Meituan30 Jun 2026Model

LongCat-2.0

Benchmark results

Benchmark	Score	Source check
SWE-bench ProClaude Code harness · Run on the lab's own corrected version of the public set	59.5%	Checked A person checked this number against its source on 23 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. Corroborated The same number is printed in 2 other lab documents: 1 2
GPQA Diamond	88.9%	Checked A person checked this number against its source on 23 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. Corroborated The same number is printed in 2 other lab documents: 1 2
BrowseCompin-house harness; context management not stated	79.9%	Checked A person checked this number against its source on 23 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. Corroborated The same number is printed in 2 other lab documents: 1 2
Terminal-Bench 2.1Claude Code harness; 6-hour agent timeout	70.8%	Checked A person checked this number against its source on 23 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. Corroborated The same number is printed in 2 other lab documents: 1 2

Sources

Reported by Meituan