Mistral AI, open weights
Ministral 8B
Ministral 8B by Mistral AI ranks 325th of 354 ranked models on the Noometry Index as of October 2026, with a score of 28.2. Its strongest category is agentic & tool use, where it ranks 148th. API pricing starts at $0.15 per million input tokens and $0.15 per million output tokens, with a 262K-token context window.
Last verified
Specifications
- Noometry rank
- #325 of 354
- Index score
- 28.2
- Evidence
- Confirmed 17 results
- Provider
Mistral AI- Released
- October 1, 2024
- Weights
- Open weights
- Reasoning
- No
- Context window
- 262K
- Max output
- 262K
- Input price
- $0.15 / M
- Output price
- $0.15 / M
- Blended price
- $0.15 / M
- Output speed
- Not measured
- Value
- #44 of 219
- Knowledge cutoff
- October 2024
- Input
- text, image
- Hugging Face
- mistralai/Ministral-3-8B-Instruct-2512
Category scores
Each category score combines every public result we have in that category.
- Coding 35.0
- Agentic & Tool Use 16.4
- Reasoning 18.4
- Math 25.7
- Knowledge 12.6
- Multilingual 35.1
- Instruction Following 60.5
- Long Context 36.7
- Writing & Preference 39.6
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 35.0 | #230 | 1 |
| Agentic & Tool Use | 16.4 | #148 | 1 |
| Reasoning | 18.4 | #281 | 2 |
| Math | 25.7 | #267 | 2 |
| Knowledge | 12.6 | #297 | 3 |
| Multilingual | 35.1 | #247 | 1 |
| Instruction Following | 60.5 | #250 | 1 |
| Long Context | 36.7 | #227 | 1 |
| Writing & Preference | 39.6 | #246 | 3 |
Strengths and weaknesses
Categories where Ministral 8B 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 | 35.0 | −3.7 | #230 of 340, top 68% |
| Long Context | 36.7 | −4.2 | #227 of 296, top 77% |
| Writing & Preference | 39.6 | −14.2 | #246 of 312, top 79% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Agentic & Tool Use | 16.4 | −14.0 | #148 of 154, top 97% |
| Knowledge | 12.6 | −24.7 | #297 of 314, top 95% |
| Multilingual | 35.1 | −12.3 | #247 of 297, top 84% |
Closest competitors
The models ranked just above and below Ministral 8B. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Llama 3.2 3B | #321 | 28.9 | $0.12 | — | Compare |
| Qwen1.5 4b Chat | #322 | 28.8 | — | — | Compare |
| Llama 3-70B | #323 | 28.8 | — | 104 | Compare |
| GPT-4o | #324 | 28.6 | $4.38 | — | Compare |
| Gemma 3 4B | #326 | 28.1 | $0.05 | 72 | Compare |
| GPT-4.1 nano | #327 | 27.9 | $0.18 | 135 | Compare |
| Phi 3 Mini 4k Instruct | #328 | 27.9 | — | — | Compare |
| Yi-34B | #329 | 27.8 | — | — | 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 |
|---|---|---|---|---|---|
| LMArena Coding | 1202 | #240 of 294, top 82% | LMArena | 2026-10-08 |
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | #46 of 49, top 94% | fc | Berkeley Function Calling Leaderboard |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 1191 | #241 of 297, top 82% | LMArena | 2026-10-08 | |
| DTBench | 45.7% | #147 of 151, top 98% | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1188 | #234 of 285, top 83% | LMArena | 2026-10-08 | |
| MATH Level 5 | 14.9% | #67 of 79, top 85% | Epoch AI | 2025-01-27 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 27.1% | #176 of 186, top 95% | Epoch AI | 2025-01-27 | |
| Vectara Hallucination Rate (lower is better) | 7.4% | #33 of 96, top 35% | Vectara Hallucination Leaderboard | ||
| LMArena Expert | 1170 | #232 of 273, top 85% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1165 | #247 of 297, top 84% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1193 | #234 of 285, top 83% | LMArena | 2026-10-08 | |
| LMArena Russian | 1195 | #236 of 283, top 84% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1161 | #249 of 298, top 84% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1212 | #237 of 291, top 82% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1191 | #247 of 297, top 84% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1175 | #242 of 295, top 83% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1166 | #246 of 295, top 84% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| mistral | $0.15 | $0.15 | $0.015 | 2026-10-10 |
| openrouter | $0.15 | $0.15 | $0.015 | 2026-10-10 |
Compare Ministral 8B
- Ministral 8B vs GPT-4o
- Ministral 8B vs Gemma 3 4B
- Ministral 8B vs Llama 3-70B
- Ministral 8B vs GPT-4.1 nano
- Ministral 8B vs Qwen1.5 4b Chat
- Ministral 8B vs Phi 3 Mini 4k Instruct
- Ministral 8B vs GPT-6 Astra
- Ministral 8B vs Claude Fable 5.1
- Ministral 8B vs Gemini 3.8 Flash
- Ministral 8B vs Kimi K3
- Ministral 8B vs Grok 4.6
- Ministral 8B vs Qwen3.8 Max
- Ministral 8B vs GLM-5.3
- Ministral 8B 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 Ministral 8B?
Ministral 8B by Mistral AI ranks 325th of 354 ranked models on the Noometry Index as of October 2026, with a score of 28.2. Its strongest category is agentic & tool use, where it ranks 148th. API pricing starts at $0.15 per million input tokens and $0.15 per million output tokens, with a 262K-token context window.
How much does Ministral 8B cost?
Ministral 8B costs $0.15 per million input tokens and $0.15 per million output tokens on Mistral AI's own API, with cached input at $0.015.
What is Ministral 8B's context window?
Ministral 8B accepts up to 262K tokens of input and can write up to 262K tokens in one response.
Is Ministral 8B open source?
Yes. Ministral 8B's weights are downloadable from Hugging Face (mistralai/Ministral-3-8B-Instruct-2512); check the license for commercial terms.
What are Ministral 8B's strengths and weaknesses?
Relative to other ranked models, Ministral 8B places best in coding, long context, writing & preference and lowest in agentic & tool use, knowledge, multilingual.
What is Ministral 8B best at?
Its best category is agentic & tool use, where it ranks 148th on Noometry.