Model Leaderboard

Compare AI models by capability and cost-effectiveness

Popular Comparisons

Custom Comparison Browse All Models

Programming & Development

59/272 models

LiveCodeBench: Real-world coding tasks

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

1GPT-5.186.4

2o4-mini86.1

3GPT-5 Codex85.0

4GPT-5.1 CodeX84.5

5GPT-5 Mini83.7

6Grok 4 Fast83.5

7Grok 481.7

8Gemini 2.5 Pro80.8

9o380.2

10GPT-5 Nano78.3

11DeepSeek V3.1 (250821)77.8

12DeepSeek R1 (250528)77.5

13Doubao Seed 1.6 (250615)75.8

14o3-mini73.8

15Claude Opus 4.573.5

Logical Reasoning

61/272 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

3Gemini 3 Flash Preview33.7

4GPT-5.126.4

5GPT-5 Codex25.5

6Grok 423.9

7GPT-5.1 CodeX23.5

8Gemini 2.5 Pro21.6

9o320.0

10GPT-5 Mini19.8

11o4-mini17.6

12Grok 4 Fast17.6

13DeepSeek R1 (250528)15.2

14Claude Sonnet 4.513.7

15Claude Opus 4.512.9

Knowledge Q&A

63/272 models

MMLU Pro: Broad knowledge assessment

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

1Gemini 3 Pro Preview91.8

2GPT-5.289.6

3Gemini 2.5 Pro89.5

4Claude Sonnet 4.589.1

5Claude Opus 4.189.0

6Claude Opus 4.588.4

7Claude Opus 487.0

8Grok 487.0

9Grok 4 Fast86.8

10Gemini 2.5 Flash86.6

11Doubao 1.5 Thinking Pro (250415)86.2

12GPT-5.1 CodeX86.0

13GPT-5.186.0

14GPT-5 Codex86.0

15o385.6

Scientific Research

67/272 models

GPQA: Graduate-level science questions

Use Cases: Academic research, scientific writing, experiment design

1GPT-5.292.4

2Gemini 3 Pro Preview91.9

3Gemini 3 Flash Preview90.4

4GPT-5 Pro88.6

5GPT-5.187.9

6Grok 487.4

7Gemini 2.5 Pro86.4

8GPT-5.1 CodeX86.0

9GPT-5 Codex84.3

10Grok 4 Fast84.3

11o3-pro83.8

12Claude Sonnet 4.583.4

13o383.0

14Gemini 2.5 Flash82.8

15GPT-5 Mini82.3

Mathematical Computation

51/272 models

AIME: Competition-level math problems

Use Cases: Financial analysis, data computation, statistical reasoning

1GPT-5.2100.0

2GPT-5 Codex99.0

3GPT-5 Pro97.2

4Gemini 3 Flash Preview95.2

5GPT-5.1 CodeX95.1

6Gemini 3 Pro Preview95.0

7GPT-5.194.0

8Grok 493.5

9Grok 4 Fast91.9

10o4-mini91.4

11GPT-5 Mini89.9

12DeepSeek V3.1 (250821)89.2

13Gemini 2.5 Pro88.0

14o387.6

15o3-mini87.0

AI Agent

46/272 models

Tau2: Autonomous task completion

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

1Gemini 3 Pro Preview90.7

2Gemini 3 Flash Preview90.2

3Grok 3 Mini90.1

4Claude Sonnet 4.587.2

5GPT-5 Codex87.0

6Claude Opus 4.587.0

7GPT-5.1 CodeX82.0

8GPT-5.181.1

9o380.5

10Gemini 2.5 Flash79.5

11Gemini 2.5 Pro77.8

12GLM-4.677.6

13Grok 475.4

14Grok Code Fast 175.1

15Kimi K2 Instruct 090572.8

SciCode

58/272 models

SciCode: Scientific coding challenges

Use Cases: Scientific computing, research code, data analysis scripts

1Claude Opus 4.547.0

2o4-mini46.2

3Grok 445.9

4Grok 4 Fast44.3

5GPT-5.143.3

6Claude Sonnet 4.543.1

7Gemini 2.5 Pro42.4

8Claude Opus 441.2

9Claude Opus 4.141.1

10o341.0

11GPT-5 Codex40.8

12DeepSeek R1 (250528)40.8

13Grok 3 Mini40.8

14GPT-5.1 CodeX40.5

15GPT-4.1 Mini40.1

Terminal

47/272 models

Terminal-Bench: Command-line operations

Use Cases: Shell scripting, system administration, DevOps automation

1GPT-5.1 CodeX Max57.5

2Gemini 3 Pro Preview54.2

3Gemini 3 Flash Preview47.6

4Claude Sonnet 4.542.8

5GPT-5.142.4

6Claude Opus 4.538.5

7Grok 437.7

8GPT-5 Codex35.8

9o334.7

10Gemini 2.5 Pro32.6

11GPT-5.1 CodeX32.5

12Claude Opus 4.132.1

13GPT-5 Mini31.0

14GLM-4.627.0

15Claude Sonnet 425.7

Instruction

46/272 models

IFEval: Instruction following accuracy

Use Cases: Precise task execution, format compliance, constraint adherence

1o3-mini93.4

2DeepSeek Reasoner87.5

3Doubao 1.5 Thinking Pro (250415)86.4

4Grok 383.8

5GPT-5 Mini76.1

6GPT-5 Codex74.0

7GPT-5.173.3

8o371.3

9GPT-5.1 CodeX70.0

10o4-mini68.5

11GPT-5 Nano67.6

12Claude Opus 4.155.3

13Grok 453.3

14Doubao Seed 1.6 (250615)50.8

15Grok 4 Fast50.7