Qwen3-Coder 30B-A3B Instruct vs Mistral Medium 3 vs GLM-4.5V
Too close to call on our weighted score (GLM-4.5V 49, Mistral Medium 3 47, Qwen3-Coder 30B-A3B Instruct 41). The right pick depends on what you value most.
Alibaba (Qwen)
Qwen3-Coder 30B-A3B Instruct
41/100- ECI—
- Price$0.45 / $2.25
- Context262K
Mistral AI
Mistral Medium 3
47/100- ECI134.1
- Price$0.40 / $2.00
- 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 2 points (GLM-4.5V 49/100, Mistral Medium 3 47/100, Qwen3-Coder 30B-A3B Instruct 41/100), so choose by what matters most for your work: Mistral Medium 3 on price and Qwen3-Coder 30B-A3B Instruct 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 3Mistral Medium 3 $0.80 · Qwen3-Coder 30B-A3B Instruct $0.90 · GLM-4.5V $0.90 per 1M tokens (3:1 blend)
- Longest contextQwen3-Coder 30B-A3B InstructQwen3-Coder 30B-A3B Instruct 262,144 · Mistral Medium 3 131,072 · GLM-4.5V 64,000 tokens
- Widest inputsGLM-4.5VQwen3-Coder 30B-A3B Instruct: Text · Mistral Medium 3: Text, Images · GLM-4.5V: Text, Images, Video
- Self-hostingQwen3-Coder 30B-A3B Instruct and GLM-4.5VPublishes downloadable weights
| Measure | Weight | Qwen3-Coder 30B-A3B Instruct | Mistral Medium 3 | GLM-4.5V |
|---|---|---|---|---|
| Price | 50% | 52 | 54 | 52 |
| Inputs & features | 30% | 25 | 50 | 70 |
| Context window | 20% | 37 | 24 | 12 |
| Overall | 100% | 41/100 | 47/100 | 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 | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 134.1 | — |
| ECI rank | — | #117 of 148 | — |
| GPQA DiamondGraduate-level science questions | — | 59.5% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 32.2% | — |
| Price per million tokens | |||
| Input | $0.45 | $0.40 (best) | $0.60 |
| Output | $2.25 | $2.00 | $1.80 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.90 | $0.80 (best) | $0.90 |
| Long-context rate | Over 32K: $0.75 / $3.75 | Same rate | Same rate |
| Price source | Official Alibaba API | Official Mistral API | Official Z.AI API |
| Limits | |||
| Context window | 262,144 tokens (best) | 131,072 tokens | 64,000 tokens |
| Max output | 65,536 tokens | 131,072 tokens (best) | 16,384 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | No | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | qwen3-coder-30b-a3b-instruct | mistral-medium-2505 | glm-4.5v |
| API providers | 13 (best) | 5 | 11 |
| Released | Apr 2025 | May 7, 2025 | Aug 11, 2025 |
| Knowledge cutoff | Apr 2025 | May 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.
Qwen3-Coder 30B-A3B Instruct$9.00
Mistral Medium 3$8.00
GLM-4.5V$9.60
Which should you choose?
Which is better: Qwen3-Coder 30B-A3B Instruct, Mistral Medium 3 or GLM-4.5V?
It is close. Our weighted score puts them within 2 points (GLM-4.5V 49/100, Mistral Medium 3 47/100, Qwen3-Coder 30B-A3B Instruct 41/100), so choose by what matters most for your work: Mistral Medium 3 on price and Qwen3-Coder 30B-A3B Instruct 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, Qwen3-Coder 30B-A3B Instruct, Mistral Medium 3 or GLM-4.5V?
Mistral Medium 3 is cheaper at $0.40 input / $2.00 output per million tokens (official Mistral API price). Qwen3-Coder 30B-A3B Instruct costs $0.45 input / $2.25 output per million tokens (official Alibaba API price); GLM-4.5V costs $0.60 input / $1.80 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $0.80 per million tokens for Mistral Medium 3 versus $0.90 for Qwen3-Coder 30B-A3B Instruct (1.1× as much) and $0.90 for GLM-4.5V (1.1× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Qwen3-Coder 30B-A3B Instruct has not been scored yet, Mistral Medium 3 has an ECI of 134.1 and GLM-4.5V has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3-Coder 30B-A3B Instruct, Mistral Medium 3 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?
Qwen3-Coder 30B-A3B Instruct has the largest context window at 262,144 tokens, against 131,072 for Mistral Medium 3 and 64,000 for GLM-4.5V. Maximum output per response: Qwen3-Coder 30B-A3B Instruct up to 65,536, Mistral Medium 3 up to 131,072, GLM-4.5V up to 16,384 tokens.
Which can read images, PDFs, audio or video?
Qwen3-Coder 30B-A3B Instruct accepts text; Mistral Medium 3 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-Coder 30B-A3B Instruct and GLM-4.5V publishes its weights and can be self-hosted; Mistral Medium 3 is proprietary.
Which is newer?
GLM-4.5V is the newest, released Aug 11, 2025. Mistral Medium 3 came out May 7, 2025; Qwen3-Coder 30B-A3B Instruct came out Apr 2025. Knowledge cutoff: Qwen3-Coder 30B-A3B Instruct Apr 2025, Mistral Medium 3 May 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.