Model comparison
Claude 3 Haiku vs Longcat Flash Chat
Longcat Flash Chat is the stronger model overall, scoring 42.1 to 25.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Longcat Flash Chat in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Longcat Flash Chat leads 61.0 to 29.7.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 34.2% for Claude 3 Haiku and 43.9% for Longcat Flash Chat.
- Longcat Flash Chat has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | Longcat Flash Chat | |
|---|---|---|
| Provider | Anthropic | Meituan |
| Noometry Index | 25.9 | 42.1 |
| Released | 2024-03-07 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Longcat Flash Chat leads
Claude 3 Haiku: 26.4 (#325), Longcat Flash Chat: 43.5 (#87)
| Benchmark | Claude 3 Haiku | Longcat Flash Chat |
|---|---|---|
| LMArena Coding | 1199 | 1471 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Longcat Flash Chat leads
Claude 3 Haiku: 16.3 (#307), Longcat Flash Chat: 19.0 (#272)
| Benchmark | Claude 3 Haiku | Longcat Flash Chat |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 43.9% |
| LMArena Hard Prompts | 1174 | 1440 |
| NYT Connections (extended) | — | 17.7% |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Longcat Flash Chat leads
Claude 3 Haiku: 9.8 (#319), Longcat Flash Chat: 39.4 (#107)
| Benchmark | Claude 3 Haiku | Longcat Flash Chat |
|---|---|---|
| LMArena Math | 1188 | 1442 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge Longcat Flash Chat leads
Claude 3 Haiku: 17.3 (#285), Longcat Flash Chat: 40.6 (#116)
| Benchmark | Claude 3 Haiku | Longcat Flash Chat |
|---|---|---|
| LMArena Expert | 1148 | 1454 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Longcat Flash Chat: —
| Benchmark | Claude 3 Haiku | Longcat Flash Chat |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Longcat Flash Chat leads
Claude 3 Haiku: 36.0 (#243), Longcat Flash Chat: 51.9 (#101)
| Benchmark | Claude 3 Haiku | Longcat Flash Chat |
|---|---|---|
| LMArena Non-English | 1178 | 1404 |
| LMArena Chinese | 1155 | 1465 |
| LMArena French | 1195 | 1456 |
| LMArena German | 1174 | 1408 |
| LMArena Japanese | 1102 | 1373 |
| LMArena Korean | 1109 | 1371 |
| LMArena Russian | 1204 | 1395 |
| LMArena Spanish | 1166 | 1445 |
Instruction Following Longcat Flash Chat leads
Claude 3 Haiku: 61.3 (#247), Longcat Flash Chat: 74.4 (#96)
| Benchmark | Claude 3 Haiku | Longcat Flash Chat |
|---|---|---|
| LMArena Instruction Following | 1173 | 1411 |
Long Context Longcat Flash Chat leads
Claude 3 Haiku: 36.1 (#237), Longcat Flash Chat: 43.5 (#93)
| Benchmark | Claude 3 Haiku | Longcat Flash Chat |
|---|---|---|
| LMArena Longer Query | 1190 | 1425 |
Writing & Preference Longcat Flash Chat leads
Claude 3 Haiku: 29.7 (#291), Longcat Flash Chat: 61.0 (#91)
| Benchmark | Claude 3 Haiku | Longcat Flash Chat |
|---|---|---|
| LMArena Text | 1195 | 1427 |
| LMArena Creative Writing | 1157 | 1388 |
| LMArena Multi-Turn | 1190 | 1418 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Longcat Flash Chat?
Longcat Flash Chat is the stronger model overall, scoring 42.1 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Longcat Flash Chat better for coding?
Longcat Flash Chat scores higher on coding benchmarks: 43.5 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Longcat Flash Chat share?
18 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Longcat Flash Chat has 19.