Model comparison
Magistral Small vs Qwen3 8B
Qwen3 8B is the stronger model overall, scoring 33.7 to 30.2 on the Noometry Index.
Last verified . 7 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 7 benchmarks with published results for both. Magistral Small scores higher in 1 category and Qwen3 8B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3 8B leads 16.6 to 6.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 30% for Magistral Small and 56.1% for Qwen3 8B.
- Qwen3 8B is cheaper at $0.18 / $0.70 per million input/output tokens, against $0.50 / $1.50 for Magistral Small.
- Qwen3 8B accepts more context: 131K tokens versus 128K.
Side by side
| Magistral Small | Qwen3 8B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.2 | 33.7 |
| Released | 2025-06-10 | 2025-04 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 40K | 8K |
| Input $ / M tokens | $0.50 | $0.18 |
| Output $ / M tokens | $1.50 | $0.70 |
| Results tracked | 10 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Small leads
Magistral Small: 38.4 (#176), Qwen3 8B: 34.0 (#248)
| Benchmark | Magistral Small | Qwen3 8B |
|---|---|---|
| SciCode | 35.2% | 22.6% |
Agentic & Tool Use Not comparable
Magistral Small: —, Qwen3 8B: 30.2 (#78)
| Benchmark | Magistral Small | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |
Reasoning Qwen3 8B leads
Magistral Small: 6.8 (#350), Qwen3 8B: 16.6 (#303)
| Benchmark | Magistral Small | Qwen3 8B |
|---|---|---|
| CritPt | 0.3% | 0% |
| Chess Puzzles | 3% | 5% |
| DTBench | 61.3% | 59.7% |
| Epoch Capabilities Index | 133.19 | 136.17 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 6.3% | — |
| ARC-AGI-1 | 5% | — |
| LMCA | — | 8.8% |
Math Qwen3 8B leads
Magistral Small: 26.2 (#261), Qwen3 8B: 34.9 (#191)
| Benchmark | Magistral Small | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | 56.1% |
Knowledge Qwen3 8B leads
Magistral Small: 30.9 (#223), Qwen3 8B: 36.1 (#173)
| Benchmark | Magistral Small | Qwen3 8B |
|---|---|---|
| GPQA Diamond | 56.1% | 56.8% |
| Vectara Hallucination Rate | — | 4.8% |
Long Context Not comparable
Magistral Small: —, Qwen3 8B: 37.9 (#210)
| Benchmark | Magistral Small | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
Frequently asked questions
Is Magistral Small better than Qwen3 8B?
Qwen3 8B is the stronger model overall, scoring 33.7 to 30.2 on the Noometry Index.
Which is cheaper, Magistral Small or Qwen3 8B?
Qwen3 8B is cheaper. It lists at $0.18 per million input tokens and $0.70 per million output tokens; Magistral Small lists at $0.50 and $1.50.
Is Magistral Small or Qwen3 8B better for coding?
Magistral Small scores higher on coding benchmarks: 38.4 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Qwen3 8B does, with 131K tokens against 128K.
How many benchmarks do Magistral Small and Qwen3 8B share?
7 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and Qwen3 8B has 11.