax-M3
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Alibaba (Qwen)
Qwen3.7 Plus
64/100- ECI148.0
- Price$0.40 / $1.60
- Context1M
Alibaba (Qwen)
Qwen3.8 2.4T A95B
32/100- ECI—
- Price$2.00 / $6.00
- Context262K
MiniMax
MiniMax-M3
64/100- ECI147.9
- Price$0.30 / $1.20
- Context1.05M
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.7 Plus 64/100, MiniMax-M3 64/100, Qwen3.8 2.4T A95B 32/100) compare the available specifications and 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 priceMiniMax-M3MiniMax-M3 $0.525 · Qwen3.7 Plus $0.70 · Qwen3.8 2.4T A95B $3.00 per 1M tokens (3:1 blend)
- Longest contextMiniMax-M3MiniMax-M3 1,048,576 · Qwen3.7 Plus 1,000,000 · Qwen3.8 2.4T A95B 262,144 tokens
- Widest inputsQwen3.7 Plus and MiniMax-M3Qwen3.7 Plus: Text, Images, Video · Qwen3.8 2.4T A95B: Text · MiniMax-M3: Text, Images, Video
- Self-hostingQwen3.8 2.4T A95B and MiniMax-M3Publishes downloadable weights (qwen3.8-max)
| Measure | Weight | Qwen3.7 Plus | Qwen3.8 2.4T A95B | MiniMax-M3 |
|---|---|---|---|---|
| Price | 50% | 55 | 26 | 60 |
| Inputs & features | 30% | 80 | 35 | 70 |
| Context window | 20% | 64 | 43 | 65 |
| Specs & price only | 100% | 64/100 | 32/100 | 64/100 |
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 | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 148.0 (best) | — | 147.9 |
| ECI rank | #75 of 158 (best) | — | #77 of 158 |
| GPQA DiamondGraduate-level science questions | 87.9% | — | 90.9% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 34.4% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 93.3% (best) | — | 71.1% |
| Price per million tokens | |||
| Input | $0.40 | $2.00 | $0.30 (best) |
| Output | $1.60 | $6.00 | $1.20 (best) |
| Cached input | $0.08 | — | $0.06 (best) |
| Blended (3:1) | $0.70 | $3.00 | $0.525 (best) |
| Long-context rate | Over 256K: $1.20 / $4.80 | Same rate | Over 512K: $0.60 / $2.40 |
| Price source | Official Alibaba API | Median of 26 providers | Official MiniMax (minimax.io) API |
| Limits | |||
| Context window | 1,000,000 tokens | 262,144 tokens | 1,048,576 tokens (best) |
| Max output | 64,000 tokens | 131,072 tokens | 512,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | Yes | No | Yes |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | Openqwen3.8-max | Open |
| API model ID | qwen3.7-plus | — | MiniMax-M3 |
| API providers | 28 | 26 | 52 (best) |
| Released | Jun 2, 2026 | Aug 12, 2026 | Jun 1, 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.
Qwen3.7 Plus$7.20
Qwen3.8 2.4T A95B$32.00
MiniMax-M3$5.40
Which should you choose?
Which is better: Qwen3.7 Plus, Qwen3.8 2.4T A95B or MiniMax-M3?
There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.7 Plus 64/100, MiniMax-M3 64/100, Qwen3.8 2.4T A95B 32/100) compare the available specifications and 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, Qwen3.7 Plus, Qwen3.8 2.4T A95B or MiniMax-M3?
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); Qwen3.8 2.4T A95B costs $2.00 input / $6.00 output per million tokens (median across 26 API providers). 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 $3.00 for Qwen3.8 2.4T A95B (5.7× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Qwen3.7 Plus has an ECI of 148.0, Qwen3.8 2.4T A95B has not been scored yet and MiniMax-M3 has an ECI of 147.9.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3.7 Plus, Qwen3.8 2.4T A95B and MiniMax-M3 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?
MiniMax-M3 has the largest context window at 1,048,576 tokens, against 1,000,000 for Qwen3.7 Plus and 262,144 for Qwen3.8 2.4T A95B. Maximum output per response: Qwen3.7 Plus up to 64,000, Qwen3.8 2.4T A95B up to 131,072, MiniMax-M3 up to 512,000 tokens.
Which can read images, PDFs, audio or video?
Qwen3.7 Plus accepts text, images and video; Qwen3.8 2.4T A95B accepts text; MiniMax-M3 accepts text, images and video. Qwen3.7 Plus handles the widest range of inputs.
Are any of these open source?
Qwen3.8 2.4T A95B and MiniMax-M3 publishes its weights (qwen3.8-max) and can be self-hosted; Qwen3.7 Plus is proprietary.
Which is newer?
Qwen3.8 2.4T A95B is the newest, released Aug 12, 2026. Qwen3.7 Plus came out Jun 2, 2026; MiniMax-M3 came out Jun 1, 2026. Knowledge cutoff: Qwen3.7 Plus Apr 2025.
How do you decide the winner?
This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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 18, 2026.