Model comparison
Llama 3-70B vs Longcat Flash Chat
Longcat Flash Chat is the stronger model overall, scoring 42.1 to 28.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
MetaSummary
- They share 18 benchmarks with published results for both. Llama 3-70B scores higher in 0 categories and Longcat Flash Chat in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Longcat Flash Chat leads 39.4 to 12.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 35.1% for Llama 3-70B and 43.9% for Longcat Flash Chat.
Side by side
| Llama 3-70B | Longcat Flash Chat | |
|---|---|---|
| Provider | Meta | Meituan |
| Noometry Index | 28.8 | 42.1 |
| Released | 2024-04-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 31 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Longcat Flash Chat leads
Llama 3-70B: 35.8 (#218), Longcat Flash Chat: 43.5 (#87)
| Benchmark | Llama 3-70B | Longcat Flash Chat |
|---|---|---|
| LMArena Coding | 1206 | 1471 |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 21.1 (#139), Longcat Flash Chat: —
| Benchmark | Llama 3-70B | Longcat Flash Chat |
|---|---|---|
| Cybench | 5% | — |
Reasoning Too close to call
Llama 3-70B: 18.0 (#288), Longcat Flash Chat: 19.0 (#272)
| Benchmark | Llama 3-70B | Longcat Flash Chat |
|---|---|---|
| Kagi LLM Benchmark | 35.1% | 43.9% |
| LMArena Hard Prompts | 1195 | 1440 |
| NYT Connections (extended) | — | 17.7% |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Longcat Flash Chat leads
Llama 3-70B: 12.8 (#305), Longcat Flash Chat: 39.4 (#107)
| Benchmark | Llama 3-70B | Longcat Flash Chat |
|---|---|---|
| LMArena Math | 1218 | 1442 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| MATH Level 5 | 22.6% | — |
Knowledge Longcat Flash Chat leads
Llama 3-70B: 20.8 (#277), Longcat Flash Chat: 40.6 (#116)
| Benchmark | Llama 3-70B | Longcat Flash Chat |
|---|---|---|
| LMArena Expert | 1149 | 1454 |
| GPQA Diamond | 40.6% | — |
| MMLU | 79.3% | — |
Multilingual Longcat Flash Chat leads
Llama 3-70B: 33.6 (#251), Longcat Flash Chat: 51.9 (#101)
| Benchmark | Llama 3-70B | Longcat Flash Chat |
|---|---|---|
| LMArena Non-English | 1142 | 1404 |
| LMArena Chinese | 1114 | 1465 |
| LMArena French | 1232 | 1456 |
| LMArena German | 1169 | 1408 |
| LMArena Japanese | 1017 | 1373 |
| LMArena Korean | 1017 | 1371 |
| LMArena Russian | 1159 | 1395 |
| LMArena Spanish | 1241 | 1445 |
Instruction Following Longcat Flash Chat leads
Llama 3-70B: 62.5 (#238), Longcat Flash Chat: 74.4 (#96)
| Benchmark | Llama 3-70B | Longcat Flash Chat |
|---|---|---|
| LMArena Instruction Following | 1194 | 1411 |
Long Context Longcat Flash Chat leads
Llama 3-70B: 35.6 (#240), Longcat Flash Chat: 43.5 (#93)
| Benchmark | Llama 3-70B | Longcat Flash Chat |
|---|---|---|
| LMArena Longer Query | 1174 | 1425 |
Writing & Preference Longcat Flash Chat leads
Llama 3-70B: 42.8 (#231), Longcat Flash Chat: 61.0 (#91)
| Benchmark | Llama 3-70B | Longcat Flash Chat |
|---|---|---|
| LMArena Text | 1221 | 1427 |
| LMArena Creative Writing | 1210 | 1388 |
| LMArena Multi-Turn | 1223 | 1418 |
Frequently asked questions
Is Llama 3-70B better than Longcat Flash Chat?
Longcat Flash Chat is the stronger model overall, scoring 42.1 to 28.8 on the Noometry Index.
Is Llama 3-70B or Longcat Flash Chat better for coding?
Longcat Flash Chat scores higher on coding benchmarks: 43.5 versus 35.8 in the Noometry coding category.
How many benchmarks do Llama 3-70B and Longcat Flash Chat share?
18 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Longcat Flash Chat has 19.