BenchLeader
Menu

TheAgentCompany leaderboard

As of 13 Nov 2026, the top score on TheAgentCompany is 42.9% by DeepSeek V3.2 (DeepSeek), ahead of Gemini 2.5 Flash 09 2025 at 41.1%, across 14 model configurations with a published result (TheAgentCompany, result dated 29 Sep 2025). An agent works in a simulated company with chat, code hosting and office tools, completing tasks a new hire would. TheAgentCompany is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 13 Nov 2026)

  • DeepSeek V3.2 holds the top TheAgentCompany score at 42.9% (TheAgentCompany, 29 Sep 2025).
  • Gemini 2.5 Flash 09 2025 is second on TheAgentCompany at 41.1% (TheAgentCompany, 25 Sep 2025).
  • TheAgentCompany: Office tasks in a simulated software company (TheAgentCompany).
  • 14 model configurations have a published TheAgentCompany result on BenchLeader (BenchLeader, 13 Nov 2026).
  • TheAgentCompany does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

Office tasks in a simulated software company.

Published by
TheAgentCompanydata via Epoch AI Benchmarking Hub
Category
Agents & tools
Index weight
Reference only
Models
14
Data as of
13 Nov 2026

CC BY 4.0 — Epoch AI, ‘AI Benchmarking Hub’, epoch.ai/benchmarks. Mirrored boards credit their original publishers.

What the test looks like

An agent works in a simulated company with chat, code hosting and office tools, completing tasks a new hire would.

How it is scored

Percent of tasks resolved, as published by TheAgentCompany.

What to keep in mind

Harness-dependent; the environment is simulated.

Top 15
  1. 1DeepSeek V3.242.9%
  2. 2Gemini 2.5 Flash 09 202541.1%
  3. 3Claude Sonnet 433.1%
  4. 4Claude 3.7 Sonnet30.9%
  5. 5Gemini 2.5 Pro30.3%
  6. 6Claude 3.5 Sonnet24.0%
  7. 7Gemini 2.0 Flash11.4%
  8. 8GPT-4o8.6%
  9. 9Llama 3.1 405B7.4%
  10. 10Llama 3.1 70B6.9%
  11. 11Qwen2.5 72B5.7%
  12. 12Gemini 1.5 Pro 0023.4%
  13. 13Nova Pro1.7%
  14. 14Qwen2-72B1.1%
14 of 14
#
1DeepSeek V3.242.9%51.02025-09-29
2Gemini 2.5 Flash 09 202541.1%47.52025-09-25
3Claude Sonnet 433.1%50.42025-05-22
4Claude 3.7 Sonnet30.9%49.82025-02-24
5Gemini 2.5 Pro30.3%54.52025-05-06
6Claude 3.5 Sonnet24.0%47.02024-10-22
7Gemini 2.0 Flash11.4%43.42025-02-05
8GPT-4o8.6%43.22024-11-20
9Llama 3.1 405B7.4%41.82024-07-23
10Llama 3.1 70B6.9%40.72024-07-23
11Qwen2.5 72B5.7%43.12024-09-19
12Gemini 1.5 Pro 0023.4%41.42024-09-24
13Nova Pro1.7%40.72024-12-03
14Qwen2-72B1.1%41.22024-06-07

AI agent benchmark leaderboard · All LLM benchmarks

Related benchmarks

Cite as: BenchLeader, “TheAgentCompany leaderboard”, data as of 13 Nov 2026, https://www.benchleader.com/benchmarks/the_agent_company.

TheAgentCompany: questions

What does TheAgentCompany measure?
An agent works in a simulated company with chat, code hosting and office tools, completing tasks a new hire would. Scores are reported in percent of tasks solved; higher is better.
What is the top score on TheAgentCompany?
As of 13 Nov 2026, the highest score on TheAgentCompany is 42.9% by DeepSeek V3.2 (result dated 29 Sep 2025), ahead of Gemini 2.5 Flash 09 2025 at 41.1%. Scores come from TheAgentCompany and are re-read daily.
Which AI model leads TheAgentCompany?
DeepSeek V3.2 leads TheAgentCompany with 42.9% as of 13 Nov 2026 (result dated 29 Sep 2025), ahead of Gemini 2.5 Flash 09 2025 at 41.1%.
How many models have TheAgentCompany results?
14 model configurations have a TheAgentCompany result on BenchLeader, all taken from TheAgentCompany via Epoch AI Benchmarking Hub.
Who runs TheAgentCompany and how often is it updated?
TheAgentCompany is published by TheAgentCompany. BenchLeader re-reads the published results once a day and records the date each result was published.
Does TheAgentCompany count toward the BenchLeader Index?
No. TheAgentCompany is shown for reference but left out of the composite index.