LetTokenBurn
Sign in
Verified100%Harbor adapterAgentic / Tool UseCodingInstruction Following

AgentBench

Agent Bench

AgentBench: 8环境多任务Agent

PaperRepoDatasetLeaderboardHomepage

How to run

ltb · agentbench
$ npm i -g lettokenburn-cli
$ ltb bench pull agentbench --n 50
$ ltb bench run ./agentbench -a claude-code -m anthropic/claude-opus-4-8
$ ltb bench push

Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs

Scores

0 sourced entries

No sourced scores recorded yet.

Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.

Reproduced by the community

All runs
Loading community runs…

About

AgentBench (Agent Bench) — 8环境多任务Agent. Scoring: 准确率. Difficulty: 高. Imported from benchmark_research.md (2026-06).