Model comparison
Longcat Flash Chat vs Tulu 3 (Tülu 3) 70B
Longcat Flash Chat is the stronger model overall, scoring 42.1 to 33.0 on the Noometry Index.
Last verified . 11 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Longcat Flash Chat scores higher in 7 categories and Tulu 3 (Tülu 3) 70B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Longcat Flash Chat leads 39.4 to 14.2.
Side by side
| Longcat Flash Chat | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Meituan | Allen Institute for AI (Ai2) |
| Noometry Index | 42.1 | 33.0 |
| Released | — | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 14 |
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), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Longcat Flash Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1471 | 1235 |
Reasoning Tulu 3 (Tülu 3) 70B leads
Longcat Flash Chat: 19.0 (#272), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Longcat Flash Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1220 |
| Kagi LLM Benchmark | 43.9% | — |
| NYT Connections (extended) | 17.7% | — |
Math Longcat Flash Chat leads
Longcat Flash Chat: 39.4 (#107), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Longcat Flash Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1442 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
Knowledge Longcat Flash Chat leads
Longcat Flash Chat: 40.6 (#116), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Longcat Flash Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| LMArena Expert | 1454 | — |
Multilingual Longcat Flash Chat leads
Longcat Flash Chat: 51.9 (#101), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Longcat Flash Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1404 | 1236 |
| LMArena Chinese | 1465 | 1249 |
| LMArena Russian | 1395 | 1246 |
| LMArena French | 1456 | — |
| LMArena German | 1408 | — |
| LMArena Japanese | 1373 | — |
| LMArena Korean | 1371 | — |
| LMArena Spanish | 1445 | — |
Instruction Following Longcat Flash Chat leads
Longcat Flash Chat: 74.4 (#96), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Longcat Flash Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1411 | 1233 |
Long Context Longcat Flash Chat leads
Longcat Flash Chat: 43.5 (#93), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Longcat Flash Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1425 | 1224 |
Writing & Preference Longcat Flash Chat leads
Longcat Flash Chat: 61.0 (#91), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Longcat Flash Chat | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1427 | 1256 |
| LMArena Creative Writing | 1388 | 1231 |
| LMArena Multi-Turn | 1418 | 1252 |
Frequently asked questions
Is Longcat Flash Chat better than Tulu 3 (Tülu 3) 70B?
Longcat Flash Chat is the stronger model overall, scoring 42.1 to 33.0 on the Noometry Index.
Is Longcat Flash Chat or Tulu 3 (Tülu 3) 70B better for coding?
Longcat Flash Chat scores higher on coding benchmarks: 43.5 versus 36.0 in the Noometry coding category.
How many benchmarks do Longcat Flash Chat and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. Longcat Flash Chat has 19 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.