Codestral vs o4-mini-deep-research vs Qwen2.5-VL 7B Instruct
o4-mini-deep-research comes out ahead, 49 to 40 and 29 on our weighted score.
Mistral AICodestral
29/100- ECI—
- Price$0.30 / $0.90
- Context256K
- Our pick
OpenAIo4-mini-deep-research
49/100- ECI—
- Price—
- Context200K
Alibaba (Qwen)Qwen2.5-VL 7B Instruct
40/100- ECI—
- Price$0.35 / $1.05
- Context131K
o4-mini-deep-research is our pick
o4-mini-deep-research is the better all-round choice, scoring 49/100 against Qwen2.5-VL 7B Instruct (40) and Codestral (29). It leads on inputs & features. Codestral wins on context window. 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 priceCodestralCodestral $0.45 · Qwen2.5-VL 7B Instruct $0.525 per 1M tokens (3:1 blend) · o4-mini-deep-research unpriced
- Longest contextCodestralCodestral 256,000 · o4-mini-deep-research 200,000 · Qwen2.5-VL 7B Instruct 131,072 tokens
- Widest inputso4-mini-deep-research and Qwen2.5-VL 7B InstructCodestral: Text · o4-mini-deep-research: Text, Images · Qwen2.5-VL 7B Instruct: Text, Images
- Self-hostingCodestral and Qwen2.5-VL 7B InstructPublishes downloadable weights
| Measure | Weight | Codestral | o4-mini-deep-research | Qwen2.5-VL 7B Instruct |
|---|---|---|---|---|
| Inputs & features | 60% | 25 | 60 | 50 |
| Context window | 40% | 36 | 32 | 24 |
| Overall | 100% | 29/100 | 49/100 | 40/100 |
Left out because at least one model lacks the data: capability and price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | CodestralMistral AI | o4-mini-deep-researchOpenAI | Qwen2.5-VL 7B InstructAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 (best) | — | $0.35 |
| Output | $0.90 (best) | — | $1.05 |
| Cached input | $0.03 | — | — |
| Blended (3:1) | $0.45 (best) | — | $0.525 |
| Long-context rate | Same rate | — | Same rate |
| Price source | Official Mistral API | — | Official Alibaba API |
| Limits | |||
| Context window | 256,000 tokens (best) | 200,000 tokens | 131,072 tokens |
| Max output | 4,096 tokens | 100,000 tokens (best) | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | codestral-latest | — | qwen2-5-vl-7b-instruct |
| API providers | 3 (best) | — | 1 |
| Released | May 29, 2024 | Jun 26, 2024 | Sep 2024 |
| Knowledge cutoff | Oct 2024 | May 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
- o4-mini-deep-research—
- Qwen2.5-VL 7B Instruct$5.60
Which should you choose?
Which is better: Codestral, o4-mini-deep-research or Qwen2.5-VL 7B Instruct?
o4-mini-deep-research is the better all-round choice, scoring 49/100 against Qwen2.5-VL 7B Instruct (40) and Codestral (29). It leads on inputs & features. Codestral wins on context window. 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, o4-mini-deep-research or Qwen2.5-VL 7B Instruct?
Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). Qwen2.5-VL 7B Instruct costs $0.35 input / $1.05 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Codestral versus $0.525 for Qwen2.5-VL 7B Instruct (1.2× as much). o4-mini-deep-research has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Codestral has not been scored yet, o4-mini-deep-research has not been scored yet and Qwen2.5-VL 7B Instruct has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Codestral, o4-mini-deep-research and Qwen2.5-VL 7B 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 200,000 for o4-mini-deep-research and 131,072 for Qwen2.5-VL 7B Instruct. Maximum output per response: Codestral up to 4,096, o4-mini-deep-research up to 100,000, Qwen2.5-VL 7B Instruct up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Codestral accepts text; o4-mini-deep-research accepts text and images; Qwen2.5-VL 7B Instruct accepts text and images. o4-mini-deep-research handles the widest range of inputs.
Are any of these open source?
Codestral and Qwen2.5-VL 7B Instruct publishes its weights and can be self-hosted; o4-mini-deep-research is proprietary.
Which is newer?
Qwen2.5-VL 7B Instruct is the newest, released Sep 2024. o4-mini-deep-research came out Jun 26, 2024; Codestral came out May 29, 2024. Knowledge cutoff: Codestral Oct 2024, o4-mini-deep-research May 2024, Qwen2.5-VL 7B Instruct Apr 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.
