Model comparison
GPT-4 vs Longcat Flash Chat
Longcat Flash Chat is the stronger model overall, scoring 42.1 to 29.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Longcat Flash Chat in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Longcat Flash Chat leads 39.4 to 10.8.
- Longcat Flash Chat has downloadable open weights; the other is API-only.
Side by side
| GPT-4 | Longcat Flash Chat | |
|---|---|---|
| Provider | OpenAI | Meituan |
| Noometry Index | 29.1 | 42.1 |
| Released | 2023-03-14 | — |
| Weights | Proprietary | Open |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $30 | — |
| Output $ / M tokens | $60 | — |
| Results tracked | 38 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Longcat Flash Chat leads
GPT-4: 31.6 (#283), Longcat Flash Chat: 43.5 (#87)
| Benchmark | GPT-4 | Longcat Flash Chat |
|---|---|---|
| LMArena Coding | 1254 | 1471 |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, Longcat Flash Chat: —
| Benchmark | GPT-4 | Longcat Flash Chat |
|---|---|---|
| METR Time Horizons | 36.1% | — |
Reasoning Longcat Flash Chat leads
GPT-4: 17.8 (#289), Longcat Flash Chat: 19.0 (#272)
| Benchmark | GPT-4 | Longcat Flash Chat |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1440 |
| Kagi LLM Benchmark | — | 43.9% |
| NYT Connections (extended) | — | 17.7% |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.89 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math Longcat Flash Chat leads
GPT-4: 10.8 (#309), Longcat Flash Chat: 39.4 (#107)
| Benchmark | GPT-4 | Longcat Flash Chat |
|---|---|---|
| LMArena Math | 1269 | 1442 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |
Knowledge Longcat Flash Chat leads
GPT-4: 18.4 (#282), Longcat Flash Chat: 40.6 (#116)
| Benchmark | GPT-4 | Longcat Flash Chat |
|---|---|---|
| LMArena Expert | 1211 | 1454 |
| GPQA Diamond | 35.7% | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multilingual Longcat Flash Chat leads
GPT-4: 40.6 (#215), Longcat Flash Chat: 51.9 (#101)
| Benchmark | GPT-4 | Longcat Flash Chat |
|---|---|---|
| LMArena Non-English | 1246 | 1404 |
| LMArena Chinese | 1242 | 1465 |
| LMArena French | 1283 | 1456 |
| LMArena German | 1251 | 1408 |
| LMArena Japanese | 1209 | 1373 |
| LMArena Korean | 1184 | 1371 |
| LMArena Russian | 1251 | 1395 |
| LMArena Spanish | 1261 | 1445 |
Instruction Following Longcat Flash Chat leads
GPT-4: 65.3 (#222), Longcat Flash Chat: 74.4 (#96)
| Benchmark | GPT-4 | Longcat Flash Chat |
|---|---|---|
| LMArena Instruction Following | 1241 | 1411 |
Long Context Longcat Flash Chat leads
GPT-4: 37.7 (#212), Longcat Flash Chat: 43.5 (#93)
| Benchmark | GPT-4 | Longcat Flash Chat |
|---|---|---|
| LMArena Longer Query | 1244 | 1425 |
Writing & Preference Longcat Flash Chat leads
GPT-4: 34.9 (#268), Longcat Flash Chat: 61.0 (#91)
| Benchmark | GPT-4 | Longcat Flash Chat |
|---|---|---|
| LMArena Text | 1263 | 1427 |
| LMArena Creative Writing | 1244 | 1388 |
| LMArena Multi-Turn | 1257 | 1418 |
| EQ-Bench Creative Writing | 752 | — |
Frequently asked questions
Is GPT-4 better than Longcat Flash Chat?
Longcat Flash Chat is the stronger model overall, scoring 42.1 to 29.1 on the Noometry Index.
Is GPT-4 or Longcat Flash Chat better for coding?
Longcat Flash Chat scores higher on coding benchmarks: 43.5 versus 31.6 in the Noometry coding category.
How many benchmarks do GPT-4 and Longcat Flash Chat share?
17 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Longcat Flash Chat has 19.