Qwen Turbo vs Ministral 8B Instruct vs Gemma 3 12B IT
Too close to call on our weighted score (Qwen Turbo 57, Gemma 3 12B IT 55, Ministral 8B Instruct 42). The right pick depends on what you value most.
Alibaba (Qwen)
Qwen Turbo
57/100- ECI—
- Price$0.05 / $0.20
- Context1M
Mistral AI
Ministral 8B Instruct
42/100- ECI—
- Price$0.15 / $0.15
- Context131K
Google
Gemma 3 12B IT
55/100- ECI123.5
- Price$0.05 / $0.15
- Context131K
Too close to call
It is close. Our weighted score puts them within 2 points (Qwen Turbo 57/100, Gemma 3 12B IT 55/100, Ministral 8B Instruct 42/100), so choose by what matters most for your work: Qwen Turbo for raw capability and Gemma 3 12B IT on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond), because Qwen Turbo and Ministral 8B Instruct has no Capabilities Index score yet.
- CapabilityQwen TurboShared benchmarks: Qwen Turbo 41.8% · Gemma 3 12B IT 39.5% · Ministral 8B Instruct 27.2%
- Lowest priceGemma 3 12B ITGemma 3 12B IT $0.075 · Qwen Turbo $0.087 · Ministral 8B Instruct $0.15 per 1M tokens (3:1 blend)
- Longest contextQwen TurboQwen Turbo 1,000,000 · Ministral 8B Instruct 131,072 · Gemma 3 12B IT 131,072 tokens
- Widest inputsGemma 3 12B ITQwen Turbo: Text · Ministral 8B Instruct: Text · Gemma 3 12B IT: Text, Images
- Self-hostingMinistral 8B Instruct and Gemma 3 12B ITPublishes downloadable weights (Mistral Research License)
| Measure | Weight | Qwen Turbo | Ministral 8B Instruct | Gemma 3 12B IT |
|---|---|---|---|---|
| CapabilityShared benchmarks | 50% | 42 | 27 | 39 |
| Price | 25% | 100 | 89 | 100 |
| Inputs & features | 15% | 35 | 25 | 50 |
| Context window | 10% | 60 | 24 | 24 |
| Overall | 100% | 57/100 | 42/100 | 55/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | 123.5 |
| ECI rank | — | — | #138 of 148 |
| GPQA DiamondGraduate-level science questions | 41.8% (best) | 27.2% | 39.5% |
| OTIS Mock AIME 2024–2025Competition mathematics | 6.1% | — | 16.7% (best) |
| Price per million tokens | |||
| Input | $0.05 (best) | $0.15 | $0.05 (best) |
| Output | $0.20 | $0.15 (best) | $0.15 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.087 | $0.15 | $0.075 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Alibaba API | Median of 1 providers | Median of 7 providers |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 131,072 tokens | 131,072 tokens |
| Max output | 16,384 tokens | 8,192 tokens | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | OpenMistral Research License | Open |
| API model ID | qwen-turbo | — | — |
| API providers | 3 | 1 | 7 (best) |
| Released | Nov 1, 2024 | Oct 16, 2024 | Mar 12, 2025 |
| Knowledge cutoff | Apr 2024 | — | Aug 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Qwen Turbo$0.90
Ministral 8B Instruct$1.80
Gemma 3 12B IT$0.80
Which should you choose?
Which is better: Qwen Turbo, Ministral 8B Instruct or Gemma 3 12B IT?
It is close. Our weighted score puts them within 2 points (Qwen Turbo 57/100, Gemma 3 12B IT 55/100, Ministral 8B Instruct 42/100), so choose by what matters most for your work: Qwen Turbo for raw capability and Gemma 3 12B IT on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond), because Qwen Turbo and Ministral 8B Instruct has no Capabilities Index score yet.
Which is cheaper, Qwen Turbo, Ministral 8B Instruct or Gemma 3 12B IT?
Gemma 3 12B IT is cheaper at $0.05 input / $0.15 output per million tokens (median across 7 API providers). Qwen Turbo costs $0.05 input / $0.20 output per million tokens (official Alibaba API price); Ministral 8B Instruct costs $0.15 input / $0.15 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.075 per million tokens for Gemma 3 12B IT versus $0.087 for Qwen Turbo (1.2× as much) and $0.15 for Ministral 8B Instruct (2× as much).
Which scores higher on benchmarks?
Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond): Qwen Turbo 41.8%, Gemma 3 12B IT 39.5% and Ministral 8B Instruct 27.2%. On individual benchmarks: GPQA Diamond — Qwen Turbo 41.8%, Gemma 3 12B IT 39.5%, Ministral 8B Instruct 27.2%.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen Turbo, Ministral 8B Instruct and Gemma 3 12B IT yet, so there is no like-for-like coding score. On overall capability, Qwen Turbo leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Qwen Turbo has the largest context window at 1,000,000 tokens, against 131,072 for Ministral 8B Instruct and 131,072 for Gemma 3 12B IT. Maximum output per response: Qwen Turbo up to 16,384, Ministral 8B Instruct up to 8,192, Gemma 3 12B IT up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Qwen Turbo accepts text; Ministral 8B Instruct accepts text; Gemma 3 12B IT accepts text and images. Gemma 3 12B IT handles the widest range of inputs.
Are any of these open source?
Ministral 8B Instruct and Gemma 3 12B IT publishes its weights (Mistral Research License) and can be self-hosted; Qwen Turbo is proprietary.
Which is newer?
Gemma 3 12B IT is the newest, released Mar 12, 2025. Qwen Turbo came out Nov 1, 2024; Ministral 8B Instruct came out Oct 16, 2024. Knowledge cutoff: Qwen Turbo Apr 2024, Gemma 3 12B IT Aug 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.