GPT-5.1 vs GPT-5.4 mini vs Qwen3.6 Max Preview
GPT-5.4 mini comes out ahead, 63 to 60 and 54 on our weighted score, and it is the cheaper option too.
OpenAIGPT-5.1
60/100- ECI149.7
- Price$1.25 / $10.00
- Context400K
- Our pickOpenAI
GPT-5.4 mini
63/100- ECI148.8
- Price$0.75 / $4.50
- Context400K
Alibaba (Qwen)Qwen3.6 Max Preview
54/100- ECI149.2
- Price$1.30 / $7.80
- Context262K
GPT-5.4 mini is our pick
GPT-5.4 mini is the better all-round choice, scoring 63/100 against GPT-5.1 (60) and Qwen3.6 Max Preview (54). It leads on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGPT-5.1Capabilities Index (ECI): GPT-5.1 149.7 · Qwen3.6 Max Preview 149.2 · GPT-5.4 mini 148.8
- Lowest priceGPT-5.4 miniGPT-5.4 mini $1.69 · Qwen3.6 Max Preview $2.92 · GPT-5.1 $3.44 per 1M tokens (3:1 blend)
- Longest contextGPT-5.1 and GPT-5.4 miniGPT-5.1 400,000 · GPT-5.4 mini 400,000 · Qwen3.6 Max Preview 262,144 tokens
- Widest inputsGPT-5.1 and GPT-5.4 miniGPT-5.1: Text, Images · GPT-5.4 mini: Text, Images · Qwen3.6 Max Preview: Text
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | GPT-5.1 | GPT-5.4 mini | Qwen3.6 Max Preview |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 78 | 77 | 77 |
| Price | 25% | 24 | 39 | 28 |
| Inputs & features | 15% | 70 | 70 | 35 |
| Context window | 10% | 44 | 44 | 37 |
| Overall | 100% | 60/100 | 63/100 | 54/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GPT-5.1OpenAI | GPT-5.4 miniOpenAI | Qwen3.6 Max PreviewAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 149.7 (best) | 148.8 | 149.2 |
| ECI rank | #52 of 148 (best) | #56 of 148 | #54 of 148 |
| GPQA DiamondGraduate-level science questions | 87.6% (best) | 86.9% | 87.4% |
| FrontierMath Tiers 1–3Research-level mathematics | — | 51.2% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 88.6% | 88.9% | 91.1% (best) |
| SWE-bench VerifiedFixing real GitHub issues | 68.0% | — | 76.7% (best) |
| SimpleQA VerifiedShort factual questions | 48.0% | 29.4% | 52.0% (best) |
| Price per million tokens | |||
| Input | $1.25 | $0.75 (best) | $1.30 |
| Output | $10.00 | $4.50 (best) | $7.80 |
| Cached input | $0.125 | $0.075 (best) | $0.13 |
| Blended (3:1) | $3.44 | $1.69 (best) | $2.92 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Official OpenAI API | Official Alibaba API |
| Limits | |||
| Context window | 400,000 tokens (best) | 400,000 tokens (best) | 262,144 tokens |
| Max output | 128,000 tokens (best) | 128,000 tokens (best) | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yeslow · medium · high | Yeslow · medium · high · xhigh | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | gpt-5.1 | gpt-5.4-mini | qwen3.6-max-preview |
| API providers | 21 | 29 (best) | 10 |
| Released | Nov 13, 2025 | Mar 17, 2026 | Apr 20, 2026 |
| Knowledge cutoff | Sep 30, 2024 | Aug 31, 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.
- GPT-5.1$32.50
- GPT-5.4 mini$16.50
- Qwen3.6 Max Preview$28.60
Which should you choose?
Which is better: GPT-5.1, GPT-5.4 mini or Qwen3.6 Max Preview?
GPT-5.4 mini is the better all-round choice, scoring 63/100 against GPT-5.1 (60) and Qwen3.6 Max Preview (54). It leads on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GPT-5.1, GPT-5.4 mini or Qwen3.6 Max Preview?
GPT-5.4 mini is cheaper at $0.75 input / $4.50 output per million tokens (official OpenAI API price). Qwen3.6 Max Preview costs $1.30 input / $7.80 output per million tokens (official Alibaba API price); GPT-5.1 costs $1.25 input / $10.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $1.69 per million tokens for GPT-5.4 mini versus $2.92 for Qwen3.6 Max Preview (1.7× as much) and $3.44 for GPT-5.1 (2× as much).
Which scores higher on benchmarks?
GPT-5.1 scores higher on the Capabilities Index (ECI): GPT-5.1 149.7 (#52 of 148), Qwen3.6 Max Preview 149.2 (#54 of 148) and GPT-5.4 mini 148.8 (#56 of 148). The confidence ranges of the top two overlap (148.3–151.1 vs 147.6–152.0), so treat the gap as small. On individual benchmarks: GPQA Diamond — GPT-5.1 87.6%, Qwen3.6 Max Preview 87.4%, GPT-5.4 mini 86.9%; OTIS Mock AIME 2024–2025 — Qwen3.6 Max Preview 91.1%, GPT-5.4 mini 88.9%, GPT-5.1 88.6%; SimpleQA Verified — Qwen3.6 Max Preview 52.0%, GPT-5.1 48.0%, GPT-5.4 mini 29.4%.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-5.4 mini yet, so there is no like-for-like coding score. On overall capability, GPT-5.1 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-5.1 and GPT-5.4 mini have the largest context windows (400,000 and 400,000 tokens), against 262,144 for Qwen3.6 Max Preview. Maximum output per response: GPT-5.1 up to 128,000, GPT-5.4 mini up to 128,000, Qwen3.6 Max Preview up to 65,536 tokens.
Which can read images, PDFs, audio or video?
GPT-5.1 accepts text and images; GPT-5.4 mini accepts text and images; Qwen3.6 Max Preview accepts text. GPT-5.1 handles the widest range of inputs.
Are any of these open source?
No. GPT-5.1, GPT-5.4 mini and Qwen3.6 Max Preview are proprietary and only available through APIs and apps.
Which is newer?
Qwen3.6 Max Preview is the newest, released Apr 20, 2026. GPT-5.4 mini came out Mar 17, 2026; GPT-5.1 came out Nov 13, 2025. Knowledge cutoff: GPT-5.1 Sep 30, 2024, GPT-5.4 mini Aug 31, 2025, Qwen3.6 Max Preview 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.
