Mistral AI, open weights
Magistral Small
Magistral Small by Mistral AI ranks 296th of 354 ranked models on the Noometry Index as of October 2026, with a score of 30.2. Its strongest category is coding, where it ranks 176th. API pricing starts at $0.50 per million input tokens and $1.50 per million output tokens, with a 128K-token context window.
Last verified
Specifications
- Noometry rank
- #296 of 354
- Index score
- 30.2
- Evidence
- Confirmed 10 results
- Provider
Mistral AI- Released
- June 10, 2025
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 128K
- Max output
- 40K
- Input price
- $0.50 / M
- Output price
- $1.50 / M
- Blended price
- $0.75 / M
- Output speed
- 0 tokens/s Kagi
- Value
- #117 of 219
- Knowledge cutoff
- Unknown
- Input
- text, image
Category scores
Each category score combines every public result we have in that category.
- Coding 38.4
- Reasoning 6.8
- Math 26.2
- Knowledge 30.9
Strengths and weaknesses
Categories where Magistral Small places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
Closest competitors
The models ranked just above and below Magistral Small. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| GPT-4 Turbo | #292 | 30.5 | $15 | — | Compare |
| Qwen1.5-32B | #293 | 30.5 | — | — | Compare |
| Amazon Nova Micro | #294 | 30.4 | $0.0613 | — | Compare |
| Olmo 7b Instruct | #295 | 30.3 | — | — | Compare |
| Qwen2.5 32B Instruct | #297 | 30.1 | $1.22 | — | Compare |
| Palm 2 | #298 | 30.0 | — | — | Compare |
| Gemma 7B | #299 | 30.0 | — | — | Compare |
| Qwen2-72B | #300 | 30.0 | — | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| SciCode | 35.2% | #100 of 121, top 83% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| ARC-AGI-2 | 0% | #83 of 83, top 100% | Epoch AI | ||
| Kagi LLM Benchmark | 6.3% | #99 of 99, top 100% | Kagi LLM Benchmark | ||
| ARC-AGI-1 | 5% | #78 of 83, top 94% | Epoch AI | ||
| CritPt | 0.3% | #95 of 134, top 71% | Epoch AI | ||
| Chess Puzzles | 3% | #102 of 129, top 80% | Epoch AI | 2026-08-30 | |
| DTBench | 61.3% | #115 of 151, top 77% | Epoch AI | ||
| Epoch Capabilities Index | 131.42 | Epoch AI | 2025-09-18 | ||
| Epoch Capabilities Index | 133.19 | #131 of 213, top 62% | Epoch AI | 2025-06-10 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | #121 of 173, top 70% | Epoch AI | 2026-08-06 | |
| OTIS Mock AIME 2024-2025 | 28.1% | Epoch AI | 2026-08-30 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 47.6% | Epoch AI | 2026-08-30 | ||
| GPQA Diamond | 56.1% | #119 of 186, top 64% | Epoch AI | 2026-08-06 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| bedrock | $0.50 | $1.50 | — | 2026-10-10 |
Compare Magistral Small
- Magistral Small vs Olmo 7b Instruct
- Magistral Small vs Qwen2.5 32B Instruct
- Magistral Small vs Amazon Nova Micro
- Magistral Small vs Palm 2
- Magistral Small vs Qwen1.5-32B
- Magistral Small vs Gemma 7B
- Magistral Small vs GPT-6 Astra
- Magistral Small vs Claude Fable 5.1
- Magistral Small vs Gemini 3.8 Flash
- Magistral Small vs Kimi K3
- Magistral Small vs Grok 4.6
- Magistral Small vs Qwen3.8 Max
- Magistral Small vs GLM-5.3
- Magistral Small vs Muse Spark 1.3
Other Mistral AI models
- Mistral Large 443.1
- Mistral Medium 3.540.2
- Mistral Large 339.1
- Mistral Medium36.3
- Magistral Medium35.2
- Devstral Small 250534.3
- Mistral Small33.4
- Pixtral Large32.2
Frequently asked questions
How good is Magistral Small?
Magistral Small by Mistral AI ranks 296th of 354 ranked models on the Noometry Index as of October 2026, with a score of 30.2. Its strongest category is coding, where it ranks 176th. API pricing starts at $0.50 per million input tokens and $1.50 per million output tokens, with a 128K-token context window.
How much does Magistral Small cost?
Magistral Small costs $0.50 per million input tokens and $1.50 per million output tokens on bedrock.
What is Magistral Small's context window?
Magistral Small accepts up to 128K tokens of input and can write up to 40K tokens in one response.
Is Magistral Small open source?
Yes. Magistral Small's weights are downloadable; check the license for commercial terms.
How fast is Magistral Small?
Magistral Small generated about 0 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.
What are Magistral Small's strengths and weaknesses?
Relative to other ranked models, Magistral Small places best in coding, knowledge and lowest in reasoning, math.
What is Magistral Small best at?
Its best category is coding, where it ranks 176th on Noometry.