Model comparison
Ministral 3B vs Ministral 8B
Ministral 8B is the stronger model overall, scoring 28.2 to 26.2 on the Noometry Index.
Last verified . 4 shared benchmarks.
Mistral AISummary
- They share 4 benchmarks with published results for both. Ministral 3B scores higher in 1 category and Ministral 8B in 2 categories; one gap is clear of the uncertainty.
- The biggest single-benchmark swing is DTBench: 51.7% for Ministral 3B and 45.7% for Ministral 8B.
- Ministral 3B is cheaper at $0.10 / $0.10 per million input/output tokens, against $0.15 / $0.15 for Ministral 8B.
- Ministral 8B accepts more context: 262K tokens versus 131K.
Side by side
| Ministral 3B | Ministral 8B | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 26.2 | 28.2 |
| Released | 2024-10-01 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 262K | 262K |
| Input $ / M tokens | $0.10 | $0.15 |
| Output $ / M tokens | $0.10 | $0.15 |
| Results tracked | 6 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Ministral 3B: —, Ministral 8B: 35.0 (#230)
| Benchmark | Ministral 3B | Ministral 8B |
|---|---|---|
| LMArena Coding | — | 1202 |
Agentic & Tool Use Not comparable
Ministral 3B: —, Ministral 8B: 16.4 (#148)
| Benchmark | Ministral 3B | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Too close to call
Ministral 3B: 18.4 (#282), Ministral 8B: 18.4 (#281)
| Benchmark | Ministral 3B | Ministral 8B |
|---|---|---|
| DTBench | 51.7% | 45.7% |
| LMArena Hard Prompts | — | 1191 |
| LMCA | 5.5% | — |
| Epoch Capabilities Index | 118.1 | — |
Math Too close to call
Ministral 3B: 26.6 (#258), Ministral 8B: 25.7 (#267)
| Benchmark | Ministral 3B | Ministral 8B |
|---|---|---|
| MATH Level 5 | 14.4% | 14.9% |
| LMArena Math | — | 1188 |
Knowledge Ministral 8B leads
Ministral 3B: 10.4 (#302), Ministral 8B: 12.6 (#297)
| Benchmark | Ministral 3B | Ministral 8B |
|---|---|---|
| GPQA Diamond | 25.3% | 27.1% |
| Vectara Hallucination Rate | 7.3% | 7.4% |
| LMArena Expert | — | 1170 |
Multilingual Not comparable
Ministral 3B: —, Ministral 8B: 35.1 (#247)
| Benchmark | Ministral 3B | Ministral 8B |
|---|---|---|
| LMArena Non-English | — | 1165 |
| LMArena Chinese | — | 1193 |
| LMArena Russian | — | 1195 |
Instruction Following Not comparable
Ministral 3B: —, Ministral 8B: 60.5 (#250)
| Benchmark | Ministral 3B | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | — | 1161 |
Long Context Not comparable
Ministral 3B: —, Ministral 8B: 36.7 (#227)
| Benchmark | Ministral 3B | Ministral 8B |
|---|---|---|
| LMArena Longer Query | — | 1212 |
Writing & Preference Not comparable
Ministral 3B: —, Ministral 8B: 39.6 (#246)
| Benchmark | Ministral 3B | Ministral 8B |
|---|---|---|
| LMArena Text | — | 1191 |
| LMArena Creative Writing | — | 1175 |
| LMArena Multi-Turn | — | 1166 |
Frequently asked questions
Is Ministral 3B better than Ministral 8B?
Ministral 8B is the stronger model overall, scoring 28.2 to 26.2 on the Noometry Index.
Which is cheaper, Ministral 3B or Ministral 8B?
Ministral 3B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Ministral 8B lists at $0.15 and $0.15.
Which has the bigger context window?
Ministral 8B does, with 262K tokens against 131K.
How many benchmarks do Ministral 3B and Ministral 8B share?
4 benchmarks have published results for both models. Ministral 3B has 6 scored results on Noometry and Ministral 8B has 17.