Qwen3.5 Plus vs Qwen3.6 Plus vs MiniMax-M2.5
Too close to call on our weighted score (Qwen3.5 Plus 66, Qwen3.6 Plus 66, MiniMax-M2.5 61). The right pick depends on what you value most.
Alibaba (Qwen)
Qwen3.5 Plus
66/100- ECI146.8
- Price$0.40 / $2.40
- Context1M
Alibaba (Qwen)
Qwen3.6 Plus
66/100- ECI147.6
- Price$0.50 / $3.00
- Context1M
MiniMax
MiniMax-M2.5
61/100- ECI146.7
- Price$0.30 / $1.20
- Context205K
Too close to call
It is close. Our weighted score puts them within a point (Qwen3.5 Plus 66/100, Qwen3.6 Plus 66/100, MiniMax-M2.5 61/100), so choose by what matters most for your work: Qwen3.6 Plus for raw capability and MiniMax-M2.5 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityQwen3.6 PlusCapabilities Index (ECI): Qwen3.6 Plus 147.6 · Qwen3.5 Plus 146.8 · MiniMax-M2.5 146.7
- Lowest priceMiniMax-M2.5MiniMax-M2.5 $0.525 · Qwen3.5 Plus $0.90 · Qwen3.6 Plus $1.13 per 1M tokens (3:1 blend)
- Longest contextQwen3.5 Plus and Qwen3.6 PlusQwen3.5 Plus 1,000,000 · Qwen3.6 Plus 1,000,000 · MiniMax-M2.5 204,800 tokens
- Widest inputsQwen3.5 Plus and Qwen3.6 PlusQwen3.5 Plus: Text, Images, Video · Qwen3.6 Plus: Text, Images, Video · MiniMax-M2.5: Text
- Self-hostingMiniMax-M2.5Publishes downloadable weights
| Measure | Weight | Qwen3.5 Plus | Qwen3.6 Plus | MiniMax-M2.5 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 74 | 75 | 74 |
| Price | 25% | 52 | 47 | 63 |
| Inputs & features | 15% | 70 | 70 | 35 |
| Context window | 10% | 60 | 60 | 32 |
| Overall | 100% | 66/100 | 66/100 | 61/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 146.8 | 147.6 (best) | 146.7 |
| ECI rank | #65 of 148 | #59 of 148 (best) | #66 of 148 |
| GPQA DiamondGraduate-level science questions | 84.9% | 88.4% (best) | — |
| FrontierMath Tiers 1–3Research-level mathematics | — | 38.3% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 86.7% | 93.3% (best) | — |
| SWE-bench VerifiedFixing real GitHub issues | — | 57.9% | — |
| SimpleQA VerifiedShort factual questions | 25.4% | 44.1% (best) | — |
| Price per million tokens | |||
| Input | $0.40 | $0.50 | $0.30 (best) |
| Output | $2.40 | $3.00 | $1.20 (best) |
| Cached input | — | $0.05 | $0.03 (best) |
| Blended (3:1) | $0.90 | $1.13 | $0.525 (best) |
| Long-context rate | Same rate | Over 256K: $2.00 / $6.00 | Same rate |
| Price source | Official Alibaba API | Official Alibaba API | Official MiniMax (minimax.io) API |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 1,000,000 tokens (best) | 204,800 tokens |
| Max output | 65,536 tokens | 65,536 tokens | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | Yes | Yes | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Open |
| API model ID | qwen3.5-plus | qwen3.6-plus | MiniMax-M2.5 |
| API providers | 10 | 18 | 21 (best) |
| Released | Feb 16, 2026 | Apr 2, 2026 | Feb 12, 2026 |
| Knowledge cutoff | Apr 2025 | 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.
Qwen3.5 Plus$8.80
Qwen3.6 Plus$11.00
MiniMax-M2.5$5.40
Which should you choose?
Which is better: Qwen3.5 Plus, Qwen3.6 Plus or MiniMax-M2.5?
It is close. Our weighted score puts them within a point (Qwen3.5 Plus 66/100, Qwen3.6 Plus 66/100, MiniMax-M2.5 61/100), so choose by what matters most for your work: Qwen3.6 Plus for raw capability and MiniMax-M2.5 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Qwen3.5 Plus, Qwen3.6 Plus or MiniMax-M2.5?
MiniMax-M2.5 is cheaper at $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price). Qwen3.5 Plus costs $0.40 input / $2.40 output per million tokens (official Alibaba API price); Qwen3.6 Plus costs $0.50 input / $3.00 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.525 per million tokens for MiniMax-M2.5 versus $0.90 for Qwen3.5 Plus (1.7× as much) and $1.13 for Qwen3.6 Plus (2.1× as much).
Which scores higher on benchmarks?
Qwen3.6 Plus scores higher on the Capabilities Index (ECI): Qwen3.6 Plus 147.6 (#59 of 148), Qwen3.5 Plus 146.8 (#65 of 148) and MiniMax-M2.5 146.7 (#66 of 148). The confidence ranges of the top two overlap (145.4–149.3 vs 144.6–148.1), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3.5 Plus and MiniMax-M2.5 yet, so there is no like-for-like coding score. On overall capability, Qwen3.6 Plus leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Qwen3.5 Plus and Qwen3.6 Plus have the largest context windows (1,000,000 and 1,000,000 tokens), against 204,800 for MiniMax-M2.5. Maximum output per response: Qwen3.5 Plus up to 65,536, Qwen3.6 Plus up to 65,536, MiniMax-M2.5 up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Qwen3.5 Plus accepts text, images and video; Qwen3.6 Plus accepts text, images and video; MiniMax-M2.5 accepts text. Qwen3.5 Plus handles the widest range of inputs.
Are any of these open source?
MiniMax-M2.5 publishes its weights and can be self-hosted; Qwen3.5 Plus and Qwen3.6 Plus is proprietary.
Which is newer?
Qwen3.6 Plus is the newest, released Apr 2, 2026. Qwen3.5 Plus came out Feb 16, 2026; MiniMax-M2.5 came out Feb 12, 2026. Knowledge cutoff: Qwen3.5 Plus Apr 2025, Qwen3.6 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.