Model comparison
Mistral Medium vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 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 5 categories and Step 3.5 Flash in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 3.5 Flash leads 39.6 to 25.0.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 256K.
Side by side
| Mistral Medium | Step 3.5 Flash | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 36.3 | 42.3 |
| Released | 2023-12-11 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 262K | 256K |
| Max output | 262K | 256K |
| Input $ / M tokens | $1.50 | $0.10 |
| Output $ / M tokens | $7.50 | $0.30 |
| Results tracked | 36 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Mistral Medium: 34.2 (#243), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Mistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1434 | 1436 |
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.3 (#90), Step 3.5 Flash: —
| Benchmark | Mistral Medium | Step 3.5 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
Reasoning Mistral Medium leads
Mistral Medium: 24.0 (#167), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Mistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1411 |
| Kagi LLM Benchmark | 50% | — |
| NYT Connections (extended) | — | 28.4% |
| CritPt | 0% | — |
| DTBench | 75.5% | — |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |
Math Step 3.5 Flash leads
Mistral Medium: 28.1 (#245), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Mistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1408 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 32.2% | — |
| ProofBench | 9% | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Step 3.5 Flash leads
Mistral Medium: 25.0 (#265), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Mistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1408 | 1421 |
| GPQA Diamond | 59.5% | — |
| Humanity's Last Exam | 4.5% | — |
| Vectara Hallucination Rate | 22.7% | — |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), Step 3.5 Flash: —
| Benchmark | Mistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Mistral Medium leads
Mistral Medium: 52.1 (#91), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Mistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1408 | 1385 |
| LMArena Chinese | 1447 | 1447 |
| LMArena French | 1459 | 1421 |
| LMArena German | 1432 | 1405 |
| LMArena Japanese | 1378 | 1354 |
| LMArena Korean | 1380 | 1352 |
| LMArena Russian | 1411 | 1385 |
| LMArena Spanish | 1433 | 1419 |
Instruction Following Too close to call
Mistral Medium: 73.7 (#116), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Mistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1398 | 1385 |
Long Context Too close to call
Mistral Medium: 42.9 (#114), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Mistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1406 | 1402 |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Mistral Medium | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1424 | 1403 |
| LMArena Creative Writing | 1391 | 1357 |
| LMArena Multi-Turn | 1418 | 1405 |
| Short-Story Creative Writing | 77.3% | — |
Frequently asked questions
Is Mistral Medium better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 36.3 on the Noometry Index.
Which is cheaper, Mistral Medium or Step 3.5 Flash?
Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 256K.
How many benchmarks do Mistral Medium and Step 3.5 Flash share?
17 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Step 3.5 Flash has 19.