Python · Apache-2.0
THUDM/AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
★ 3.8k
Stars
295 forks · 80 open issues
+2.6/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
25.6
Momentum / 100
see the breakdown below
3y ago
Created
last push 9mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 10.6 | +2.6/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 4.7 | last week ran 1.31× the monthly pace |
| Freshness | 15 | 0.0 | last push 9mo ago; decays to zero at 180 days |
| Scale | 15 | 10.4 | 3.8k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 25.6 | sum of the above |
Detail
| Topics | chatgptgpt-4llmllm-agent |
| Matched on | AI Agents (llm-agent) |
| Short window | +18 stars over 7 days = 2.6/day |
| Long window | +51 stars over 26 days = 2.0/day |
| Lifetime average | 3.19 stars/day over 1,196 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |