Arena Elo: scores, leaders and methodology
Arena Elo leaderboard data from the index. Human preference rating from pairwise model comparisons. The top score is 1501.9 and the average is 1349.9.
What the data shows
Claude Opus 4.5 Max leads at 1501.9. The gap to the average is 152.0 points, and the gap to the 10th-ranked model is 14.3 points.
The median score is 1373.8. Models above that line are in the upper half of the index for this benchmark.
How to read the ranking
- Use the score to shortlist, not to declare a winner.
- Check price and context for the top candidates.
- Read the benchmark methodology before quoting a score.
- Pair this benchmark with a task-specific evaluation.
Top 20 on Arena Elo
| # | Model | Provider | Score | Input / 1M | Context |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.5 Max | Anthropic | 1501.9 | $20.90 | 1,000,000 |
| 2 | GPT-5.2 Reasoning | OpenAI | 1500.4 | $20.98 | 1,000,000 |
| 3 | GPT-5.2 Turbo | OpenAI | 1500.3 | $20.73 | 1,000,000 |
| 4 | Claude Opus 4.5 Reasoning | Anthropic | 1497.5 | $20.91 | 2,000,000 |
| 5 | GPT-5.2 Max | OpenAI | 1495.3 | $21.39 | 1,000,000 |
| 6 | Gemini 3 Pro Turbo | Google DeepMind | 1494.9 | $19.62 | 400,000 |
| 7 | Grok 4 Max | xAI | 1491.4 | $19.70 | 2,000,000 |
| 8 | Claude Opus 4.5 | Anthropic | 1491.2 | $19.42 | 400,000 |
| 9 | GPT-5.1 Pro | OpenAI | 1490.0 | $19.77 | 200,000 |
| 10 | Grok 4 Reasoning | xAI | 1487.6 | $19.67 | 2,000,000 |
| 11 | Grok 4 Pro | xAI | 1487.5 | $19.00 | 1,000,000 |
| 12 | Claude Sonnet 4.5 Reasoning | Anthropic | 1486.5 | $19.48 | 400,000 |
| 13 | o4 Max | OpenAI | 1486.0 | $19.51 | 2,000,000 |
| 14 | GPT-5.1 Reasoning | OpenAI | 1485.9 | $20.27 | 400,000 |
| 15 | GPT-5.2 Pro | OpenAI | 1485.0 | $21.32 | 2,000,000 |
| 16 | Gemini 3 Pro Reasoning | Google DeepMind | 1485.0 | $19.69 | 200,000 |
| 17 | Gemini 3 Pro Pro | Google DeepMind | 1484.4 | $19.80 | 200,000 |
| 18 | GPT-5.2 Vision | OpenAI | 1484.3 | $19.03 | 1,000,000 |
| 19 | Claude Opus 4.5 Pro | Anthropic | 1483.9 | $20.98 | 200,000 |
| 20 | GPT-5.1 Turbo | OpenAI | 1482.0 | $19.19 | 2,000,000 |
Methodology
This story uses the AI & LLM Index dataset: 600 models, 40 providers and 12 benchmarks. Prices are listed per million tokens. Scores are modelled estimates on a 0–100 scale and are not official benchmark results. Figures are rounded for readability.
Related
FAQ
What does the Arena Elo: scores, leaders and methodology data show?
Arena Elo leaderboard data from the index. Human preference rating from pairwise model comparisons. The top score is 1501.9 and the average is 1349.9.
Are the numbers official?
No. Prices and scores are compiled for this demo index. Benchmark values are modelled estimates, not official results. Verify figures with the provider or benchmark owner before making decisions.
How should I use this ranking?
Use it to form a shortlist. Check the specific model pages, compare price and context, and test the shortlist on your own examples before committing.