LongCat 2.0 Thinking

Meituan's LongCat 2.0 Thinking is the reasoning-enabled variant for harder coding, tool use, multi-step reasoning, and long-context agent workflows.

  • Reasoning
  • Tool Calling

Added Jul 21, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.75
Output
$3.00
Cache read
$0.015
Compare provider prices

Specifications

Context window
1M
Max output
131.1K
Parameters
1.6T / 48B
Total / active
Avg output (7d)
800 tokens
Longer than 63% of models

Benchmarks

Sourced from Artificial Analysis.

Intelligence Index

19.1

Better than 67% of models compared

Coding Index

45.3

Better than 52% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

4.5%

Better than 27% of models compared

AA-Briefcase

Agentic knowledge work (Elo)

740 Elo

Better than 32% of models compared

GDPval-AA v2

Economically valuable tasks (Elo)

873 Elo

Better than 39% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

6.4%

Better than 31% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

65.0%

Better than 56% of models compared

Reasoning

HLE

Humanity's Last Exam

33.7%

Better than 81% of models compared

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

0.0%

Better than 16% of models compared

SciCode

Python programming for scientific computing

36.3%

Better than 16% of models compared

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

78.0%

Better than 63% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

65.0%

Better than 56% of models compared

Last updated Oct 10, 2026

Artificial Analysis

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…