Llama 4 Maverick 17B Instruct vs Magistral Small vs Qwen3 8B
Too close to call on our weighted score (Llama 4 Maverick 17B Instruct 48, Qwen3 8B 46, Magistral Small 40). The right pick depends on what you value most.
Price in rating: Excluded · Include price
Meta
Llama 4 Maverick 17B Instruct
48/100- ECI132.2
- Price$0.27 / $0.86
- Context1M
Mistral AI
Magistral Small
40/100- ECI—
- Price$0.50 / $1.50
- Context131K
Alibaba (Qwen)
Qwen3 8B
46/100- ECI132.1
- Price$0.18 / $0.70
- Context33K
Too close to call
It is close. Our weighted score puts them within 2 points (Llama 4 Maverick 17B Instruct 48/100, Qwen3 8B 46/100, Magistral Small 40/100), so choose by what matters most for your work: Qwen3 8B for raw capability and Llama 4 Maverick 17B Instruct for long inputs. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Magistral Small has no Capabilities Index score yet.
- CapabilityQwen3 8BShared benchmarks: Qwen3 8B 56.4% · Llama 4 Maverick 17B Instruct 43.8% · Magistral Small 43.0%
- Lowest priceQwen3 8BQwen3 8B $0.31 · Llama 4 Maverick 17B Instruct $0.417 · Magistral Small $0.75 per 1M tokens (3:1 blend)
- Longest contextLlama 4 Maverick 17B InstructLlama 4 Maverick 17B Instruct 1,000,000 · Magistral Small 131,072 · Qwen3 8B 32,768 tokens
- Widest inputsLlama 4 Maverick 17B InstructLlama 4 Maverick 17B Instruct: Text, Images · Magistral Small: Text · Qwen3 8B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Llama 4 Maverick 17B Instruct | Magistral Small | Qwen3 8B |
|---|---|---|---|---|
| CapabilityShared benchmarks | 67% | 44 | 43 | 56 |
| Inputs & features | 20% | 50 | 35 | 35 |
| Context window | 13% | 64 | 32 | 11 |
| Overall | 100% | 48/100 | 40/100 | 46/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 132.2 (best) | — | 132.1 |
| ECI rank | #134 of 158 (best) | — | #135 of 158 |
| GPQA DiamondGraduate-level science questions | 67.0% (best) | 56.1% | 56.8% |
| OTIS Mock AIME 2024–2025Competition mathematics | 20.6% | 30.0% | 56.1% (best) |
| Price per million tokens | |||
| Input | $0.27 | $0.50 | $0.18 (best) |
| Output | $0.86 | $1.50 | $0.70 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.417 | $0.75 | $0.31 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 16 providers | Median of 1 providers | Official Alibaba API |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 131,072 tokens | 32,768 tokens |
| Max output | 16,384 tokens | 8,192 tokens | 32,768 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | OpenApache 2.0 | OpenApache-2.0 |
| API model ID | — | — | qwen3-8b |
| API providers | 16 (best) | 2 | 6 |
| Released | Apr 5, 2025 | Jun 10, 2025 | Apr 29, 2025 |
| Knowledge cutoff | 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.
Llama 4 Maverick 17B Instruct$4.42
Magistral Small$8.00
Qwen3 8B$3.20
Which should you choose?
Which is better: Llama 4 Maverick 17B Instruct, Magistral Small or Qwen3 8B?
It is close. Our weighted score puts them within 2 points (Llama 4 Maverick 17B Instruct 48/100, Qwen3 8B 46/100, Magistral Small 40/100), so choose by what matters most for your work: Qwen3 8B for raw capability and Llama 4 Maverick 17B Instruct for long inputs. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Magistral Small has no Capabilities Index score yet.
Which is cheaper, Llama 4 Maverick 17B Instruct, Magistral Small or Qwen3 8B?
Qwen3 8B is cheaper at $0.18 input / $0.70 output per million tokens (official Alibaba API price). Llama 4 Maverick 17B Instruct costs $0.27 input / $0.86 output per million tokens (median across 16 API providers); Magistral Small costs $0.50 input / $1.50 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.31 per million tokens for Qwen3 8B versus $0.417 for Llama 4 Maverick 17B Instruct (1.3× as much) and $0.75 for Magistral Small (2.4× 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 and OTIS Mock AIME 2024–2025): Qwen3 8B 56.4%, Llama 4 Maverick 17B Instruct 43.8% and Magistral Small 43.0%. On individual benchmarks: GPQA Diamond — Llama 4 Maverick 17B Instruct 67.0%, Qwen3 8B 56.8%, Magistral Small 56.1%; OTIS Mock AIME 2024–2025 — Qwen3 8B 56.1%, Magistral Small 30.0%, Llama 4 Maverick 17B Instruct 20.6%.
Which is better for coding?
There are no published SWE-bench Verified results for Llama 4 Maverick 17B Instruct, Magistral Small and Qwen3 8B yet, so there is no like-for-like coding score. On overall capability, Qwen3 8B 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?
Llama 4 Maverick 17B Instruct has the largest context window at 1,000,000 tokens, against 131,072 for Magistral Small and 32,768 for Qwen3 8B. Maximum output per response: Llama 4 Maverick 17B Instruct up to 16,384, Magistral Small up to 8,192, Qwen3 8B up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Llama 4 Maverick 17B Instruct accepts text and images; Magistral Small accepts text; Qwen3 8B accepts text. Llama 4 Maverick 17B Instruct handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache 2.0 and Apache-2.0), so you can self-host them.
Which is newer?
Magistral Small is the newest, released Jun 10, 2025. Qwen3 8B came out Apr 29, 2025; Llama 4 Maverick 17B Instruct came out Apr 5, 2025. Knowledge cutoff: Llama 4 Maverick 17B Instruct Aug 2024.
How do you decide the winner?
This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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.