Qwen3.5 Plus vs GPT-5.4 mini vs MiniMax-M2.5
Qwen3.5 Plus comes out ahead, 66 to 63 and 61 on our weighted score, though MiniMax-M2.5 is 42% cheaper per token.
- Our pick
Alibaba (Qwen)Qwen3.5 Plus
66/100- ECI146.8
- Price$0.40 / $2.40
- Context1M
OpenAIGPT-5.4 mini
63/100- ECI148.8
- Price$0.75 / $4.50
- Context400K
MiniMaxMiniMax-M2.5
61/100- ECI146.7
- Price$0.30 / $1.20
- Context205K
Qwen3.5 Plus is our pick
Qwen3.5 Plus is the better all-round choice, scoring 66/100 against GPT-5.4 mini (63) and MiniMax-M2.5 (61). It leads on context window. GPT-5.4 mini wins on capability. MiniMax-M2.5 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGPT-5.4 miniCapabilities Index (ECI): GPT-5.4 mini 148.8 · Qwen3.5 Plus 146.8 · MiniMax-M2.5 146.7
- Lowest priceMiniMax-M2.5MiniMax-M2.5 $0.525 · Qwen3.5 Plus $0.90 · GPT-5.4 mini $1.69 per 1M tokens (3:1 blend)
- Longest contextQwen3.5 PlusQwen3.5 Plus 1,000,000 · GPT-5.4 mini 400,000 · MiniMax-M2.5 204,800 tokens
- Widest inputsQwen3.5 PlusQwen3.5 Plus: Text, Images, Video · GPT-5.4 mini: Text, Images · MiniMax-M2.5: Text
- Self-hostingMiniMax-M2.5Publishes downloadable weights
| Measure | Weight | Qwen3.5 Plus | GPT-5.4 mini | MiniMax-M2.5 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 74 | 77 | 74 |
| Price | 25% | 52 | 39 | 63 |
| Inputs & features | 15% | 70 | 70 | 35 |
| Context window | 10% | 60 | 44 | 32 |
| Overall | 100% | 66/100 | 63/100 | 61/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Qwen3.5 PlusAlibaba (Qwen) | GPT-5.4 miniOpenAI | MiniMax-M2.5MiniMax |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 146.8 | 148.8 (best) | 146.7 |
| ECI rank | #65 of 148 | #56 of 148 (best) | #66 of 148 |
| GPQA DiamondGraduate-level science questions | 84.9% | 86.9% (best) | — |
| FrontierMath Tiers 1–3Research-level mathematics | — | 51.2% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 86.7% | 88.9% (best) | — |
| SimpleQA VerifiedShort factual questions | 25.4% | 29.4% (best) | — |
| Price per million tokens | |||
| Input | $0.40 | $0.75 | $0.30 (best) |
| Output | $2.40 | $4.50 | $1.20 (best) |
| Cached input | — | $0.075 | $0.03 (best) |
| Blended (3:1) | $0.90 | $1.69 | $0.525 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Alibaba API | Official OpenAI API | Official MiniMax (minimax.io) API |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 400,000 tokens | 204,800 tokens |
| Max output | 65,536 tokens | 128,000 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 | No | No |
| Reasoning | Yes | Yeslow · medium · high · xhigh | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Open |
| API model ID | qwen3.5-plus | gpt-5.4-mini | MiniMax-M2.5 |
| API providers | 10 | 29 (best) | 21 |
| Released | Feb 16, 2026 | Mar 17, 2026 | Feb 12, 2026 |
| Knowledge cutoff | Apr 2025 | Aug 31, 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
- GPT-5.4 mini$16.50
- MiniMax-M2.5$5.40
Which should you choose?
Which is better: Qwen3.5 Plus, GPT-5.4 mini or MiniMax-M2.5?
Qwen3.5 Plus is the better all-round choice, scoring 66/100 against GPT-5.4 mini (63) and MiniMax-M2.5 (61). It leads on context window. GPT-5.4 mini wins on capability. MiniMax-M2.5 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Qwen3.5 Plus, GPT-5.4 mini 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); GPT-5.4 mini costs $0.75 input / $4.50 output per million tokens (official OpenAI 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 $1.69 for GPT-5.4 mini (3.2× as much).
Which scores higher on benchmarks?
GPT-5.4 mini scores higher on the Capabilities Index (ECI): GPT-5.4 mini 148.8 (#56 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 (147.1–150.5 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, GPT-5.4 mini and MiniMax-M2.5 yet, so there is no like-for-like coding score. On overall capability, GPT-5.4 mini 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 has the largest context window at 1,000,000 tokens, against 400,000 for GPT-5.4 mini and 204,800 for MiniMax-M2.5. Maximum output per response: Qwen3.5 Plus up to 65,536, GPT-5.4 mini up to 128,000, MiniMax-M2.5 up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Qwen3.5 Plus accepts text, images and video; GPT-5.4 mini accepts text and images; 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 GPT-5.4 mini is proprietary.
Which is newer?
GPT-5.4 mini is the newest, released Mar 17, 2026. Qwen3.5 Plus came out Feb 16, 2026; MiniMax-M2.5 came out Feb 12, 2026. Knowledge cutoff: Qwen3.5 Plus Apr 2025, GPT-5.4 mini Aug 31, 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.
