Model comparison
Mistral Medium vs Mistral Small 3
Mistral Medium is the stronger model overall, scoring 36.3 to 31.2 on the Noometry Index. Mistral Small 3 costs 52× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Mistral AISummary
- They share 18 benchmarks with published results for both. Mistral Medium scores higher in 6 categories and Mistral Small 3 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 32.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 6.7% for Mistral Small 3.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 33K.
Side by side
| Mistral Medium | Mistral Small 3 | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 36.3 | 31.2 |
| Released | 2023-12-11 | 2025-01-30 |
| Weights | Open | Open |
| Context window | 262K | 33K |
| Max output | 262K | 16K |
| Input $ / M tokens | $1.50 | $0.05 |
| Output $ / M tokens | $7.50 | $0.08 |
| Results tracked | 36 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
Mistral Medium: 34.2 (#243), Mistral Small 3: 36.5 (#207)
| Benchmark | Mistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1434 | 1246 |
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.3 (#90), Mistral Small 3: —
| Benchmark | Mistral Medium | Mistral Small 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
Reasoning Mistral Medium leads
Mistral Medium: 24.0 (#167), Mistral Small 3: 18.9 (#273)
| Benchmark | Mistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1233 |
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| DTBench | 75.5% | — |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 127.07 |
Math Mistral Medium leads
Mistral Medium: 28.1 (#245), Mistral Small 3: 16.3 (#295)
| Benchmark | Mistral Medium | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | 6.7% |
| LMArena Math | 1408 | 1240 |
| ProofBench | 9% | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Too close to call
Mistral Medium: 25.0 (#265), Mistral Small 3: 25.1 (#263)
| Benchmark | Mistral Medium | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 59.5% | 47.3% |
| LMArena Expert | 1408 | 1202 |
| Humanity's Last Exam | 4.5% | — |
| Confabulations | — | 25.2% |
| Vectara Hallucination Rate | 22.7% | — |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), Mistral Small 3: —
| Benchmark | Mistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Mistral Medium leads
Mistral Medium: 52.1 (#91), Mistral Small 3: 37.3 (#236)
| Benchmark | Mistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1408 | 1198 |
| LMArena Chinese | 1447 | 1204 |
| LMArena French | 1459 | 1203 |
| LMArena German | 1432 | 1211 |
| LMArena Japanese | 1378 | 1111 |
| LMArena Korean | 1380 | 1188 |
| LMArena Russian | 1411 | 1216 |
| LMArena Spanish | 1433 | — |
Instruction Following Mistral Medium leads
Mistral Medium: 73.7 (#116), Mistral Small 3: 63.7 (#229)
| Benchmark | Mistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1398 | 1214 |
Long Context Mistral Medium leads
Mistral Medium: 42.9 (#114), Mistral Small 3: 37.8 (#211)
| Benchmark | Mistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1406 | 1246 |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), Mistral Small 3: 32.2 (#280)
| Benchmark | Mistral Medium | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1424 | 1234 |
| LMArena Creative Writing | 1391 | 1195 |
| LMArena Multi-Turn | 1418 | 1217 |
| Short-Story Creative Writing | 77.3% | — |
| EQ-Bench Creative Writing | — | 707 |
Frequently asked questions
Is Mistral Medium better than Mistral Small 3?
Mistral Medium is the stronger model overall, scoring 36.3 to 31.2 on the Noometry Index. Mistral Small 3 costs 52× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.
Which is cheaper, Mistral Medium or Mistral Small 3?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Mistral Small 3 better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 33K.
How many benchmarks do Mistral Medium and Mistral Small 3 share?
18 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Mistral Small 3 has 24.