o3-deep-research vs Gemma 3n E2B IT vs Devstral Medium
o3-deep-research comes out ahead, 49 to 25 and 21 on our weighted score, and it is the cheaper option too.
- Our pick
OpenAIo3-deep-research
49/100- ECI—
- Price$9.00 / $36.00
- Context200K
GoogleGemma 3n E2B IT
21/100- ECI—
- Price—
- Context33K
Mistral AIDevstral Medium
25/100- ECI—
- Price—
- Context128K
o3-deep-research is our pick
o3-deep-research is the better all-round choice, scoring 49/100 against Devstral Medium (25) and Gemma 3n E2B IT (21). 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 priceo3-deep-researcho3-deep-research $15.75 per 1M tokens (3:1 blend) · Gemma 3n E2B IT and Devstral Medium unpriced
- Longest contexto3-deep-researcho3-deep-research 200,000 · Devstral Medium 128,000 · Gemma 3n E2B IT 32,768 tokens
- Widest inputsGemma 3n E2B ITo3-deep-research: Text, Images · Gemma 3n E2B IT: Text, Images, Audio · Devstral Medium: Text
- Self-hostingGemma 3n E2B ITPublishes downloadable weights (Gemma Terms of Use)
| Measure | Weight | o3-deep-research | Gemma 3n E2B IT | Devstral Medium |
|---|---|---|---|---|
| Inputs & features | 60% | 60 | 35 | 25 |
| Context window | 40% | 32 | 0 | 24 |
| Overall | 100% | 49/100 | 21/100 | 25/100 |
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 | o3-deep-researchOpenAI | Gemma 3n E2B ITGoogle | Devstral MediumMistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $9.00 | — | — |
| Output | $36.00 | — | — |
| Cached input | — | — | — |
| Blended (3:1) | $15.75 | — | — |
| Long-context rate | Same rate | — | — |
| Price source | Median of 1 providers | — | — |
| Limits | |||
| Context window | 200,000 tokens (best) | 32,768 tokens | 128,000 tokens |
| Max output | 100,000 tokens | 32,768 tokens | 128,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | No | No |
| Audio | No | Yes | No |
| Video | No | No | No |
| Reasoning | Yes | No | No |
| Tool calling | Yes | No | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | OpenGemma Terms of Use | Proprietary |
| API model ID | — | — | — |
| API providers | 1 | — | — |
| Released | Jun 26, 2025 | Jun 26, 2025 | Jul 10, 2025 |
| Knowledge cutoff | May 2024 | Jun 2024 | May 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- o3-deep-research$162.00
- Gemma 3n E2B IT—
- Devstral Medium—
Which should you choose?
Which is better: o3-deep-research, Gemma 3n E2B IT or Devstral Medium?
o3-deep-research is the better all-round choice, scoring 49/100 against Devstral Medium (25) and Gemma 3n E2B IT (21). 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, o3-deep-research, Gemma 3n E2B IT or Devstral Medium?
o3-deep-research is cheaper at $9.00 input / $36.00 output per million tokens (median across 1 API provider). . At a typical mix of three input tokens to one output token, that is $15.75 per million tokens for o3-deep-research versus . Gemma 3n E2B IT and Devstral Medium has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. o3-deep-research has not been scored yet, Gemma 3n E2B IT has not been scored yet and Devstral Medium has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for o3-deep-research, Gemma 3n E2B IT and Devstral Medium yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Gemma 3n E2B IT does not support tool calling, which most coding agents need.
Which has the bigger context window?
o3-deep-research has the largest context window at 200,000 tokens, against 128,000 for Devstral Medium and 32,768 for Gemma 3n E2B IT. Maximum output per response: o3-deep-research up to 100,000, Gemma 3n E2B IT up to 32,768, Devstral Medium up to 128,000 tokens.
Which can read images, PDFs, audio or video?
o3-deep-research accepts text and images; Gemma 3n E2B IT accepts text, images and audio; Devstral Medium accepts text. Gemma 3n E2B IT handles the widest range of inputs.
Are any of these open source?
Gemma 3n E2B IT publishes its weights (Gemma Terms of Use) and can be self-hosted; o3-deep-research and Devstral Medium is proprietary.
Which is newer?
Devstral Medium is the newest, released Jul 10, 2025. o3-deep-research came out Jun 26, 2025; Gemma 3n E2B IT came out Jun 26, 2025. Knowledge cutoff: o3-deep-research May 2024, Gemma 3n E2B IT Jun 2024, Devstral Medium May 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 Nov 2, 2026.
