GPT-5.4 mini vs MiniMax-M2.7 vs Qwen3.6 35B-A3B
Qwen3.6 35B-A3B comes out ahead, 68 to 63 and 61 on our weighted score, though MiniMax-M2.7 is 6% cheaper per token.
OpenAIGPT-5.4 mini
63/100- ECI148.8
- Price$0.75 / $4.50
- Context400K
MiniMaxMiniMax-M2.7
61/100- ECI145.9
- Price$0.30 / $1.20
- Context205K
- Our pick
Alibaba (Qwen)Qwen3.6 35B-A3B
68/100- ECI143.9
- Price$0.248 / $1.49
- Context262K
Qwen3.6 35B-A3B is our pick
Qwen3.6 35B-A3B is the better all-round choice, scoring 68/100 against GPT-5.4 mini (63) and MiniMax-M2.7 (61). It leads on inputs & features. GPT-5.4 mini wins on capability and context window. 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 · MiniMax-M2.7 145.9 · Qwen3.6 35B-A3B 143.9
- Lowest priceMiniMax-M2.7MiniMax-M2.7 $0.525 · Qwen3.6 35B-A3B $0.557 · GPT-5.4 mini $1.69 per 1M tokens (3:1 blend)
- Longest contextGPT-5.4 miniGPT-5.4 mini 400,000 · Qwen3.6 35B-A3B 262,144 · MiniMax-M2.7 204,800 tokens
- Widest inputsQwen3.6 35B-A3BGPT-5.4 mini: Text, Images · MiniMax-M2.7: Text · Qwen3.6 35B-A3B: Text, Images, Audio, Video
- Self-hostingMiniMax-M2.7 and Qwen3.6 35B-A3BPublishes downloadable weights
| Measure | Weight | GPT-5.4 mini | MiniMax-M2.7 | Qwen3.6 35B-A3B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 77 | 73 | 70 |
| Price | 25% | 39 | 63 | 62 |
| Inputs & features | 15% | 70 | 35 | 90 |
| Context window | 10% | 44 | 32 | 37 |
| Overall | 100% | 63/100 | 61/100 | 68/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GPT-5.4 miniOpenAI | MiniMax-M2.7MiniMax | Qwen3.6 35B-A3BAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 148.8 (best) | 145.9 | 143.9 |
| ECI rank | #56 of 148 (best) | #73 of 148 | #83 of 148 |
| GPQA DiamondGraduate-level science questions | 86.9% (best) | — | 84.9% |
| FrontierMath Tiers 1–3Research-level mathematics | 51.2% (best) | — | 20.4% |
| OTIS Mock AIME 2024–2025Competition mathematics | 88.9% (best) | — | 86.7% |
| SimpleQA VerifiedShort factual questions | 29.4% | — | — |
| Price per million tokens | |||
| Input | $0.75 | $0.30 | $0.248 (best) |
| Output | $4.50 | $1.20 (best) | $1.49 |
| Cached input | $0.075 | $0.06 (best) | — |
| Blended (3:1) | $1.69 | $0.525 (best) | $0.557 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Official MiniMax (minimax.io) API | Official Alibaba API |
| Limits | |||
| Context window | 400,000 tokens (best) | 204,800 tokens | 262,144 tokens |
| Max output | 128,000 tokens | 131,072 tokens (best) | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | Yes |
| Video | No | No | Yes |
| Reasoning | Yeslow · medium · high · xhigh | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | gpt-5.4-mini | MiniMax-M2.7 | qwen3.6-35b-a3b |
| API providers | 29 | 29 | 34 (best) |
| Released | Mar 17, 2026 | Mar 18, 2026 | Apr 17, 2026 |
| Knowledge cutoff | 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.
- GPT-5.4 mini$16.50
- MiniMax-M2.7$5.40
- Qwen3.6 35B-A3B$5.45
Which should you choose?
Which is better: GPT-5.4 mini, MiniMax-M2.7 or Qwen3.6 35B-A3B?
Qwen3.6 35B-A3B is the better all-round choice, scoring 68/100 against GPT-5.4 mini (63) and MiniMax-M2.7 (61). It leads on inputs & features. GPT-5.4 mini wins on capability and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GPT-5.4 mini, MiniMax-M2.7 or Qwen3.6 35B-A3B?
MiniMax-M2.7 is cheaper at $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price). Qwen3.6 35B-A3B costs $0.248 input / $1.49 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-M2.7 versus $0.557 for Qwen3.6 35B-A3B (1.1× 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), MiniMax-M2.7 145.9 (#73 of 148) and Qwen3.6 35B-A3B 143.9 (#83 of 148). The confidence ranges of the top two overlap (147.1–150.5 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 GPT-5.4 mini, MiniMax-M2.7 and Qwen3.6 35B-A3B 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?
GPT-5.4 mini has the largest context window at 400,000 tokens, against 262,144 for Qwen3.6 35B-A3B and 204,800 for MiniMax-M2.7. Maximum output per response: GPT-5.4 mini up to 128,000, MiniMax-M2.7 up to 131,072, Qwen3.6 35B-A3B up to 65,536 tokens.
Which can read images, PDFs, audio or video?
GPT-5.4 mini accepts text and images; MiniMax-M2.7 accepts text; Qwen3.6 35B-A3B accepts text, images, audio and video. Qwen3.6 35B-A3B handles the widest range of inputs.
Are any of these open source?
MiniMax-M2.7 and Qwen3.6 35B-A3B publishes its weights and can be self-hosted; GPT-5.4 mini is proprietary.
Which is newer?
Qwen3.6 35B-A3B is the newest, released Apr 17, 2026. MiniMax-M2.7 came out Mar 18, 2026; GPT-5.4 mini came out Mar 17, 2026. Knowledge cutoff: 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.
