Mistral Medium 3.1 vs Qwen3 VL 235B A22B Thinking vs GLM-4.5V
Too close to call on our weighted score (Mistral Medium 3.1 50, GLM-4.5V 49, Qwen3 VL 235B A22B Thinking 48). The right pick depends on what you value most.
Mistral AIMistral Medium 3.1
50/100- ECI—
- Price$0.40 / $2.00
- Context262K
Alibaba (Qwen)Qwen3 VL 235B A22B Thinking
48/100- ECI—
- Price$0.40 / $4.00
- Context131K
Z.ai (Zhipu)GLM-4.5V
49/100- ECI—
- Price$0.60 / $1.80
- Context64K
Too close to call
It is close. Our weighted score puts them within a point (Mistral Medium 3.1 50/100, GLM-4.5V 49/100, Qwen3 VL 235B A22B Thinking 48/100), so choose by what matters most for your work: Mistral Medium 3.1 on price and Mistral Medium 3.1 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 priceMistral Medium 3.1Mistral Medium 3.1 $0.80 · GLM-4.5V $0.90 · Qwen3 VL 235B A22B Thinking $1.30 per 1M tokens (3:1 blend)
- Longest contextMistral Medium 3.1Mistral Medium 3.1 262,144 · Qwen3 VL 235B A22B Thinking 131,072 · GLM-4.5V 64,000 tokens
- Widest inputsGLM-4.5VMistral Medium 3.1: Text, Images · Qwen3 VL 235B A22B Thinking: Text, Images · GLM-4.5V: Text, Images, Video
- Self-hostingQwen3 VL 235B A22B Thinking and GLM-4.5VPublishes downloadable weights
| Measure | Weight | Mistral Medium 3.1 | Qwen3 VL 235B A22B Thinking | GLM-4.5V |
|---|---|---|---|---|
| Price | 50% | 54 | 44 | 52 |
| Inputs & features | 30% | 50 | 70 | 70 |
| Context window | 20% | 37 | 24 | 12 |
| Overall | 100% | 50/100 | 48/100 | 49/100 |
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 | Mistral Medium 3.1Mistral AI | Qwen3 VL 235B A22B ThinkingAlibaba (Qwen) | GLM-4.5VZ.ai (Zhipu) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.40 (best) | $0.40 (best) | $0.60 |
| Output | $2.00 | $4.00 | $1.80 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.80 (best) | $1.30 | $0.90 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Median of 9 providers | Official Z.AI API |
| Limits | |||
| Context window | 262,144 tokens (best) | 131,072 tokens | 64,000 tokens |
| Max output | 262,144 tokens (best) | 32,768 tokens | 16,384 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | No | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | mistral-medium-2508 | — | glm-4.5v |
| API providers | 1 | 9 | 11 (best) |
| Released | Aug 12, 2025 | Sep 23, 2025 | Aug 11, 2025 |
| Knowledge cutoff | May 2025 | Mar 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.
- Mistral Medium 3.1$8.00
- Qwen3 VL 235B A22B Thinking$12.00
- GLM-4.5V$9.60
Which should you choose?
Which is better: Mistral Medium 3.1, Qwen3 VL 235B A22B Thinking or GLM-4.5V?
It is close. Our weighted score puts them within a point (Mistral Medium 3.1 50/100, GLM-4.5V 49/100, Qwen3 VL 235B A22B Thinking 48/100), so choose by what matters most for your work: Mistral Medium 3.1 on price and Mistral Medium 3.1 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, Mistral Medium 3.1, Qwen3 VL 235B A22B Thinking or GLM-4.5V?
Mistral Medium 3.1 is cheaper at $0.40 input / $2.00 output per million tokens (official Mistral API price). GLM-4.5V costs $0.60 input / $1.80 output per million tokens (official Z.AI 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 $0.80 per million tokens for Mistral Medium 3.1 versus $0.90 for GLM-4.5V (1.1× as much) and $1.30 for Qwen3 VL 235B A22B Thinking (1.6× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Mistral Medium 3.1 has not been scored yet, Qwen3 VL 235B A22B Thinking has not been scored yet and GLM-4.5V has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Mistral Medium 3.1, Qwen3 VL 235B A22B Thinking and GLM-4.5V 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?
Mistral Medium 3.1 has the largest context window at 262,144 tokens, against 131,072 for Qwen3 VL 235B A22B Thinking and 64,000 for GLM-4.5V. Maximum output per response: Mistral Medium 3.1 up to 262,144, Qwen3 VL 235B A22B Thinking up to 32,768, GLM-4.5V up to 16,384 tokens.
Which can read images, PDFs, audio or video?
Mistral Medium 3.1 accepts text and images; Qwen3 VL 235B A22B Thinking accepts text and images; GLM-4.5V accepts text, images and video. GLM-4.5V handles the widest range of inputs.
Are any of these open source?
Qwen3 VL 235B A22B Thinking and GLM-4.5V publishes its weights and can be self-hosted; Mistral Medium 3.1 is proprietary.
Which is newer?
Qwen3 VL 235B A22B Thinking is the newest, released Sep 23, 2025. Mistral Medium 3.1 came out Aug 12, 2025; GLM-4.5V came out Aug 11, 2025. Knowledge cutoff: Mistral Medium 3.1 May 2025, Qwen3 VL 235B A22B Thinking Mar 31, 2025, GLM-4.5V 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.
