Qwen3 VL 235B A22B Instruct vs MiniMax-M2 vs GPT-5.1 Codex mini
GPT-5.1 Codex mini comes out ahead, 59 to 53 and 48 on our weighted score, though MiniMax-M2 is 24% cheaper per token.
Alibaba (Qwen)Qwen3 VL 235B A22B Instruct
53/100- ECI—
- Price$0.30 / $1.55
- Context131K
MiniMaxMiniMax-M2
48/100- ECI—
- Price$0.30 / $1.20
- Context205K
- Our pick
OpenAIGPT-5.1 Codex mini
59/100- ECI—
- Price$0.25 / $2.00
- Context400K
GPT-5.1 Codex mini is our pick
GPT-5.1 Codex mini is the better all-round choice, scoring 59/100 against Qwen3 VL 235B A22B Instruct (53) and MiniMax-M2 (48). It leads on inputs & features and context window. MiniMax-M2 wins on price. 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 235B A22B Instruct $0.613 · 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 · MiniMax-M2 204,800 · Qwen3 VL 235B A22B Instruct 131,072 tokens
- Widest inputsQwen3 VL 235B A22B Instruct and GPT-5.1 Codex miniQwen3 VL 235B A22B Instruct: Text, Images · MiniMax-M2: Text · GPT-5.1 Codex mini: Text, Images
- Self-hostingQwen3 VL 235B A22B Instruct and MiniMax-M2Publishes downloadable weights
| Measure | Weight | Qwen3 VL 235B A22B Instruct | MiniMax-M2 | GPT-5.1 Codex mini |
|---|---|---|---|---|
| Price | 50% | 60 | 63 | 58 |
| Inputs & features | 30% | 60 | 35 | 70 |
| Context window | 20% | 24 | 32 | 44 |
| Overall | 100% | 53/100 | 48/100 | 59/100 |
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 | Qwen3 VL 235B A22B InstructAlibaba (Qwen) | MiniMax-M2MiniMax | GPT-5.1 Codex miniOpenAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 | $0.30 | $0.25 (best) |
| Output | $1.55 | $1.20 (best) | $2.00 |
| Cached input | — | — | — |
| Blended (3:1) | $0.613 | $0.525 (best) | $0.688 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 12 providers | Official MiniMax (minimax.io) API | Median of 10 providers |
| Limits | |||
| Context window | 131,072 tokens | 204,800 tokens | 400,000 tokens (best) |
| Max output | 32,768 tokens | 131,072 tokens (best) | 128,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | — | MiniMax-M2 | — |
| API providers | 12 | 13 (best) | 10 |
| Released | Sep 23, 2025 | Oct 27, 2025 | Nov 13, 2025 |
| Knowledge cutoff | Mar 31, 2025 | — | Sep 30, 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Qwen3 VL 235B A22B Instruct$6.10
- MiniMax-M2$5.40
- GPT-5.1 Codex mini$6.50
Which should you choose?
Which is better: Qwen3 VL 235B A22B Instruct, MiniMax-M2 or GPT-5.1 Codex mini?
GPT-5.1 Codex mini is the better all-round choice, scoring 59/100 against Qwen3 VL 235B A22B Instruct (53) and MiniMax-M2 (48). It leads on inputs & features and context window. MiniMax-M2 wins on price. 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, Qwen3 VL 235B A22B Instruct, MiniMax-M2 or GPT-5.1 Codex mini?
MiniMax-M2 is cheaper at $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price). Qwen3 VL 235B A22B Instruct costs $0.30 input / $1.55 output per million tokens (median across 12 API providers); 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 $0.613 for Qwen3 VL 235B A22B Instruct (1.2× 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. Qwen3 VL 235B A22B Instruct has not been scored yet, MiniMax-M2 has not been scored yet and GPT-5.1 Codex mini has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3 VL 235B A22B Instruct, MiniMax-M2 and GPT-5.1 Codex mini 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 204,800 for MiniMax-M2 and 131,072 for Qwen3 VL 235B A22B Instruct. Maximum output per response: Qwen3 VL 235B A22B Instruct up to 32,768, MiniMax-M2 up to 131,072, GPT-5.1 Codex mini up to 128,000 tokens.
Which can read images, PDFs, audio or video?
Qwen3 VL 235B A22B Instruct accepts text and images; MiniMax-M2 accepts text; GPT-5.1 Codex mini accepts text and images. Qwen3 VL 235B A22B Instruct handles the widest range of inputs.
Are any of these open source?
Qwen3 VL 235B A22B Instruct and MiniMax-M2 publishes its weights and can be self-hosted; GPT-5.1 Codex mini 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 235B A22B Instruct came out Sep 23, 2025. Knowledge cutoff: Qwen3 VL 235B A22B Instruct Mar 31, 2025, GPT-5.1 Codex mini Sep 30, 2024.
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.
