Schematron V2 Turbo vs DeepSeek V3.2 vs Gemma 4 E2B IT
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Inference.net
Schematron V2 Turbo
56/100- ECI—
- Price$0.03 / $0.15
- Context128K
DeepSeek
DeepSeek V3.2
52/100- ECI146.3
- Price$0.28 / $0.42
- Context128K
Google
Gemma 4 E2B IT
77/100- ECI—
- Price$0.04 / $0.08
- Context131K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Gemma 4 E2B IT 77/100, Schematron V2 Turbo 56/100, DeepSeek V3.2 52/100) compare the available specifications and price. 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 priceGemma 4 E2B ITGemma 4 E2B IT $0.05 · Schematron V2 Turbo $0.06 · DeepSeek V3.2 $0.315 per 1M tokens (3:1 blend)
- Longest contextGemma 4 E2B ITGemma 4 E2B IT 131,072 · Schematron V2 Turbo 128,000 · DeepSeek V3.2 128,000 tokens
- Widest inputsGemma 4 E2B ITSchematron V2 Turbo: Text · DeepSeek V3.2: Text · Gemma 4 E2B IT: Text, Images, Audio
- Self-hostingDeepSeek V3.2 and Gemma 4 E2B ITPublishes downloadable weights (MIT License)
| Measure | Weight | Schematron V2 Turbo | DeepSeek V3.2 | Gemma 4 E2B IT |
|---|---|---|---|---|
| Price | 50% | 100 | 71 | 100 |
| Inputs & features | 30% | 0 | 35 | 70 |
| Context window | 20% | 32 | 32 | 32 |
| Specs & price only | 100% | 56/100 | 52/100 | 77/100 |
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 | Schematron V2 TurboInference.net | ||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 146.3 | — |
| ECI rank | — | #87 of 158 | — |
| GPQA DiamondGraduate-level science questions | — | 83.4% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 87.8% | — |
| Price per million tokens | |||
| Input | $0.03 (best) | $0.28 | $0.04 |
| Output | $0.15 | $0.42 | $0.08 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.06 | $0.315 | $0.05 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 5 providers | Median of 30 providers | Median of 1 providers |
| Limits | |||
| Context window | 128,000 tokens | 128,000 tokens | 131,072 tokens (best) |
| Max output | 8,192 tokens | 64,000 tokens (best) | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | Yes |
| Video | No | No | No |
| Reasoning | No | Yes | Yes |
| Tool calling | No | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | OpenMIT License | Open |
| API model ID | — | — | — |
| API providers | 5 | 30 (best) | 1 |
| Released | Apr 16, 2026 | Dec 1, 2025 | Apr 2, 2026 |
| Knowledge cutoff | — | Jul 2024 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Schematron V2 Turbo$0.60
DeepSeek V3.2$3.64
Gemma 4 E2B IT$0.56
Which should you choose?
Which is better: Schematron V2 Turbo, DeepSeek V3.2 or Gemma 4 E2B IT?
There is not enough shared capability evidence to name an overall winner. The scores (Gemma 4 E2B IT 77/100, Schematron V2 Turbo 56/100, DeepSeek V3.2 52/100) compare the available specifications and price. 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, Schematron V2 Turbo, DeepSeek V3.2 or Gemma 4 E2B IT?
Gemma 4 E2B IT is cheaper at $0.04 input / $0.08 output per million tokens (median across 1 API provider). Schematron V2 Turbo costs $0.03 input / $0.15 output per million tokens (median across 5 API providers); DeepSeek V3.2 costs $0.28 input / $0.42 output per million tokens (median across 30 API providers). At a typical mix of three input tokens to one output token, that is $0.05 per million tokens for Gemma 4 E2B IT versus $0.06 for Schematron V2 Turbo (1.2× as much) and $0.315 for DeepSeek V3.2 (6.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Schematron V2 Turbo has not been scored yet, DeepSeek V3.2 has an ECI of 146.3 and Gemma 4 E2B IT has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Schematron V2 Turbo, DeepSeek V3.2 and Gemma 4 E2B IT yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Schematron V2 Turbo does not support tool calling, which most coding agents need.
Which has the bigger context window?
Gemma 4 E2B IT has the largest context window at 131,072 tokens, against 128,000 for Schematron V2 Turbo and 128,000 for DeepSeek V3.2. Maximum output per response: Schematron V2 Turbo up to 8,192, DeepSeek V3.2 up to 64,000, Gemma 4 E2B IT up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Schematron V2 Turbo accepts text; DeepSeek V3.2 accepts text; Gemma 4 E2B IT accepts text, images and audio. Gemma 4 E2B IT handles the widest range of inputs.
Are any of these open source?
DeepSeek V3.2 and Gemma 4 E2B IT publishes its weights (MIT License) and can be self-hosted; Schematron V2 Turbo is proprietary.
Which is newer?
Schematron V2 Turbo is the newest, released Apr 16, 2026. Gemma 4 E2B IT came out Apr 2, 2026; DeepSeek V3.2 came out Dec 1, 2025. Knowledge cutoff: DeepSeek V3.2 Jul 2024.
How do you decide the winner?
This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.