Arena Elo: leaderboard, scores and methodology
Human preference rating from pairwise model comparisons.
Top 10
Bars are scaled to the highest observed score. The leader sets the pace; the spread below it shows how much separation exists in this benchmark.
Leaderboard
| # | Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.5 Max | Anthropic | 1000000 | $20.90 | 87.8 |
| 2 | GPT-5.2 Reasoning | OpenAI | 1000000 | $20.98 | 87.5 |
| 3 | GPT-5.2 Turbo | OpenAI | 1000000 | $20.73 | 87.4 |
| 4 | Claude Opus 4.5 Reasoning | Anthropic | 2000000 | $20.91 | 88.2 |
| 5 | GPT-5.2 Max | OpenAI | 1000000 | $21.39 | 89.2 |
| 6 | Gemini 3 Pro Turbo | Google DeepMind | 400000 | $19.62 | 86.4 |
| 7 | Grok 4 Max | xAI | 2000000 | $19.70 | 86.6 |
| 8 | Claude Opus 4.5 | Anthropic | 400000 | $19.42 | 87.7 |
| 9 | GPT-5.1 Pro | OpenAI | 200000 | $19.77 | 87.8 |
| 10 | Grok 4 Reasoning | xAI | 2000000 | $19.67 | 87.8 |
| 11 | Grok 4 Pro | xAI | 1000000 | $19.00 | 85.4 |
| 12 | Claude Sonnet 4.5 Reasoning | Anthropic | 400000 | $19.48 | 87.7 |
| 13 | o4 Max | OpenAI | 2000000 | $19.51 | 86.2 |
| 14 | GPT-5.1 Reasoning | OpenAI | 400000 | $20.27 | 88.3 |
| 15 | GPT-5.2 Pro | OpenAI | 2000000 | $21.32 | 89.6 |
| 16 | Gemini 3 Pro Reasoning | Google DeepMind | 200000 | $19.69 | 87.5 |
| 17 | Gemini 3 Pro Pro | Google DeepMind | 200000 | $19.80 | 87.3 |
| 18 | GPT-5.2 Vision | OpenAI | 1000000 | $19.03 | 87.4 |
| 19 | Claude Opus 4.5 Pro | Anthropic | 200000 | $20.98 | 89.1 |
| 20 | GPT-5.1 Turbo | OpenAI | 2000000 | $19.19 | 86.1 |
| 21 | Claude Sonnet 4.5 | Anthropic | 400000 | $17.84 | 86.0 |
| 22 | GPT-5.1 Max | OpenAI | 2000000 | $20.50 | 87.9 |
| 23 | GPT-5.2 | OpenAI | 2000000 | $19.71 | 88.0 |
| 24 | Gemini 3 Pro Max | Google DeepMind | 2000000 | $20.57 | 87.9 |
| 25 | Grok 3 Max | xAI | 2000000 | $17.66 | 85.9 |
| 26 | Claude Sonnet 4.5 Max | Anthropic | 1000000 | $19.90 | 87.2 |
| 27 | Gemini 3 Flash Turbo | Google DeepMind | 200000 | $17.07 | 84.1 |
| 28 | o4 Vision | OpenAI | 200000 | $17.01 | 84.5 |
| 29 | o4 Reasoning | OpenAI | 1000000 | $19.69 | 87.5 |
| 30 | Gemini 2.5 Pro Reasoning | Google DeepMind | 128000 | $16.81 | 83.8 |
| 31 | o3 Pro | OpenAI | 400000 | $17.89 | 85.8 |
| 32 | o4 Pro | OpenAI | 1000000 | $19.37 | 87.3 |
| 33 | o4 | OpenAI | 2000000 | $17.74 | 85.4 |
| 34 | Claude Opus 4.5 Turbo | Anthropic | 2000000 | $19.57 | 85.7 |
| 35 | Gemini 3 Flash Pro | Google DeepMind | 400000 | $17.71 | 84.8 |
| 36 | Claude Sonnet 4.5 Pro | Anthropic | 1000000 | $18.73 | 86.7 |
| 37 | o4 Turbo | OpenAI | 2000000 | $19.34 | 86.6 |
| 38 | Qwen3-Max Max | Alibaba Cloud | 400000 | $18.53 | 85.9 |
| 39 | GPT-4.1 Max | OpenAI | 400000 | $17.34 | 84.7 |
| 40 | Grok 4 Turbo | xAI | 1000000 | $19.21 | 86.7 |
| 41 | GPT-4.1 Reasoning | OpenAI | 1000000 | $16.97 | 83.8 |
| 42 | Qwen3-Max Pro | Alibaba Cloud | 400000 | $18.87 | 86.2 |
| 43 | o3 Max | OpenAI | 2000000 | $17.82 | 84.8 |
| 44 | Claude 3.7 Sonnet Reasoning | Anthropic | 128000 | $16.30 | 83.7 |
| 45 | Gemini 2.5 Pro Turbo | Google DeepMind | 1000000 | $16.32 | 83.9 |
| 46 | GPT-5.1 | OpenAI | 2000000 | $19.01 | 86.0 |
| 47 | GPT-5.1 Vision | OpenAI | 400000 | $17.76 | 84.8 |
| 48 | DeepSeek-V3.2 Chat | DeepSeek | 1000000 | $5.80 | 82.5 |
| 49 | Claude Sonnet 4.5 Turbo | Anthropic | 1000000 | $18.37 | 85.9 |
| 50 | Claude 3.7 Sonnet Max | Anthropic | 128000 | $16.88 | 83.7 |
Methodology
Arena Elo is included as a preference benchmark with a typical score range of 800 to 1600. The values in this index are deterministic modelled estimates generated for comparison at scale. They are not official leaderboard results and should not be quoted as vendor benchmarks.
Each model receives a score derived from its capability tier, release generation and benchmark difficulty. Scores are normalised to a 0–100 scale so that models from different providers can be placed side by side. The average shown is the arithmetic mean across all 600 scored models.
Read the leaderboard as a relative map. A five-point gap is meaningful at the top and less meaningful in the middle of the distribution. Pair the score with price and context data before choosing a model.
How to use this leaderboard
- Use the top 10 to shortlist candidates, not to declare a winner.
- Check whether the leader is open weights or proprietary before assuming you can deploy it.
- Compare the score against input and output price on each model page.
- Look at the model's scores on related benchmarks before trusting a single number.
FAQ
What is Arena Elo?
Human preference rating from pairwise model comparisons.
Who leads Arena Elo?
Claude Opus 4.5 Max from Anthropic leads this index with a score of 1501.9, followed by GPT-5.2 Reasoning at 1500.4.
What is a good Arena Elo score?
The top quartile starts around 1419.9. The index average is 1349.9, so a score above 1419.9 is a strong result relative to this dataset.
How are Arena Elo scores calculated?
The values are modelled estimates on a 800–1600 scale, generated from capability tier, release generation and benchmark difficulty. They are not official leaderboard results.
Which models are included?
All 600 models in the index are scored on Arena Elo, across 40 providers and every model category.