LLM Agent Benchmark Leaderboard

Name: LLM Agent Benchmark Leaderboard
Creator: DataLearner
License: https://creativecommons.org/licenses/by/4.0/

This page provides the LLM Agent benchmark leaderboard, covering Aider-Polyglot, τ²-Bench, Terminal Bench 2.0, Tool Decathlon, and OSWorld-Verified. Compare GPT, Claude, Qwen, and DeepSeek on tool use, task planning, and autonomous execution.

Updated on 2026-07-28 08:43:41

As of 2026-07, this page covers Aider-Polyglot, τ²-Bench, Terminal Bench 2.0, Tool Decathlon and related benchmarks for LLM Agent Benchmark Leaderboard, making it straightforward to compare within the same task family.

Click any model name to check context length, licensing, and pricing on its detail page. See Data Methodology for scoring details.

Benchmark

Agent能力评测Aider-Polyglot τ²-Bench

AI Agent - 工具使用Terminal Bench 2.0 Tool Decathlon OSWorld-Verified

More Benchmarks

Model Size:All 3B and below 7B 13B 34B 65B 100B and above

Model Type:All Reasoning Models Foundation Models Instruction/Chat Models Coding Models

Source:All Open Source Closed Source

Origin:All China

Model release cutoff:

Top picks

Ranked by Aider-Polyglot

Current SOTA

GPT-5

OpenAI

88.00Aider-Polyglot

View model

Best Open-Source

DeepSeek V3.2-Exp

DeepSeek-AI

74.20Aider-Polyglot−13.80

View model

Best China-Made

DeepSeek V3.2-Exp

DeepSeek-AI

74.20Aider-Polyglot−13.80

View model

LLM Performance Results

Data source: DataLearnerAI

Click any row to open the model page. Tick the checkboxes to compare up to 4 models side by side.

Rank	Model						License
	GPT-5 Thinking Enabled OpenAI	88.00	—	—	—	—	Proprietary	Details
	GPT-5 Thinking Enabled OpenAI	86.70	—	—	—	—	Proprietary	Details
	o3-pro Thinking Enabled OpenAI	84.90	—	—	—	—	Proprietary	Details
4	Gemini 2.5-Pro Thinking Enabled Google Deep Mind	83.10	—	—	—	—	Proprietary	Details
5	OpenAI o3 Thinking Enabled OpenAI	81.30	—	—	—	—	Proprietary	Details
6	GPT-5 Thinking Enabled OpenAI	81.30	—	—	—	—	Proprietary	Details
7	Grok 4 Thinking Enabled xAI	79.60	—	—	—	—	Proprietary	Details
8	Gemini 2.5-Pro Thinking Enabled Google Deep Mind	79.10	—	—	—	—	Proprietary	Details
9	OpenAI o3 OpenAI	76.90	—	—	—	—	Proprietary	Details
10	Gemini-2.5-Pro-Preview-05-06 Google Deep Mind	76.90	—	—	—	—	Proprietary	Details
11	DeepSeek V3.2-Exp Thinking Enabled DeepSeek-AI	74.20	—	—	—	—	Free commercial	Details
12	Gemini 2.5 Pro Experimental 03-25 Google Deep Mind	72.90	—	—	—	—	Proprietary	Details
13	OpenAI o4 - mini Thinking Enabled OpenAI	72.00	—	—	—	—	Proprietary	Details
14	Claude Opus 4 Thinking Enabled Anthropic	72.00	—	—	—	—	Proprietary	Details
15	DeepSeek-R1-0528 Thinking Enabled DeepSeek-AI	71.40	—	—	—	—	Free commercial	Details
16	Claude Opus 4 Anthropic	70.70	—	—	—	—	Proprietary	Details
17	DeepSeek V3.2-Exp DeepSeek-AI	70.20	—	—	—	—	Free commercial	Details
18	Claude Sonnet 3.7 Thinking Enabled Anthropic	64.90	—	—	—	—	Proprietary	Details
19	OpenAI o1 Thinking Enabled OpenAI	61.70	—	—	—	—	Proprietary	Details
20	Claude Sonnet 4 Thinking Enabled Anthropic	61.30	—	—	—	—	Proprietary	Details
21	OpenAI o3-mini Thinking Enabled OpenAI	60.40	—	—	—	—	Proprietary	Details
22	Claude Sonnet 3.7 Anthropic	60.40	—	—	—	—	Proprietary	Details
23	Qwen3-235B-A22B 阿里巴巴	59.60	—	—	—	—	Free commercial	Details
24	Kimi K2 Moonshot AI	59.10	—	—	—	—	Free commercial	Details
25	DeepSeek-R1 Thinking Enabled DeepSeek-AI	56.90	—	—	—	—	Free commercial	Details
26	Claude Sonnet 4 Anthropic	56.40	—	—	—	—	Proprietary	Details
27	DeepSeek-V3-0324 DeepSeek-AI	55.10	—	—	—	—	Free commercial	Details
28	Gemini 2.5 Flash Thinking Enabled Google Deep Mind	55.10	—	—	—	—	Proprietary	Details
29	OpenAI o3-mini Thinking Enabled OpenAI	53.80	—	—	—	—	Proprietary	Details
30	Grok 3 xAI	53.30	—	—	—	—	Proprietary	Details
31	GPT-4.1 OpenAI	52.40	—	—	—	—	Proprietary	Details
32	Claude 3.5 Sonnet New Anthropic	51.60	—	—	—	—	Proprietary	Details
33	Grok 3 mini Thinking Enabled xAI	49.30	—	—	—	—	Proprietary	Details
34	DeepSeek-V3 DeepSeek-AI	48.40	—	—	—	—	Free commercial	Details
35	Gemini 2.5 Flash Google Deep Mind	47.10	—	—	—	—	Proprietary	Details
36	GPT-4o(2025-03-27) OpenAI	45.30	—	—	—	—	Proprietary	Details
37	GPT-4.5 OpenAI	44.90	—	—	—	—	Proprietary	Details
38	GPT OSS 120B Thinking Enabled OpenAI	41.80	—	—	—	—	Free commercial	Details
39	Qwen3-32B 阿里巴巴	40.00	—	—	—	—	Free commercial	Details
40	Gemini 2.0 Flash Experimental DeepMind	38.20	—	—	—	—	Proprietary	Details
41	Gemini 2.0 Pro Experimental DeepMind	35.60	—	—	—	—	Proprietary	Details
42	Grok 3 mini Thinking Enabled xAI	34.70	—	—	—	—	Proprietary	Details
43	OpenAI o1-mini OpenAI	32.90	—	—	—	—	Proprietary	Details
44	GPT-4.1 mini OpenAI	32.40	—	—	—	—	Proprietary	Details
45	Claude 3.5 Haiku Anthropic	28.00	—	—	—	—	Proprietary	Details
46	GPT-4o(2025-01-29) OpenAI	27.10	—	—	—	—	Proprietary	Details
47	GPT-4o OpenAI	23.10	—	—	—	—	Proprietary	Details
48	Qwen2.5-Max 阿里巴巴	21.80	—	—	—	—	Proprietary	Details
49	QwQ-32B Thinking Enabled 阿里巴巴	20.90	—	—	—	—	Free commercial	Details
50	Gemini 2.0 Flash Experimental Thinking Enabled DeepMind	18.20	—	—	—	—	Proprietary	Details

GPT-5 OpenAI

Thinking Enabled

Aider-Polyglot88.00

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

GPT-5 OpenAI

Thinking Enabled

Aider-Polyglot86.70

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

o3-pro OpenAI

Thinking Enabled

Aider-Polyglot84.90

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Gemini 2.5-Pro Google Deep Mind

Thinking Enabled

Aider-Polyglot83.10

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

OpenAI o3 OpenAI

Thinking Enabled

Aider-Polyglot81.30

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

GPT-5 OpenAI

Thinking Enabled

Aider-Polyglot81.30

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Grok 4 xAI

Thinking Enabled

Aider-Polyglot79.60

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Gemini 2.5-Pro Google Deep Mind

Thinking Enabled

Aider-Polyglot79.10

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

OpenAI o3 OpenAI

Aider-Polyglot76.90

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Gemini-2.5-Pro-Preview-05-06 Google Deep Mind

Aider-Polyglot76.90

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

DeepSeek V3.2-Exp DeepSeek-AI

Thinking Enabled

Aider-Polyglot74.20

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Free commercial

Gemini 2.5 Pro Experimental 03-25 Google Deep Mind

Aider-Polyglot72.90

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

OpenAI o4 - mini OpenAI

Thinking Enabled

Aider-Polyglot72.00

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Claude Opus 4 Anthropic

Thinking Enabled

Aider-Polyglot72.00

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

DeepSeek-R1-0528 DeepSeek-AI

Thinking Enabled

Aider-Polyglot71.40

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Free commercial

Claude Opus 4 Anthropic

Aider-Polyglot70.70

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

DeepSeek V3.2-Exp DeepSeek-AI

Aider-Polyglot70.20

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Free commercial

Claude Sonnet 3.7 Anthropic

Thinking Enabled

Aider-Polyglot64.90

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

OpenAI o1 OpenAI

Thinking Enabled

Aider-Polyglot61.70

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Claude Sonnet 4 Anthropic

Thinking Enabled

Aider-Polyglot61.30

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

OpenAI o3-mini OpenAI

Thinking Enabled

Aider-Polyglot60.40

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Claude Sonnet 3.7 Anthropic

Aider-Polyglot60.40

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Qwen3-235B-A22B 阿里巴巴

Aider-Polyglot59.60

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Free commercial

Kimi K2 Moonshot AI

Aider-Polyglot59.10

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Free commercial

DeepSeek-R1 DeepSeek-AI

Thinking Enabled

Aider-Polyglot56.90

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Free commercial

Claude Sonnet 4 Anthropic

Aider-Polyglot56.40

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

DeepSeek-V3-0324 DeepSeek-AI

Aider-Polyglot55.10

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Free commercial

Gemini 2.5 Flash Google Deep Mind

Thinking Enabled

Aider-Polyglot55.10

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

OpenAI o3-mini OpenAI

Thinking Enabled

Aider-Polyglot53.80

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Grok 3 xAI

Aider-Polyglot53.30

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

GPT-4.1 OpenAI

Aider-Polyglot52.40

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Claude 3.5 Sonnet New Anthropic

Aider-Polyglot51.60

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Grok 3 mini xAI

Thinking Enabled

Aider-Polyglot49.30

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

DeepSeek-V3 DeepSeek-AI

Aider-Polyglot48.40

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Free commercial

Gemini 2.5 Flash Google Deep Mind

Aider-Polyglot47.10

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

GPT-4o(2025-03-27)OpenAI

Aider-Polyglot45.30

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

GPT-4.5 OpenAI

Aider-Polyglot44.90

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

GPT OSS 120B OpenAI

Thinking Enabled

Aider-Polyglot41.80

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Free commercial

Qwen3-32B 阿里巴巴

Aider-Polyglot40.00

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Free commercial

Gemini 2.0 Flash Experimental DeepMind

Aider-Polyglot38.20

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Gemini 2.0 Pro Experimental DeepMind

Aider-Polyglot35.60

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Grok 3 mini xAI

Thinking Enabled

Aider-Polyglot34.70

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

OpenAI o1-mini OpenAI

Aider-Polyglot32.90

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

GPT-4.1 mini OpenAI

Aider-Polyglot32.40

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Claude 3.5 Haiku Anthropic

Aider-Polyglot28.00

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

GPT-4o(2025-01-29)OpenAI

Aider-Polyglot27.10

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

GPT-4o OpenAI

Aider-Polyglot23.10

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Qwen2.5-Max 阿里巴巴

Aider-Polyglot21.80

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

QwQ-32B 阿里巴巴

Thinking Enabled

Aider-Polyglot20.90

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Free commercial

Gemini 2.0 Flash Experimental DeepMind

Thinking Enabled

Aider-Polyglot18.20

τ²-Bench—

Terminal Bench 2.0—

Tool Decathlon—

OSWorld-Verified—

Proprietary

Sort by:

Showing 50 of 149 modelsView Aider-Polyglot benchmark page