olmOCR 2 7B vs Ministral 3 8B vs Gemini 2.5 Flash-Lite Preview 09-2025
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Allenai
olmOCR 2 7B
51/100- ECI—
- Price$0.071 / $0.345
- Context16K
Mistral AI
Ministral 3 8B
69/100- ECI—
- Price$0.15 / $0.15
- Context262K
Google
Gemini 2.5 Flash-Lite Preview 09-2025
82/100- ECI—
- Price$0.09 / $0.36
- Context1.05M
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Gemini 2.5 Flash-Lite Preview 09-2025 82/100, Ministral 3 8B 69/100, olmOCR 2 7B 51/100) 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 priceolmOCR 2 7BolmOCR 2 7B $0.14 · Ministral 3 8B $0.15 · Gemini 2.5 Flash-Lite Preview 09-2025 $0.158 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 Flash-Lite Preview 09-2025Gemini 2.5 Flash-Lite Preview 09-2025 1,048,576 · Ministral 3 8B 262,144 · olmOCR 2 7B 16,384 tokens
- Widest inputsGemini 2.5 Flash-Lite Preview 09-2025olmOCR 2 7B: Text, Images · Ministral 3 8B: Text, Images · Gemini 2.5 Flash-Lite Preview 09-2025: Text, Images, PDFs, Audio, Video
- Self-hostingolmOCR 2 7B and Ministral 3 8BPublishes downloadable weights (Apache-2.0 and Apache 2.0)
| Measure | Weight | olmOCR 2 7B | Ministral 3 8B | Gemini 2.5 Flash-Lite Preview 09-2025 |
|---|---|---|---|---|
| Price | 50% | 87 | 85 | 84 |
| Inputs & features | 30% | 25 | 60 | 90 |
| Context window | 20% | 0 | 43 | 65 |
| Specs & price only | 100% | 51/100 | 69/100 | 82/100 |
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 | olmOCR 2 7BAllenai | ||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.071 (best) | $0.15 | $0.09 |
| Output | $0.345 | $0.15 (best) | $0.36 |
| Cached input | — | $0.015 | — |
| Blended (3:1) | $0.14 (best) | $0.15 | $0.158 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Official Mistral API | Median of 1 providers |
| Limits | |||
| Context window | 16,384 tokens | 262,144 tokens | 1,048,576 tokens (best) |
| Max output | — | 262,144 tokens (best) | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | Yes |
| Video | No | No | Yes |
| Reasoning | No | No | Yes |
| Tool calling | No | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenApache-2.0 | OpenApache 2.0 | Proprietary |
| API model ID | — | ministral-8b-2512 | — |
| API providers | 1 | 12 (best) | 1 |
| Released | Oct 22, 2025 | Dec 2, 2025 | Sep 25, 2025 |
| Knowledge cutoff | — | — | Jan 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- olmOCR 2 7B$1.40
Ministral 3 8B$1.80
Gemini 2.5 Flash-Lite Preview 09-2025$1.62
Which should you choose?
Which is better: olmOCR 2 7B, Ministral 3 8B or Gemini 2.5 Flash-Lite Preview 09-2025?
There is not enough shared capability evidence to name an overall winner. The scores (Gemini 2.5 Flash-Lite Preview 09-2025 82/100, Ministral 3 8B 69/100, olmOCR 2 7B 51/100) 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, olmOCR 2 7B, Ministral 3 8B or Gemini 2.5 Flash-Lite Preview 09-2025?
olmOCR 2 7B is cheaper at $0.071 input / $0.345 output per million tokens (median across 1 API provider). Ministral 3 8B costs $0.15 input / $0.15 output per million tokens (official Mistral API price); Gemini 2.5 Flash-Lite Preview 09-2025 costs $0.09 input / $0.36 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.14 per million tokens for olmOCR 2 7B versus $0.15 for Ministral 3 8B (1.1× as much) and $0.158 for Gemini 2.5 Flash-Lite Preview 09-2025 (1.1× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. olmOCR 2 7B has not been scored yet, Ministral 3 8B has not been scored yet and Gemini 2.5 Flash-Lite Preview 09-2025 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for olmOCR 2 7B, Ministral 3 8B and Gemini 2.5 Flash-Lite Preview 09-2025 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that olmOCR 2 7B does not support tool calling, which most coding agents need.
Which has the bigger context window?
Gemini 2.5 Flash-Lite Preview 09-2025 has the largest context window at 1,048,576 tokens, against 262,144 for Ministral 3 8B and 16,384 for olmOCR 2 7B. Maximum output per response: Ministral 3 8B up to 262,144, Gemini 2.5 Flash-Lite Preview 09-2025 up to 65,536 tokens.
Which can read images, PDFs, audio or video?
olmOCR 2 7B accepts text and images; Ministral 3 8B accepts text and images; Gemini 2.5 Flash-Lite Preview 09-2025 accepts text, images, PDFs, audio and video. Gemini 2.5 Flash-Lite Preview 09-2025 handles the widest range of inputs.
Are any of these open source?
olmOCR 2 7B and Ministral 3 8B publishes its weights (Apache-2.0 and Apache 2.0) and can be self-hosted; Gemini 2.5 Flash-Lite Preview 09-2025 is proprietary.
Which is newer?
Ministral 3 8B is the newest, released Dec 2, 2025. olmOCR 2 7B came out Oct 22, 2025; Gemini 2.5 Flash-Lite Preview 09-2025 came out Sep 25, 2025. Knowledge cutoff: Gemini 2.5 Flash-Lite Preview 09-2025 Jan 2025.
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.