MiniMax-M2.7 vs Qwen3.6 Max Preview vs GPT-5.4 nano
GPT-5.4 nano comes out ahead, 68 to 61 and 54 on our weighted score, and it is the cheaper option too.
MiniMax
MiniMax-M2.7
61/100- ECI145.9
- Price$0.30 / $1.20
- Context205K
Alibaba (Qwen)
Qwen3.6 Max Preview
54/100- ECI149.2
- Price$1.30 / $7.80
- Context262K
- Our pick
OpenAI
GPT-5.4 nano
68/100- ECI145.8
- Price$0.20 / $1.25
- Context400K
GPT-5.4 nano is our pick
GPT-5.4 nano is the better all-round choice, scoring 68/100 against MiniMax-M2.7 (61) and Qwen3.6 Max Preview (54). It leads on price, inputs & features and context window. Qwen3.6 Max Preview wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityQwen3.6 Max PreviewCapabilities Index (ECI): Qwen3.6 Max Preview 149.2 · MiniMax-M2.7 145.9 · GPT-5.4 nano 145.8
- Lowest priceGPT-5.4 nanoGPT-5.4 nano $0.463 · MiniMax-M2.7 $0.525 · Qwen3.6 Max Preview $2.92 per 1M tokens (3:1 blend)
- Longest contextGPT-5.4 nanoGPT-5.4 nano 400,000 · Qwen3.6 Max Preview 262,144 · MiniMax-M2.7 204,800 tokens
- Widest inputsGPT-5.4 nanoMiniMax-M2.7: Text · Qwen3.6 Max Preview: Text · GPT-5.4 nano: Text, Images
- Self-hostingMiniMax-M2.7Publishes downloadable weights
| Measure | Weight | MiniMax-M2.7 | Qwen3.6 Max Preview | GPT-5.4 nano |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 73 | 77 | 73 |
| Price | 25% | 63 | 28 | 66 |
| Inputs & features | 15% | 35 | 35 | 70 |
| Context window | 10% | 32 | 37 | 44 |
| Overall | 100% | 61/100 | 54/100 | 68/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 145.9 | 149.2 (best) | 145.8 |
| ECI rank | #73 of 148 | #54 of 148 (best) | #75 of 148 |
| GPQA DiamondGraduate-level science questions | — | 87.4% (best) | 78.5% |
| FrontierMath Tiers 1–3Research-level mathematics | — | — | 44.9% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 91.1% (best) | 87.8% |
| SWE-bench VerifiedFixing real GitHub issues | — | 76.7% | — |
| SimpleQA VerifiedShort factual questions | — | 52.0% (best) | 11.7% |
| Price per million tokens | |||
| Input | $0.30 | $1.30 | $0.20 (best) |
| Output | $1.20 (best) | $7.80 | $1.25 |
| Cached input | $0.06 | $0.13 | $0.02 (best) |
| Blended (3:1) | $0.525 | $2.92 | $0.463 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official MiniMax (minimax.io) API | Official Alibaba API | Official OpenAI API |
| Limits | |||
| Context window | 204,800 tokens | 262,144 tokens | 400,000 tokens (best) |
| Max output | 131,072 tokens (best) | 65,536 tokens | 128,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | Yeslow · medium · high · xhigh |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | MiniMax-M2.7 | qwen3.6-max-preview | gpt-5.4-nano |
| API providers | 29 (best) | 10 | 26 |
| Released | Mar 18, 2026 | Apr 20, 2026 | Mar 17, 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.
MiniMax-M2.7$5.40
Qwen3.6 Max Preview$28.60
GPT-5.4 nano$4.50
Which should you choose?
Which is better: MiniMax-M2.7, Qwen3.6 Max Preview or GPT-5.4 nano?
GPT-5.4 nano is the better all-round choice, scoring 68/100 against MiniMax-M2.7 (61) and Qwen3.6 Max Preview (54). It leads on price, inputs & features and context window. Qwen3.6 Max Preview wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, MiniMax-M2.7, Qwen3.6 Max Preview or GPT-5.4 nano?
GPT-5.4 nano is cheaper at $0.20 input / $1.25 output per million tokens (official OpenAI API price). MiniMax-M2.7 costs $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price); Qwen3.6 Max Preview costs $1.30 input / $7.80 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.463 per million tokens for GPT-5.4 nano versus $0.525 for MiniMax-M2.7 (1.1× as much) and $2.92 for Qwen3.6 Max Preview (6.3× as much).
Which scores higher on benchmarks?
Qwen3.6 Max Preview scores higher on the Capabilities Index (ECI): Qwen3.6 Max Preview 149.2 (#54 of 148), MiniMax-M2.7 145.9 (#73 of 148) and GPT-5.4 nano 145.8 (#75 of 148). The confidence ranges of the top two overlap (147.6–152.0 vs 138.2–148.0), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for MiniMax-M2.7 and GPT-5.4 nano yet, so there is no like-for-like coding score. On overall capability, Qwen3.6 Max Preview 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?
GPT-5.4 nano has the largest context window at 400,000 tokens, against 262,144 for Qwen3.6 Max Preview and 204,800 for MiniMax-M2.7. Maximum output per response: MiniMax-M2.7 up to 131,072, Qwen3.6 Max Preview up to 65,536, GPT-5.4 nano up to 128,000 tokens.
Which can read images, PDFs, audio or video?
MiniMax-M2.7 accepts text; Qwen3.6 Max Preview accepts text; GPT-5.4 nano accepts text and images. GPT-5.4 nano handles the widest range of inputs.
Are any of these open source?
MiniMax-M2.7 publishes its weights and can be self-hosted; Qwen3.6 Max Preview and GPT-5.4 nano is proprietary.
Which is newer?
Qwen3.6 Max Preview is the newest, released Apr 20, 2026. MiniMax-M2.7 came out Mar 18, 2026; GPT-5.4 nano came out Mar 17, 2026. Knowledge cutoff: Qwen3.6 Max Preview Apr 2025, GPT-5.4 nano 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.