Model comparison
Mistral Medium vs Step 1o Turbo 202506
Step 1o Turbo 202506 is the stronger model overall, scoring 39.7 to 36.3 on the Noometry Index.
Last verified . 14 shared benchmarks.
Mistral AI
StepFunSummary
- They share 14 benchmarks with published results for both. Mistral Medium scores higher in 4 categories and Step 1o Turbo 202506 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 1o Turbo 202506 leads 36.1 to 25.0.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Mistral Medium | Step 1o Turbo 202506 | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 36.3 | 39.7 |
| Released | 2023-12-11 | — |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $1.50 | — |
| Output $ / M tokens | $7.50 | — |
| Results tracked | 36 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 1o Turbo 202506 leads
Mistral Medium: 34.2 (#243), Step 1o Turbo 202506: 39.2 (#160)
| Benchmark | Mistral Medium | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Coding | 1434 | 1339 |
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.3 (#90), Step 1o Turbo 202506: —
| Benchmark | Mistral Medium | Step 1o Turbo 202506 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
Reasoning Step 1o Turbo 202506 leads
Mistral Medium: 24.0 (#167), Step 1o Turbo 202506: 26.8 (#129)
| Benchmark | Mistral Medium | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1335 |
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| DTBench | 75.5% | — |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |
Math Step 1o Turbo 202506 leads
Mistral Medium: 28.1 (#245), Step 1o Turbo 202506: 36.6 (#164)
| Benchmark | Mistral Medium | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Math | 1408 | 1318 |
| OTIS Mock AIME 2024-2025 | 32.2% | — |
| ProofBench | 9% | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Step 1o Turbo 202506 leads
Mistral Medium: 25.0 (#265), Step 1o Turbo 202506: 36.1 (#176)
| Benchmark | Mistral Medium | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Expert | 1408 | 1308 |
| 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 1o Turbo 202506: 36.1 (#80)
| Benchmark | Mistral Medium | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Vision | 1172 | 1186 |
Multilingual Mistral Medium leads
Mistral Medium: 52.1 (#91), Step 1o Turbo 202506: 45.3 (#173)
| Benchmark | Mistral Medium | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Non-English | 1408 | 1313 |
| LMArena Chinese | 1447 | 1380 |
| LMArena German | 1432 | 1314 |
| LMArena Russian | 1411 | 1327 |
| LMArena French | 1459 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1380 | — |
| LMArena Spanish | 1433 | — |
Instruction Following Mistral Medium leads
Mistral Medium: 73.7 (#116), Step 1o Turbo 202506: 69.2 (#176)
| Benchmark | Mistral Medium | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Instruction Following | 1398 | 1310 |
Long Context Mistral Medium leads
Mistral Medium: 42.9 (#114), Step 1o Turbo 202506: 41.0 (#146)
| Benchmark | Mistral Medium | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Longer Query | 1406 | 1348 |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), Step 1o Turbo 202506: 53.1 (#160)
| Benchmark | Mistral Medium | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Text | 1424 | 1336 |
| LMArena Creative Writing | 1391 | 1307 |
| LMArena Multi-Turn | 1418 | 1340 |
| Short-Story Creative Writing | 77.3% | — |
Frequently asked questions
Is Mistral Medium better than Step 1o Turbo 202506?
Step 1o Turbo 202506 is the stronger model overall, scoring 39.7 to 36.3 on the Noometry Index.
Is Mistral Medium or Step 1o Turbo 202506 better for coding?
Step 1o Turbo 202506 scores higher on coding benchmarks: 39.2 versus 34.2 in the Noometry coding category.
How many benchmarks do Mistral Medium and Step 1o Turbo 202506 share?
14 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Step 1o Turbo 202506 has 14.