Model comparison
Mistral Large 3 vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 39.1 on the Noometry Index. Mistral Large 3 costs 3.8× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
Mistral AI
StepFunSummary
- They share 15 benchmarks with published results for both. Mistral Large 3 scores higher in 0 categories and Step 5 Preview in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 15.2.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 262K.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Large 3 | Step 5 Preview | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 39.1 | 47.9 |
| Released | 2025-12-02 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.02M |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.25 | $1 |
| Output $ / M tokens | $0.75 | $2.70 |
| Results tracked | 24 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Mistral Large 3: 34.4 (#237), Step 5 Preview: 51.8 (#36)
| Benchmark | Mistral Large 3 | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1230 | 1564 |
| LMArena Coding | 1448 | 1480 |
| SciCode | — | 58.9% |
Reasoning Step 5 Preview leads
Mistral Large 3: 15.2 (#319), Step 5 Preview: 40.0 (#57)
| Benchmark | Mistral Large 3 | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1429 | 1465 |
| Kagi LLM Benchmark | 50.9% | — |
| NYT Connections (extended) | 7.5% | — |
| CritPt | — | 20.9% |
| Thematic Generalization | 23% | — |
Math Step 5 Preview leads
Mistral Large 3: 38.7 (#129), Step 5 Preview: 46.1 (#72)
| Benchmark | Mistral Large 3 | Step 5 Preview |
|---|---|---|
| LMArena Math | 1414 | 1470 |
| ProofBench | — | 42% |
Knowledge Step 5 Preview leads
Mistral Large 3: 36.0 (#177), Step 5 Preview: 41.2 (#112)
| Benchmark | Mistral Large 3 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1421 | 1470 |
| Vectara Hallucination Rate | 14.5% | — |
Multimodal Step 5 Preview leads
Mistral Large 3: 38.2 (#66), Step 5 Preview: 41.0 (#41)
| Benchmark | Mistral Large 3 | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1221 | 1267 |
Multilingual Step 5 Preview leads
Mistral Large 3: 52.5 (#84), Step 5 Preview: 53.8 (#54)
| Benchmark | Mistral Large 3 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1413 | 1432 |
| LMArena Chinese | 1447 | 1519 |
| LMArena Russian | 1411 | 1436 |
| LMArena Spanish | 1440 | 1439 |
| LMArena French | 1455 | — |
| LMArena German | 1437 | — |
| LMArena Japanese | 1394 | — |
| LMArena Korean | 1384 | — |
Instruction Following Step 5 Preview leads
Mistral Large 3: 74.0 (#108), Step 5 Preview: 76.0 (#50)
| Benchmark | Mistral Large 3 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1403 | 1444 |
Long Context Step 5 Preview leads
Mistral Large 3: 43.1 (#105), Step 5 Preview: 44.5 (#64)
| Benchmark | Mistral Large 3 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1413 | 1455 |
Writing & Preference Step 5 Preview leads
Mistral Large 3: 60.0 (#101), Step 5 Preview: 62.8 (#71)
| Benchmark | Mistral Large 3 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1428 | 1442 |
| LMArena Creative Writing | 1386 | 1410 |
| LMArena Multi-Turn | 1429 | 1447 |
| EQ-Bench Creative Writing | 1412 | — |
Frequently asked questions
Is Mistral Large 3 better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 39.1 on the Noometry Index. Mistral Large 3 costs 3.8× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, Mistral Large 3 or Step 5 Preview?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Mistral Large 3 or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 262K.
How many benchmarks do Mistral Large 3 and Step 5 Preview share?
15 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Step 5 Preview has 18.