Model comparison
Longcat Flash Chat vs Step 3
Longcat Flash Chat is the stronger model overall, scoring 42.1 to 40.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
StepFunSummary
- They share 16 benchmarks with published results for both. Longcat Flash Chat scores higher in 7 categories and Step 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3 leads 28.4 to 19.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 43.9% for Longcat Flash Chat and 62.3% for Step 3.
Side by side
| Longcat Flash Chat | Step 3 | |
|---|---|---|
| Provider | Meituan | StepFun |
| Noometry Index | 42.1 | 40.5 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Longcat Flash Chat leads
Longcat Flash Chat: 43.5 (#87), Step 3: 40.1 (#147)
| Benchmark | Longcat Flash Chat | Step 3 |
|---|---|---|
| LMArena Coding | 1471 | 1367 |
Reasoning Step 3 leads
Longcat Flash Chat: 19.0 (#272), Step 3: 28.4 (#105)
| Benchmark | Longcat Flash Chat | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 43.9% | 62.3% |
| LMArena Hard Prompts | 1440 | 1355 |
| NYT Connections (extended) | 17.7% | — |
Math Longcat Flash Chat leads
Longcat Flash Chat: 39.4 (#107), Step 3: 37.6 (#148)
| Benchmark | Longcat Flash Chat | Step 3 |
|---|---|---|
| LMArena Math | 1442 | 1366 |
Knowledge Longcat Flash Chat leads
Longcat Flash Chat: 40.6 (#116), Step 3: 36.8 (#164)
| Benchmark | Longcat Flash Chat | Step 3 |
|---|---|---|
| LMArena Expert | 1454 | 1333 |
Multimodal Not comparable
Longcat Flash Chat: —, Step 3: 35.5 (#86)
| Benchmark | Longcat Flash Chat | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Longcat Flash Chat leads
Longcat Flash Chat: 51.9 (#101), Step 3: 46.3 (#159)
| Benchmark | Longcat Flash Chat | Step 3 |
|---|---|---|
| LMArena Non-English | 1404 | 1327 |
| LMArena Chinese | 1465 | 1397 |
| LMArena German | 1408 | 1371 |
| LMArena Korean | 1371 | 1269 |
| LMArena Russian | 1395 | 1331 |
| LMArena Spanish | 1445 | 1371 |
| LMArena French | 1456 | — |
| LMArena Japanese | 1373 | — |
Instruction Following Longcat Flash Chat leads
Longcat Flash Chat: 74.4 (#96), Step 3: 70.4 (#164)
| Benchmark | Longcat Flash Chat | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1411 | 1332 |
Long Context Longcat Flash Chat leads
Longcat Flash Chat: 43.5 (#93), Step 3: 40.3 (#157)
| Benchmark | Longcat Flash Chat | Step 3 |
|---|---|---|
| LMArena Longer Query | 1425 | 1326 |
Writing & Preference Longcat Flash Chat leads
Longcat Flash Chat: 61.0 (#91), Step 3: 54.3 (#151)
| Benchmark | Longcat Flash Chat | Step 3 |
|---|---|---|
| LMArena Text | 1427 | 1350 |
| LMArena Creative Writing | 1388 | 1321 |
| LMArena Multi-Turn | 1418 | 1341 |
Frequently asked questions
Is Longcat Flash Chat better than Step 3?
Longcat Flash Chat is the stronger model overall, scoring 42.1 to 40.5 on the Noometry Index.
Is Longcat Flash Chat or Step 3 better for coding?
Longcat Flash Chat scores higher on coding benchmarks: 43.5 versus 40.1 in the Noometry coding category.
How many benchmarks do Longcat Flash Chat and Step 3 share?
16 benchmarks have published results for both models. Longcat Flash Chat has 19 scored results on Noometry and Step 3 has 17.