Mistral AI, open weights
Mistral Small 3
Mistral Small 3 by Mistral AI ranks 278th of 354 ranked models on the Noometry Index as of October 2026, with a score of 31.2. Its strongest category is coding, where it ranks 207th. API pricing starts at $0.05 per million input tokens and $0.08 per million output tokens, with a 33K-token context window.
Last verified
Specifications
- Noometry rank
- #278 of 354
- Index score
- 31.2
- Evidence
- Confirmed 24 results
- Provider
Mistral AI- Released
- January 30, 2025
- Weights
- Open weights
- Reasoning
- Unknown
- Context window
- 33K
- Max output
- 16K
- Input price
- $0.05 / M
- Output price
- $0.08 / M
- Blended price
- $0.0575 / M
- Output speed
- Not measured
- Value
- #5 of 219
- Knowledge cutoff
- Unknown
- Input
- text
- Hugging Face
- mistralai/Mistral-Small-24B-Instruct-2501
Category scores
Each category score combines every public result we have in that category.
- Coding 36.5
- Reasoning 18.9
- Math 16.3
- Knowledge 25.1
- Multilingual 37.3
- Instruction Following 63.7
- Long Context 37.8
- Writing & Preference 32.2
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 36.5 | #207 | 3 |
| Reasoning | 18.9 | #273 | 2 |
| Math | 16.3 | #295 | 2 |
| Knowledge | 25.1 | #263 | 3 |
| Multilingual | 37.3 | #236 | 1 |
| Instruction Following | 63.7 | #229 | 1 |
| Long Context | 37.8 | #211 | 1 |
| Writing & Preference | 32.2 | #280 | 4 |
Strengths and weaknesses
Categories where Mistral Small 3 places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Coding | 36.5 | −2.2 | #207 of 340, top 61% |
| Long Context | 37.8 | −3.1 | #211 of 296, top 72% |
| Instruction Following | 63.7 | −7.6 | #229 of 305, top 76% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Math | 16.3 | −20.3 | #295 of 327, top 91% |
| Writing & Preference | 32.2 | −21.6 | #280 of 312, top 90% |
| Knowledge | 25.1 | −12.2 | #263 of 314, top 84% |
Closest competitors
The models ranked just above and below Mistral Small 3. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Wizardlm 13b | #274 | 31.4 | — | — | Compare |
| Qwen-14B | #275 | 31.4 | — | — | Compare |
| Phi 3 Mini 4k Instruct June 2024 | #276 | 31.3 | — | — | Compare |
| Gemma 1.1 7b IT | #277 | 31.3 | — | — | Compare |
| Phi-4 | #279 | 31.2 | $0.0875 | — | Compare |
| Mistral Small 3.2 | #280 | 31.2 | $0.13 | 68 | Compare |
| Amazon Nova Pro | #281 | 31.0 | $1.40 | — | Compare |
| Llama 4 Maverick | #282 | 30.9 | $0.30 | 456 | 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 |
|---|---|---|---|---|---|
| BigCodeBench Instruct | 45.3% | #20 of 64, top 32% | BigCodeBench | 2025-01-31 | |
| LMArena Coding | 1246 | #227 of 294, top 78% | LMArena | 2026-10-08 | |
| BigCodeBench Complete | 50.4% | #32 of 66, top 49% | BigCodeBench | 2025-01-31 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Chess Puzzles | 0% | #124 of 129, top 97% | Epoch AI | 2026-08-30 | |
| LMArena Hard Prompts | 1233 | #228 of 297, top 77% | LMArena | 2026-10-08 | |
| Epoch Capabilities Index | 127.07 | #151 of 213, top 71% | Epoch AI | 2025-01-30 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | #143 of 173, top 83% | Epoch AI | 2026-08-30 | |
| LMArena Math | 1240 | #220 of 285, top 78% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 47.3% | #137 of 186, top 74% | Epoch AI | 2026-08-30 | |
| Confabulations (lower is better) | 25.2% | #42 of 51, top 83% | Lech Mazur benchmarks | ||
| LMArena Expert | 1202 | #221 of 273, top 81% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1198 | #236 of 297, top 80% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1204 | #232 of 285, top 82% | LMArena | 2026-10-08 | |
| LMArena French | 1203 | #192 of 223, top 87% | LMArena | 2026-10-08 | |
| LMArena German | 1211 | #188 of 231, top 82% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1111 | #185 of 211, top 88% | LMArena | 2026-10-08 | |
| LMArena Korean | 1188 | #166 of 213, top 78% | LMArena | 2026-10-08 | |
| LMArena Russian | 1216 | #229 of 283, top 81% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1214 | #230 of 298, top 78% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1246 | #223 of 291, top 77% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1234 | #228 of 297, top 77% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1195 | #236 of 295, top 80% | LMArena | 2026-10-08 | |
| EQ-Bench Creative Writing | 707 | #110 of 115, top 96% | EQ-Bench | ||
| LMArena Multi-Turn | 1217 | #233 of 295, top 79% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| openrouter | $0.05 | $0.08 | — | 2026-10-10 |
Compare Mistral Small 3
- Mistral Small 3 vs Mistral Small
- Mistral Small 3 vs Gemma 1.1 7b IT
- Mistral Small 3 vs Phi-4
- Mistral Small 3 vs Phi 3 Mini 4k Instruct June 2024
- Mistral Small 3 vs Mistral Small 3.2
- Mistral Small 3 vs Qwen-14B
- Mistral Small 3 vs Amazon Nova Pro
- Mistral Small 3 vs GPT-6 Astra
- Mistral Small 3 vs Claude Fable 5.1
- Mistral Small 3 vs Gemini 3.8 Flash
- Mistral Small 3 vs Kimi K3
- Mistral Small 3 vs Grok 4.6
- Mistral Small 3 vs Qwen3.8 Max
- Mistral Small 3 vs GLM-5.3
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 Mistral Small 3?
Mistral Small 3 by Mistral AI ranks 278th of 354 ranked models on the Noometry Index as of October 2026, with a score of 31.2. Its strongest category is coding, where it ranks 207th. API pricing starts at $0.05 per million input tokens and $0.08 per million output tokens, with a 33K-token context window.
How much does Mistral Small 3 cost?
Mistral Small 3 costs $0.05 per million input tokens and $0.08 per million output tokens on openrouter.
What is Mistral Small 3's context window?
Mistral Small 3 accepts up to 33K tokens of input and can write up to 16K tokens in one response.
Is Mistral Small 3 open source?
Yes. Mistral Small 3's weights are downloadable from Hugging Face (mistralai/Mistral-Small-24B-Instruct-2501); check the license for commercial terms.
What are Mistral Small 3's strengths and weaknesses?
Relative to other ranked models, Mistral Small 3 places best in coding, long context, instruction following and lowest in math, writing & preference, knowledge.
What is Mistral Small 3 best at?
Its best category is coding, where it ranks 207th on Noometry.