Model comparison
Ministral 8B vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.3 to 28.2 on the Noometry Index. Ministral 8B costs 20× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Ministral 8B scores higher in 1 category and Mistral Medium in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 39.6.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Ministral 8B and 81.6% for Mistral Medium.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
Side by side
| Ministral 8B | Mistral Medium | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 28.2 | 36.3 |
| Released | 2024-10-01 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 262K |
| Input $ / M tokens | $0.15 | $1.50 |
| Output $ / M tokens | $0.15 | $7.50 |
| Results tracked | 17 | 36 |
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 Medium: 34.2 (#243)
| Benchmark | Ministral 8B | Mistral Medium |
|---|---|---|
| LMArena Coding | 1202 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Mistral Medium leads
Ministral 8B: 16.4 (#148), Mistral Medium: 28.3 (#90)
| Benchmark | Ministral 8B | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | 37.7% |
Reasoning Mistral Medium leads
Ministral 8B: 18.4 (#281), Mistral Medium: 24.0 (#167)
| Benchmark | Ministral 8B | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1426 |
| DTBench | 45.7% | 75.5% |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math Mistral Medium leads
Ministral 8B: 25.7 (#267), Mistral Medium: 28.1 (#245)
| Benchmark | Ministral 8B | Mistral Medium |
|---|---|---|
| LMArena Math | 1188 | 1408 |
| MATH Level 5 | 14.9% | 81.6% |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Mistral Medium leads
Ministral 8B: 12.6 (#297), Mistral Medium: 25.0 (#265)
| Benchmark | Ministral 8B | Mistral Medium |
|---|---|---|
| GPQA Diamond | 27.1% | 59.5% |
| Vectara Hallucination Rate | 7.4% | 22.7% |
| LMArena Expert | 1170 | 1408 |
| Humanity's Last Exam | — | 4.5% |
Multimodal Not comparable
Ministral 8B: —, Mistral Medium: 35.3 (#88)
| Benchmark | Ministral 8B | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
Ministral 8B: 35.1 (#247), Mistral Medium: 52.1 (#91)
| Benchmark | Ministral 8B | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1165 | 1408 |
| LMArena Chinese | 1193 | 1447 |
| LMArena Russian | 1195 | 1411 |
| LMArena French | — | 1459 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1380 |
| LMArena Spanish | — | 1433 |
Instruction Following Mistral Medium leads
Ministral 8B: 60.5 (#250), Mistral Medium: 73.7 (#116)
| Benchmark | Ministral 8B | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1161 | 1398 |
Long Context Mistral Medium leads
Ministral 8B: 36.7 (#227), Mistral Medium: 42.9 (#114)
| Benchmark | Ministral 8B | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1212 | 1406 |
Writing & Preference Mistral Medium leads
Ministral 8B: 39.6 (#246), Mistral Medium: 60.0 (#103)
| Benchmark | Ministral 8B | Mistral Medium |
|---|---|---|
| LMArena Text | 1191 | 1424 |
| LMArena Creative Writing | 1175 | 1391 |
| LMArena Multi-Turn | 1166 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
Frequently asked questions
Is Ministral 8B better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.3 to 28.2 on the Noometry Index. Ministral 8B costs 20× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Which is cheaper, Ministral 8B or Mistral Medium?
Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Ministral 8B or Mistral Medium better for coding?
They score almost the same on coding (35.0 vs 34.2); 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 Medium share?
17 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Mistral Medium has 36.