Overall AI Model Rankings
This page shows the overall ranking of AI models based on benchmark results across multiple genres. Use it to compare average scores, sample size, and overall performance trends.
Compare Performance by Model
Scoring Criteria / See fairness policy
Latest Updated: May 12, 2026 14:43
Win Rate
Average Score
Win Rate
Average Score
Win Rate
Average Score
Win Rate
Average Score
Win Rate
Average Score
Win Rate
Average Score
Win Rate
Average Score
Win Rate
Average Score
Win Rate
Average Score
Win Rate
Average Score
Win Rate
Average Score
| Ranked Models | Detail | ||||||
|---|---|---|---|---|---|---|---|
| #1 | Claude Opus 4.7 NEW | Anthropic |
86%
|
86
|
19 | 22 | View scores and evaluation for Claude Opus 4.7 |
| #2 | Claude Opus 4.6 Retired | Anthropic |
84%
|
87
|
82 | 98 | View scores and evaluation for Claude Opus 4.6 |
| #3 | GPT-5.5 NEW | OpenAI |
76%
|
86
|
16 | 21 | View scores and evaluation for GPT-5.5 |
| #4 | GPT-5.2 Retired | OpenAI |
75%
|
87
|
77 | 102 | View scores and evaluation for GPT-5.2 |
| #5 | Claude Sonnet 4.6 | Anthropic |
73%
|
85
|
74 | 101 | View scores and evaluation for Claude Sonnet 4.6 |
| #6 | GPT-5 mini | OpenAI |
71%
|
84
|
72 | 101 | View scores and evaluation for GPT-5 mini |
| #7 | GPT-5.4 NEW | OpenAI |
71%
|
85
|
73 | 103 | View scores and evaluation for GPT-5.4 |
| #8 | Claude Haiku 4.5 | Anthropic |
52%
|
80
|
53 | 102 | View scores and evaluation for Claude Haiku 4.5 |
| #9 | Gemini 2.5 Pro |
9%
|
78
|
10 | 106 | View scores and evaluation for Gemini 2.5 Pro | |
| #10 | Gemini 2.5 Flash |
4%
|
74
|
4 | 106 | View scores and evaluation for Gemini 2.5 Flash | |
| #11 | Gemini 2.5 Flash-Lite |
3%
|
73
|
3 | 104 | View scores and evaluation for Gemini 2.5 Flash-Lite |
Compare by Genre
You can review top models by genre. Open each card to view its detailed ranking page.
Discussion
Top 3 models
Creative Writing
Top 3 models
Coding
Top 3 models
System Design
Top 3 models
Education Q&A
Top 3 models
Explanation
Top 3 models
Summarization
Top 3 models
Idea Generation
Top 3 models
Roleplay
Top 3 models
Business Writing
Top 3 models
Planning
Top 3 models
Analysis
Top 3 models
Score Breakdown
Top model per criterion.
Clarity
Instruction Following
Persuasiveness
Logic
Rebuttal Quality
Structure
Originality
Appropriateness
Audience Fit
Diversity
Latest AI Picks
Based on the latest Orivel benchmark results, this page helps you review top-performing models and genre-specific recommendations in one place.
AI Pricing Comparison
If price matters when choosing an AI, see the AI Pricing Comparison & Best Value Ranking. You can compare the price and performance of major models in one place.