MiniMax-M2 vs GPT-5.1 Codex mini vs Qwen3-VL Plus
Too close to call on our weighted score (GPT-5.1 Codex mini 59, Qwen3-VL Plus 56, MiniMax-M2 48). The right pick depends on what you value most.
MiniMaxMiniMax-M2
48/100- ECI—
- Price$0.30 / $1.20
- Context205K
OpenAIGPT-5.1 Codex mini
59/100- ECI—
- Price$0.25 / $2.00
- Context400K
Alibaba (Qwen)Qwen3-VL Plus
56/100- ECI—
- Price$0.20 / $1.60
- Context262K
Too close to call
It is close. Our weighted score puts them within 2 points (GPT-5.1 Codex mini 59/100, Qwen3-VL Plus 56/100, MiniMax-M2 48/100), so choose by what matters most for your work: MiniMax-M2 on price and GPT-5.1 Codex mini for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceMiniMax-M2MiniMax-M2 $0.525 · Qwen3-VL Plus $0.55 · GPT-5.1 Codex mini $0.688 per 1M tokens (3:1 blend)
- Longest contextGPT-5.1 Codex miniGPT-5.1 Codex mini 400,000 · Qwen3-VL Plus 262,144 · MiniMax-M2 204,800 tokens
- Widest inputsGPT-5.1 Codex mini and Qwen3-VL PlusMiniMax-M2: Text · GPT-5.1 Codex mini: Text, Images · Qwen3-VL Plus: Text, Images
- Self-hostingMiniMax-M2Publishes downloadable weights
| Measure | Weight | MiniMax-M2 | GPT-5.1 Codex mini | Qwen3-VL Plus |
|---|---|---|---|---|
| Price | 50% | 63 | 58 | 62 |
| Inputs & features | 30% | 35 | 70 | 60 |
| Context window | 20% | 32 | 44 | 37 |
| Overall | 100% | 48/100 | 59/100 | 56/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | MiniMax-M2MiniMax | GPT-5.1 Codex miniOpenAI | Qwen3-VL PlusAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 | $0.25 | $0.20 (best) |
| Output | $1.20 (best) | $2.00 | $1.60 |
| Cached input | — | — | — |
| Blended (3:1) | $0.525 (best) | $0.688 | $0.55 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official MiniMax (minimax.io) API | Median of 10 providers | Official Alibaba API |
| Limits | |||
| Context window | 204,800 tokens | 400,000 tokens (best) | 262,144 tokens |
| Max output | 131,072 tokens (best) | 128,000 tokens | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | MiniMax-M2 | — | qwen3-vl-plus |
| API providers | 13 (best) | 10 | 6 |
| Released | Oct 27, 2025 | Nov 13, 2025 | Sep 23, 2025 |
| Knowledge cutoff | — | Sep 30, 2024 | 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.
- MiniMax-M2$5.40
- GPT-5.1 Codex mini$6.50
- Qwen3-VL Plus$5.20
Which should you choose?
Which is better: MiniMax-M2, GPT-5.1 Codex mini or Qwen3-VL Plus?
It is close. Our weighted score puts them within 2 points (GPT-5.1 Codex mini 59/100, Qwen3-VL Plus 56/100, MiniMax-M2 48/100), so choose by what matters most for your work: MiniMax-M2 on price and GPT-5.1 Codex mini for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, MiniMax-M2, GPT-5.1 Codex mini or Qwen3-VL Plus?
MiniMax-M2 is cheaper at $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price). Qwen3-VL Plus costs $0.20 input / $1.60 output per million tokens (official Alibaba API price); GPT-5.1 Codex mini costs $0.25 input / $2.00 output per million tokens (median across 10 API providers). At a typical mix of three input tokens to one output token, that is $0.525 per million tokens for MiniMax-M2 versus $0.55 for Qwen3-VL Plus (1× as much) and $0.688 for GPT-5.1 Codex mini (1.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MiniMax-M2 has not been scored yet, GPT-5.1 Codex mini has not been scored yet and Qwen3-VL Plus has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MiniMax-M2, GPT-5.1 Codex mini and Qwen3-VL Plus yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
GPT-5.1 Codex mini has the largest context window at 400,000 tokens, against 262,144 for Qwen3-VL Plus and 204,800 for MiniMax-M2. Maximum output per response: MiniMax-M2 up to 131,072, GPT-5.1 Codex mini up to 128,000, Qwen3-VL Plus up to 32,768 tokens.
Which can read images, PDFs, audio or video?
MiniMax-M2 accepts text; GPT-5.1 Codex mini accepts text and images; Qwen3-VL Plus accepts text and images. GPT-5.1 Codex mini handles the widest range of inputs.
Are any of these open source?
MiniMax-M2 publishes its weights and can be self-hosted; GPT-5.1 Codex mini and Qwen3-VL Plus is proprietary.
Which is newer?
GPT-5.1 Codex mini is the newest, released Nov 13, 2025. MiniMax-M2 came out Oct 27, 2025; Qwen3-VL Plus came out Sep 23, 2025. Knowledge cutoff: GPT-5.1 Codex mini Sep 30, 2024, Qwen3-VL 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.
