Meituan
availableShows if the model has enough results for an index.LongCat-Flash-Lite-Sparse
LongCat-Flash-Lite-Sparse is a reasoning model from Meituan in the LongCat-Flash-Lite family. 10 benchmarks count toward its score, in 4 categories.
IndexOverall score out of 100.41.5 ±8.6
CoverageShare of the index weight with results.65%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.1M
EloLMArena rating and rank.N/A
The index is a score out of 100. The ± range shows how much it can change.
CapabilitiesScore per category, out of 100.
Out of 100Results
10 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result as a score out of 100. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| MATH-500 Problem Set | Math | 95.8% | 48.9 | — | — | Dan Hendrycks et al. |
| C-Eval | Knowledge | 85.8% | — | — | — | C-Eval authors |
| Massive Multitask Language Understanding | Knowledge | 85.3% | — | — | — | Dan Hendrycks et al. |
| Chinese Massive Multitask Language Understanding | Knowledge | 84.3% | — | — | — | DeepSeek-AI |
| Massive Multitask Language Understanding Professional | Knowledge | 79.2% | 45.4 | — | — | Yubo Wang et al. |
| GPQA Diamond | Knowledge | 69.5% | 42.4 | — | — | David Rein et al. |
| Software Engineering Benchmark Verified | Coding | 68.2% | 52.2 | — | — | Carlos E. Jimenez et al. |
| AIME 2026 | Math | 65.7% | 32.3 | — | — | Qwen |
| IMOAnswerBench | Math | 49.4% | — | — | — | DeepSeek-AI |
| BrowseComp | Agentic | 48.6% | 40.8 | — | — | OpenAI |
| MCP Atlas | Agentic | 45.6% | 42.6 | — | — | OpenAI |
| SWE-bench Pro | Coding | 40.6% | 43.3 | — | — | Xiang Deng et al. |
| Harvard-MIT Mathematics Tournament February 2026 | Math | 40.5% | 20.2 | — | — | Qwen |
| VITA-Bench | Agentic | 21.7% | 40.9 | — | — | Meituan LongCat Team |
10 benchmarks count, from 10 of 14 results. A grey row does not count. Too few models took that benchmark.