GPT-5.1 Codex mini vs Qwen3 VL 235B A22B Thinking vs Mistral Large 3
GPT-5.1 Codex mini comes out ahead, 59 to 50 and 48 on our weighted score, and it is the cheaper option too.
- Our pick
OpenAIGPT-5.1 Codex mini
59/100- ECI—
- Price$0.25 / $2.00
- Context400K
Alibaba (Qwen)Qwen3 VL 235B A22B Thinking
48/100- ECI—
- Price$0.40 / $4.00
- Context131K
Mistral AIMistral Large 3
50/100- ECI—
- Price$0.50 / $1.50
- Context262K
GPT-5.1 Codex mini is our pick
GPT-5.1 Codex mini is the better all-round choice, scoring 59/100 against Mistral Large 3 (50) and Qwen3 VL 235B A22B Thinking (48). It leads on price and context window. 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 priceGPT-5.1 Codex miniGPT-5.1 Codex mini $0.688 · Mistral Large 3 $0.75 · Qwen3 VL 235B A22B Thinking $1.30 per 1M tokens (3:1 blend)
- Longest contextGPT-5.1 Codex miniGPT-5.1 Codex mini 400,000 · Mistral Large 3 262,144 · Qwen3 VL 235B A22B Thinking 131,072 tokens
- Widest inputsSame inputsGPT-5.1 Codex mini: Text, Images · Qwen3 VL 235B A22B Thinking: Text, Images · Mistral Large 3: Text, Images
- Self-hostingQwen3 VL 235B A22B Thinking and Mistral Large 3Publishes downloadable weights
| Measure | Weight | GPT-5.1 Codex mini | Qwen3 VL 235B A22B Thinking | Mistral Large 3 |
|---|---|---|---|---|
| Price | 50% | 58 | 44 | 56 |
| Inputs & features | 30% | 70 | 70 | 50 |
| Context window | 20% | 44 | 24 | 37 |
| Overall | 100% | 59/100 | 48/100 | 50/100 |
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 | GPT-5.1 Codex miniOpenAI | Qwen3 VL 235B A22B ThinkingAlibaba (Qwen) | Mistral Large 3Mistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.25 (best) | $0.40 | $0.50 |
| Output | $2.00 | $4.00 | $1.50 (best) |
| Cached input | — | — | $0.05 |
| Blended (3:1) | $0.688 (best) | $1.30 | $0.75 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 10 providers | Median of 9 providers | Official Mistral API |
| Limits | |||
| Context window | 400,000 tokens (best) | 131,072 tokens | 262,144 tokens |
| Max output | 128,000 tokens | 32,768 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | — | — | mistral-large-2512 |
| API providers | 10 | 9 | 13 (best) |
| Released | Nov 13, 2025 | Sep 23, 2025 | Dec 2, 2025 |
| Knowledge cutoff | Sep 30, 2024 | Mar 31, 2025 | Nov 2024 |
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 Codex mini$6.50
- Qwen3 VL 235B A22B Thinking$12.00
- Mistral Large 3$8.00
Which should you choose?
Which is better: GPT-5.1 Codex mini, Qwen3 VL 235B A22B Thinking or Mistral Large 3?
GPT-5.1 Codex mini is the better all-round choice, scoring 59/100 against Mistral Large 3 (50) and Qwen3 VL 235B A22B Thinking (48). It leads on price and context window. 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, GPT-5.1 Codex mini, Qwen3 VL 235B A22B Thinking or Mistral Large 3?
GPT-5.1 Codex mini is cheaper at $0.25 input / $2.00 output per million tokens (median across 10 API providers). Mistral Large 3 costs $0.50 input / $1.50 output per million tokens (official Mistral API price); Qwen3 VL 235B A22B Thinking costs $0.40 input / $4.00 output per million tokens (median across 9 API providers). At a typical mix of three input tokens to one output token, that is $0.688 per million tokens for GPT-5.1 Codex mini versus $0.75 for Mistral Large 3 (1.1× as much) and $1.30 for Qwen3 VL 235B A22B Thinking (1.9× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. GPT-5.1 Codex mini has not been scored yet, Qwen3 VL 235B A22B Thinking has not been scored yet and Mistral Large 3 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-5.1 Codex mini, Qwen3 VL 235B A22B Thinking and Mistral Large 3 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 Mistral Large 3 and 131,072 for Qwen3 VL 235B A22B Thinking. Maximum output per response: GPT-5.1 Codex mini up to 128,000, Qwen3 VL 235B A22B Thinking up to 32,768, Mistral Large 3 up to 262,144 tokens.
Which can read images, PDFs, audio or video?
GPT-5.1 Codex mini accepts text and images; Qwen3 VL 235B A22B Thinking accepts text and images; Mistral Large 3 accepts text and images. They handle the same number of input types.
Are any of these open source?
Qwen3 VL 235B A22B Thinking and Mistral Large 3 publishes its weights and can be self-hosted; GPT-5.1 Codex mini is proprietary.
Which is newer?
Mistral Large 3 is the newest, released Dec 2, 2025. GPT-5.1 Codex mini came out Nov 13, 2025; Qwen3 VL 235B A22B Thinking came out Sep 23, 2025. Knowledge cutoff: GPT-5.1 Codex mini Sep 30, 2024, Qwen3 VL 235B A22B Thinking Mar 31, 2025, Mistral Large 3 Nov 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.
