Find the right AI model

Select your use case — we'll rank the best options for your needs.

716 models tracked across 187 benchmarks. Updated daily.

Coding

Software development & debugging

Research / Data Analysis

Academic research & data science

Creative Writing

Stories, marketing & content

General Assistant

Chat, Q&A & summarization

Agentic Tasks

Tool use & multi-step workflows

Not sure / Explore all

See the best across all categories

Already know what you're looking for? Browse all models

Best Models by Category

Updated daily

Popular

Top-rated for Coding

Ranked by AgMoBench overall score (observed data only)

Gemini 3.1 Pro Preview

Google$4.50/MAgMoBench: 77.6

Also top for Top-rated for Research, Top-rated for Creative Writing, Top-rated for General Use, Top-rated for Agentic Tasks

Claude Opus 4.6 (Non-reasoning, High Effort)

Anthropic$10.00/MAgMoBench: 75.0

Also top for Top-rated for Research, Top-rated for Creative Writing, Top-rated for General Use, Top-rated for Agentic Tasks

Claude Sonnet 4.6 (Non-reasoning, High Effort)

Anthropic$6.00/MAgMoBench: 74.0

Also top for Top-rated for Research, Top-rated for Creative Writing, Top-rated for General Use, Top-rated for Agentic Tasks

See all →

Top-rated for Research

Ranked by AgMoBench overall score (observed data only)

Gemini 3.1 Pro Preview

Google$4.50/MAgMoBench: 77.6

Also top for Top-rated for Coding, Top-rated for Creative Writing, Top-rated for General Use, Top-rated for Agentic Tasks

Claude Opus 4.6 (Non-reasoning, High Effort)

Anthropic$10.00/MAgMoBench: 75.0

Also top for Top-rated for Coding, Top-rated for Creative Writing, Top-rated for General Use, Top-rated for Agentic Tasks

Claude Sonnet 4.6 (Non-reasoning, High Effort)

Anthropic$6.00/MAgMoBench: 74.0

Also top for Top-rated for Coding, Top-rated for Creative Writing, Top-rated for General Use, Top-rated for Agentic Tasks

See all →

Top-rated for Creative Writing

Ranked by AgMoBench overall score (observed data only)

Gemini 3.1 Pro Preview

Google$4.50/MAgMoBench: 77.6

Also top for Top-rated for Coding, Top-rated for Research, Top-rated for General Use, Top-rated for Agentic Tasks

Claude Opus 4.6 (Non-reasoning, High Effort)

Anthropic$10.00/MAgMoBench: 75.0

Also top for Top-rated for Coding, Top-rated for Research, Top-rated for General Use, Top-rated for Agentic Tasks

Claude Sonnet 4.6 (Non-reasoning, High Effort)

Anthropic$6.00/MAgMoBench: 74.0

Also top for Top-rated for Coding, Top-rated for Research, Top-rated for General Use, Top-rated for Agentic Tasks

See all →

Popular

Top-rated for General Use

Ranked by AgMoBench overall score (observed data only)

Gemini 3.1 Pro Preview

Google$4.50/MAgMoBench: 77.6

Also top for Top-rated for Coding, Top-rated for Research, Top-rated for Creative Writing, Top-rated for Agentic Tasks

Claude Opus 4.6 (Non-reasoning, High Effort)

Anthropic$10.00/MAgMoBench: 75.0

Also top for Top-rated for Coding, Top-rated for Research, Top-rated for Creative Writing, Top-rated for Agentic Tasks

Claude Sonnet 4.6 (Non-reasoning, High Effort)

Anthropic$6.00/MAgMoBench: 74.0

Also top for Top-rated for Coding, Top-rated for Research, Top-rated for Creative Writing, Top-rated for Agentic Tasks

See all →

Top-rated for Agentic Tasks

Ranked by AgMoBench overall score (observed data only)

Gemini 3.1 Pro Preview

Google$4.50/MAgMoBench: 77.6

Also top for Top-rated for Coding, Top-rated for Research, Top-rated for Creative Writing, Top-rated for General Use

Claude Opus 4.6 (Non-reasoning, High Effort)

Anthropic$10.00/MAgMoBench: 75.0

Also top for Top-rated for Coding, Top-rated for Research, Top-rated for Creative Writing, Top-rated for General Use

Claude Sonnet 4.6 (Non-reasoning, High Effort)

Anthropic$6.00/MAgMoBench: 74.0

Also top for Top-rated for Coding, Top-rated for Research, Top-rated for Creative Writing, Top-rated for General Use

See all →

Best Value

Best quality-to-price ratio (observed data only)

gpt-oss-20B (high)

OpenAI$0.09/MAgMoBench: 35.3

Gemma 3n E4B Instruct

Google$0.03/MAgMoBench: 8.8

gpt-oss-20B (low)

OpenAI$0.09/MAgMoBench: 29.1

See all →

Fastest

Highest output tokens per second

Mercury 2

Inception$0.38/MSpeed: 927 tok/s

Granite 4.0 H Small

IBM$0.11/MSpeed: 546 tok/s

Gemini 2.5 Flash-Lite (Non-reasoning)

Google$0.17/MSpeed: 374 tok/s

See all →

Find the right AI model

Best Models by Category

Top-rated for Coding

Top-rated for Research

Top-rated for Creative Writing

Top-rated for General Use

Top-rated for Agentic Tasks

Best Value

Fastest

Recently Updated

Find the right AI model

Best Models by Category

Top-rated for Coding

Top-rated for Research

Top-rated for Creative Writing

Top-rated for General Use

Top-rated for Agentic Tasks

Best Value

Fastest

Recently Updated