LongCat-2.5 Benchmarks, Pricing & Rankings
Meituan · 2026-11-01 · Closed · Current
Snapshot 2026-11-06 · updated weekly
LongCat-2.5 ranks #64 of 71 on the AMR leaderboard.
LongCat-2.5 benchmark scores
LongCat-2.5 price, speed & context
Input price
Free
per 1M tokens
Output price
Free
per 1M tokens
Speed
—
tok/s
Context
—
tokens
About LongCat-2.5
LongCat-2.5 is Meituan's newest LongCat release, announced 2026-11-01 per llm-stats. Pricing, context window, weights availability, and benchmarks are all unpublished so far - the model is not yet on OpenRouter (LongCat-2.0 lists at 0.30/1.20 dollars per million tokens there, but that is the previous generation's card and is deliberately not copied here; prices show as unlisted rather than guessed). AMR score of 45 is a conservative provisional anchor in the small-vendor entry tier with zero measured scores, to be replaced on first benchmark or leaderboard appearance.
Models around LongCat-2.5 in the rankings
LongCat-2.5 FAQ
Where does LongCat-2.5 rank?
LongCat-2.5 ranks #64 of 71 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 45.0. Its strongest dimension is AMR at 45.0.
How much does LongCat-2.5 cost?
LongCat-2.5 costs Free per million input tokens and Free per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $0.00 per million tokens.
What is the LongCat-2.5 context window?
LongCat-2.5 supports a — token context window and generates at a median 0 output tokens per second. That context fits roughly 0 standard documents in a single prompt.
Is LongCat-2.5 open source?
No — LongCat-2.5 is a closed model available only through Meituan’s official API and authorized cloud partners.
What is better than LongCat-2.5?
Laya 1 ranks one place higher at #63 with an AMR score of 45.4. LongCat-2.5 still wins 0 of the tracked dimensions head-to-head — check the comparison table to see exactly which.