Model Leaderboard

Compare AI models by capability and cost-effectiveness

Popular Comparisons

Custom Comparison Browse All Models

Overall Leaderboard

53/267 models

Overall model ranking based on comprehensive evaluation

Use Cases: General tasks, cross-domain applications

1GPT-5.282.3

2Gemini 3 Pro Preview81.9

3GPT-5 Codex77.8

4GPT-5.177.0

5GPT-5.1 CodeX76.2

6Grok 474.8

7o372.8

8GPT-5 Mini71.4

9Grok 4 Fast70.7

10Grok 3 Mini69.7

11Gemini 2.5 Pro69.1

12o4-mini69.0

Programming & Development

52/267 models

LiveCodeBench: Real-world coding tasks

Use Cases: Code completion, debugging, code review, script generation

1Gemini 3 Pro Preview92.6

2GPT-5.186.4

3o4-mini86.1

4GPT-5 Codex85.0

5GPT-5.1 CodeX84.5

6GPT-5 Mini83.7

7Grok 4 Fast83.5

8Grok 481.7

9Gemini 2.5 Pro80.8

10o380.2

11GPT-5.280.0

12GPT-5 Nano78.3

Logical Reasoning

52/267 models

HLE: Complex reasoning and problem-solving

Use Cases: Complex decision-making, multi-step analysis, logical reasoning

1Gemini 3 Pro Preview37.5

2GPT-5.234.5

3GPT-5.126.4

4GPT-5 Codex25.5

5Grok 423.9

6GPT-5.1 CodeX23.5

7Gemini 2.5 Pro21.2

8o320.0

9GPT-5 Mini19.8

10o4-mini17.6

11Grok 4 Fast17.0

12Claude Opus 4.512.9

Knowledge Q&A

51/267 models

MMLU Pro: Broad knowledge assessment

Use Cases: Expert Q&A, fact-checking, educational tutoring

1GPT-5.289.6

2Gemini 3 Pro Preview89.2

3Claude Opus 4.189.0

4Claude Opus 4.588.4

5Claude Opus 487.0

6Claude Sonnet 4.587.0

7Grok 487.0

8Gemini 2.5 Pro86.3

9GPT-5 Codex86.0

10GPT-5.186.0

11GPT-5.1 CodeX86.0

12o385.6

Scientific Research

53/267 models

GPQA: Graduate-level science questions

Use Cases: Academic research, scientific writing, experiment design

1GPT-5.292.4

2Gemini 3 Pro Preview90.3

3GPT-5.187.9

4Grok 487.4

5GPT-5.1 CodeX86.0

6GPT-5 Codex84.3

7Grok 4 Fast84.3

8Gemini 2.5 Pro84.0

9o3-pro83.8

10o383.0

11GPT-5 Mini82.3

12Claude Opus 4.581.0

Mathematical Computation

38/267 models

AIME: Competition-level math problems

Use Cases: Financial analysis, data computation, statistical reasoning

1GPT-5.2100.0

2GPT-5 Codex99.0

3Gemini 3 Pro Preview95.8

4GPT-5.1 CodeX95.1

5GPT-5.194.0

6Grok 493.5

7o4-mini91.4

8GPT-5 Mini89.9

9Grok 4 Fast89.3

10Gemini 2.5 Pro88.4

11o387.6

12Grok 3 Mini84.9

Image Understanding

1/267 models

MMMU Pro: Multimodal understanding

Use Cases: Image understanding, document OCR, chart analysis

1GPT-5.280.4

AI Agent

38/267 models

Tau2: Autonomous task completion

Use Cases: Automated workflows, multi-tool invocation, complex task decomposition

1GPT-5.298.7

2Grok 3 Mini90.1

3Claude Opus 4.587.0

4GPT-5 Codex87.0

5Gemini 3 Pro Preview86.2

6GPT-5.1 CodeX82.0

7GPT-5.181.1

8o380.5

9GLM-4.677.6

10Grok 475.4

11Grok Code Fast 175.1

12Claude Opus 4.171.1