Codestral vs Qwen-VL Plus vs Qwen2.5-Coder-32B-Instruct
No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.
Price in rating: Excluded · Include price
Mistral AI
Codestral
38/100- ECI—
- Price$0.30 / $0.90
- Context256K
Alibaba (Qwen)
Qwen-VL Plus
43/100- ECI—
- Price$0.21 / $0.63
- Context131K
Alibaba (Qwen)
Qwen2.5-Coder-32B-Instruct
28/100- ECI—
- Price$0.66 / $1.00
- Context131K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Qwen-VL Plus 43/100, Codestral 38/100, Qwen2.5-Coder-32B-Instruct 28/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. 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 priceQwen-VL PlusQwen-VL Plus $0.315 · Codestral $0.45 · Qwen2.5-Coder-32B-Instruct $0.745 per 1M tokens (3:1 blend)
- Longest contextCodestralCodestral 256,000 · Qwen-VL Plus 131,072 · Qwen2.5-Coder-32B-Instruct 131,072 tokens
- Widest inputsQwen-VL PlusCodestral: Text · Qwen-VL Plus: Text, Images · Qwen2.5-Coder-32B-Instruct: Text
- Self-hostingCodestral and Qwen2.5-Coder-32B-InstructPublishes downloadable weights
| Measure | Weight | Codestral | Qwen-VL Plus | Qwen2.5-Coder-32B-Instruct |
|---|---|---|---|---|
| Inputs & features | 60% | 35 | 50 | 25 |
| Context window | 40% | 43 | 32 | 32 |
| Specs only | 100% | 38/100 | 43/100 | 28/100 |
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) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 | $0.21 (best) | $0.66 |
| Output | $0.90 | $0.63 (best) | $1.00 |
| Cached input | $0.03 | — | — |
| Blended (3:1) | $0.45 | $0.315 (best) | $0.745 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Official Alibaba API | Median of 7 providers |
| Limits | |||
| Context window | 256,000 tokens (best) | 131,072 tokens | 131,072 tokens |
| Max output | 4,096 tokens | 8,192 tokens (best) | 8,192 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | codestral-latest | qwen-vl-plus | — |
| API providers | 4 | 1 | 7 (best) |
| Released | May 29, 2024 | Jan 25, 2024 | Nov 12, 2024 |
| Knowledge cutoff | Oct 2024 | Apr 2024 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Codestral$4.80
Qwen-VL Plus$3.36
Qwen2.5-Coder-32B-Instruct$8.60
Which should you choose?
Which is better: Codestral, Qwen-VL Plus or Qwen2.5-Coder-32B-Instruct?
There is not enough shared capability evidence to name an overall winner. The scores (Qwen-VL Plus 43/100, Codestral 38/100, Qwen2.5-Coder-32B-Instruct 28/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Codestral, Qwen-VL Plus or Qwen2.5-Coder-32B-Instruct?
Qwen-VL Plus is cheaper at $0.21 input / $0.63 output per million tokens (official Alibaba API price). Codestral costs $0.30 input / $0.90 output per million tokens (official Mistral API price); Qwen2.5-Coder-32B-Instruct costs $0.66 input / $1.00 output per million tokens (median across 7 API providers). At a typical mix of three input tokens to one output token, that is $0.315 per million tokens for Qwen-VL Plus versus $0.45 for Codestral (1.4× as much) and $0.745 for Qwen2.5-Coder-32B-Instruct (2.4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Codestral has not been scored yet, Qwen-VL Plus has not been scored yet and Qwen2.5-Coder-32B-Instruct has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Codestral, Qwen-VL Plus and Qwen2.5-Coder-32B-Instruct 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?
Codestral has the largest context window at 256,000 tokens, against 131,072 for Qwen-VL Plus and 131,072 for Qwen2.5-Coder-32B-Instruct. Maximum output per response: Codestral up to 4,096, Qwen-VL Plus up to 8,192, Qwen2.5-Coder-32B-Instruct up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Codestral accepts text; Qwen-VL Plus accepts text and images; Qwen2.5-Coder-32B-Instruct accepts text. Qwen-VL Plus handles the widest range of inputs.
Are any of these open source?
Codestral and Qwen2.5-Coder-32B-Instruct publishes its weights and can be self-hosted; Qwen-VL Plus is proprietary.
Which is newer?
Qwen2.5-Coder-32B-Instruct is the newest, released Nov 12, 2024. Codestral came out May 29, 2024; Qwen-VL Plus came out Jan 25, 2024. Knowledge cutoff: Codestral Oct 2024, Qwen-VL Plus Apr 2024.
How do you decide the winner?
This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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 Nov 18, 2026.