Vision Large vs o3-deep-research vs Codestral
Vision Large comes out ahead, 84 to 49 and 29 on our weighted score.
- Our pick
VisparkVision Large
84/100- ECI—
- Price—
- Context1M
OpenAIo3-deep-research
49/100- ECI—
- Price—
- Context200K
Mistral AICodestral
29/100- ECI—
- Price$0.30 / $0.90
- Context256K
Vision Large is our pick
Vision Large is the better all-round choice, scoring 84/100 against o3-deep-research (49) and Codestral (29). It leads on inputs & features and 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 per 1M tokens (3:1 blend) · Vision Large and o3-deep-research unpriced
- Longest contextVision LargeVision Large 1,000,000 · Codestral 256,000 · o3-deep-research 200,000 tokens
- Widest inputsVision LargeVision Large: Text, Images, PDFs, Audio, Video · o3-deep-research: Text, Images · Codestral: Text
- Self-hostingCodestralPublishes downloadable weights
| Measure | Weight | Vision Large | o3-deep-research | Codestral |
|---|---|---|---|---|
| Inputs & features | 60% | 100 | 60 | 25 |
| Context window | 40% | 60 | 32 | 36 |
| Overall | 100% | 84/100 | 49/100 | 29/100 |
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 | Vision LargeVispark | o3-deep-researchOpenAI | CodestralMistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | — | — | $0.30 |
| Output | — | — | $0.90 |
| Cached input | — | — | $0.03 |
| Blended (3:1) | — | — | $0.45 |
| Long-context rate | — | — | Same rate |
| Price source | — | — | Official Mistral API |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 200,000 tokens | 256,000 tokens |
| Max output | 65,536 tokens | 100,000 tokens (best) | 4,096 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | Yes | No | No |
| Audio | Yes | No | No |
| Video | Yes | No | No |
| Reasoning | Yes | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Open |
| API model ID | — | — | codestral-latest |
| API providers | — | — | 3 |
| Released | May 15, 2024 | Jun 26, 2024 | May 29, 2024 |
| Knowledge cutoff | — | May 2024 | Oct 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Vision Large—
- o3-deep-research—
- Codestral$4.80
Which should you choose?
Which is better: Vision Large, o3-deep-research or Codestral?
Vision Large is the better all-round choice, scoring 84/100 against o3-deep-research (49) and Codestral (29). It leads on inputs & features and 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, Vision Large, o3-deep-research or Codestral?
Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). . At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Codestral versus . Vision Large and o3-deep-research has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Vision Large has not been scored yet, o3-deep-research has not been scored yet and Codestral has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Vision Large, o3-deep-research and Codestral 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?
Vision Large has the largest context window at 1,000,000 tokens, against 256,000 for Codestral and 200,000 for o3-deep-research. Maximum output per response: Vision Large up to 65,536, o3-deep-research up to 100,000, Codestral up to 4,096 tokens.
Which can read images, PDFs, audio or video?
Vision Large accepts text, images, PDFs, audio and video; o3-deep-research accepts text and images; Codestral accepts text. Vision Large handles the widest range of inputs.
Are any of these open source?
Codestral publishes its weights and can be self-hosted; Vision Large and o3-deep-research is proprietary.
Which is newer?
o3-deep-research is the newest, released Jun 26, 2024. Codestral came out May 29, 2024; Vision Large came out May 15, 2024. Knowledge cutoff: o3-deep-research May 2024, Codestral Oct 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.
