Model comparison
Ministral 8B vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 28.2 on the Noometry Index. Ministral 8B costs 2.5× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Mistral AISummary
- They share 13 benchmarks with published results for both. Ministral 8B scores higher in 2 categories and Mistral Large 3 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Large 3 leads 36.0 to 12.6.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 7.4% for Ministral 8B and 14.5% for Mistral Large 3.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.25 / $0.75 for Mistral Large 3.
Side by side
| Ministral 8B | Mistral Large 3 | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 28.2 | 39.1 |
| Released | 2024-10-01 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 8K |
| Input $ / M tokens | $0.15 | $0.25 |
| Output $ / M tokens | $0.15 | $0.75 |
| Results tracked | 17 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Ministral 8B: 35.0 (#230), Mistral Large 3: 34.4 (#237)
| Benchmark | Ministral 8B | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1202 | 1448 |
| LMArena WebDev | — | 1230 |
Agentic & Tool Use Not comparable
Ministral 8B: 16.4 (#148), Mistral Large 3: —
| Benchmark | Ministral 8B | Mistral Large 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |
Reasoning Ministral 8B leads
Ministral 8B: 18.4 (#281), Mistral Large 3: 15.2 (#319)
| Benchmark | Ministral 8B | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| Thematic Generalization | — | 23% |
| DTBench | 45.7% | — |
Math Mistral Large 3 leads
Ministral 8B: 25.7 (#267), Mistral Large 3: 38.7 (#129)
| Benchmark | Ministral 8B | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1188 | 1414 |
| MATH Level 5 | 14.9% | — |
Knowledge Mistral Large 3 leads
Ministral 8B: 12.6 (#297), Mistral Large 3: 36.0 (#177)
| Benchmark | Ministral 8B | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 7.4% | 14.5% |
| LMArena Expert | 1170 | 1421 |
| GPQA Diamond | 27.1% | — |
Multimodal Not comparable
Ministral 8B: —, Mistral Large 3: 38.2 (#66)
| Benchmark | Ministral 8B | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Mistral Large 3 leads
Ministral 8B: 35.1 (#247), Mistral Large 3: 52.5 (#84)
| Benchmark | Ministral 8B | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1165 | 1413 |
| LMArena Chinese | 1193 | 1447 |
| LMArena Russian | 1195 | 1411 |
| LMArena French | — | 1455 |
| LMArena German | — | 1437 |
| LMArena Japanese | — | 1394 |
| LMArena Korean | — | 1384 |
| LMArena Spanish | — | 1440 |
Instruction Following Mistral Large 3 leads
Ministral 8B: 60.5 (#250), Mistral Large 3: 74.0 (#108)
| Benchmark | Ministral 8B | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1161 | 1403 |
Long Context Mistral Large 3 leads
Ministral 8B: 36.7 (#227), Mistral Large 3: 43.1 (#105)
| Benchmark | Ministral 8B | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1212 | 1413 |
Writing & Preference Mistral Large 3 leads
Ministral 8B: 39.6 (#246), Mistral Large 3: 60.0 (#101)
| Benchmark | Ministral 8B | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1191 | 1428 |
| LMArena Creative Writing | 1175 | 1386 |
| LMArena Multi-Turn | 1166 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
Frequently asked questions
Is Ministral 8B better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 28.2 on the Noometry Index. Ministral 8B costs 2.5× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.
Which is cheaper, Ministral 8B or Mistral Large 3?
Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Mistral Large 3 lists at $0.25 and $0.75.
Is Ministral 8B or Mistral Large 3 better for coding?
They score almost the same on coding (35.0 vs 34.4); test both on your own repository before choosing.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Ministral 8B and Mistral Large 3 share?
13 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Mistral Large 3 has 24.