meituan/longcat-flash-chatProviders do have offers, but we have not collected a current price yet. That is a gap on our side, not a model missing from the market.
| Task set | Result | Run conditions | Measured by |
|---|---|---|---|
| Arena Score, programming | 1,467.98 1,455–1,481 | — | — |
| Arena Score in French | 1,459.11 1,412–1,506 | — | — |
| Arena Score in Spanish | 1,444.1 1,412–1,476 | — | — |
| Arena Score, mathematics | 1,440.87 1,419–1,463 | — | — |
| Arena Score in English | 1,440.51 1,432–1,449 | — | — |
| Arena Score, expert questions | 1,438.56 1,413–1,464 | — | — |
| Arena Score, hard prompts | 1,433.01 1,425–1,441 | — | — |
| Arena Score, overall | 1,422.32 1,416–1,429 | — | — |
| Arena Score, multi-turn dialogue | 1,403.21 1,390–1,416 | — | — |
| Arena Score, instruction following | 1,398 1,387–1,409 | — | — |
| Arena Score, long queries | 1,391.19 1,379–1,403 | — | — |
| Arena Score in Russian | 1,387.66 1,366–1,409 | — | — |
| Arena Score, creative writing | 1,346.08 1,330–1,362 | — | — |