Model comparison
Mistral Medium vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 36.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
StepFunSummary
- They share 17 benchmarks with published results for both. Mistral Medium scores higher in 4 categories and Step 3 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 3 leads 36.8 to 25.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 50% for Mistral Medium and 62.3% for Step 3.
Side by side
| Mistral Medium | Step 3 | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 36.3 | 40.5 |
| Released | 2023-12-11 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $1.50 | — |
| Output $ / M tokens | $7.50 | — |
| Results tracked | 36 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Mistral Medium: 34.2 (#243), Step 3: 40.1 (#147)
| Benchmark | Mistral Medium | Step 3 |
|---|---|---|
| LMArena Coding | 1434 | 1367 |
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.3 (#90), Step 3: —
| Benchmark | Mistral Medium | Step 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
Reasoning Step 3 leads
Mistral Medium: 24.0 (#167), Step 3: 28.4 (#105)
| Benchmark | Mistral Medium | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 50% | 62.3% |
| LMArena Hard Prompts | 1426 | 1355 |
| CritPt | 0% | — |
| DTBench | 75.5% | — |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |
Math Step 3 leads
Mistral Medium: 28.1 (#245), Step 3: 37.6 (#148)
| Benchmark | Mistral Medium | Step 3 |
|---|---|---|
| LMArena Math | 1408 | 1366 |
| OTIS Mock AIME 2024-2025 | 32.2% | — |
| ProofBench | 9% | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Step 3 leads
Mistral Medium: 25.0 (#265), Step 3: 36.8 (#164)
| Benchmark | Mistral Medium | Step 3 |
|---|---|---|
| LMArena Expert | 1408 | 1333 |
| GPQA Diamond | 59.5% | — |
| Humanity's Last Exam | 4.5% | — |
| Vectara Hallucination Rate | 22.7% | — |
Multimodal Too close to call
Mistral Medium: 35.3 (#88), Step 3: 35.5 (#86)
| Benchmark | Mistral Medium | Step 3 |
|---|---|---|
| LMArena Vision | 1172 | 1177 |
Multilingual Mistral Medium leads
Mistral Medium: 52.1 (#91), Step 3: 46.3 (#159)
| Benchmark | Mistral Medium | Step 3 |
|---|---|---|
| LMArena Non-English | 1408 | 1327 |
| LMArena Chinese | 1447 | 1397 |
| LMArena German | 1432 | 1371 |
| LMArena Korean | 1380 | 1269 |
| LMArena Russian | 1411 | 1331 |
| LMArena Spanish | 1433 | 1371 |
| LMArena French | 1459 | — |
| LMArena Japanese | 1378 | — |
Instruction Following Mistral Medium leads
Mistral Medium: 73.7 (#116), Step 3: 70.4 (#164)
| Benchmark | Mistral Medium | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1398 | 1332 |
Long Context Mistral Medium leads
Mistral Medium: 42.9 (#114), Step 3: 40.3 (#157)
| Benchmark | Mistral Medium | Step 3 |
|---|---|---|
| LMArena Longer Query | 1406 | 1326 |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), Step 3: 54.3 (#151)
| Benchmark | Mistral Medium | Step 3 |
|---|---|---|
| LMArena Text | 1424 | 1350 |
| LMArena Creative Writing | 1391 | 1321 |
| LMArena Multi-Turn | 1418 | 1341 |
| Short-Story Creative Writing | 77.3% | — |
Frequently asked questions
Is Mistral Medium better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 36.3 on the Noometry Index.
Is Mistral Medium or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 34.2 in the Noometry coding category.
How many benchmarks do Mistral Medium and Step 3 share?
17 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Step 3 has 17.