Chatbot Arena Elo · Coding
The Frontier
Best score over time · one chart, every benchmark
Full rankings
46 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 | 1653.9 | |
| 2 | 1593.3 | |
| 3 | 1556.9 | |
| 4 | 1542.3 | |
| 5 | 1542.2 | |
| 6 | 1538.3 | |
| 7 | 1529.2 | |
| 8 | 1521.0 | |
| 9 | 1513.5 | |
| 10 | 1505.5 | |
| 11 | 1504.9 | |
| 12 | 1482.8 | |
| 13 | 1471.3 | |
| 14 | 1466.1 | |
| 15 | 1461.9 | |
| 16 | 1447.0 | |
| 17 | 1440.0 | |
| 18 | 1438.8 | |
| 19 | 1437.1 | |
| 20 | 1434.5 | |
| 21 | 1433.4 | |
| 22 | 1432.1 | |
| 23 | 1411.1 | |
| 24 | 1405.0 | |
| 25 | 1395.1 | |
| 26 | 1394.5 | |
| 27 | 1382.0 | |
| 28 | 1373.9 | |
| 29 | 1364.2 | |
| 30 | 1364.0 | |
| 31 | 1359.3 | |
| 32 | 1356.9 | |
| 33 | 1355.4 | |
| 34 | 1339.6 | |
| 35 | 1336.5 | |
| 36 | 1331.9 | |
| 37 | 1304.7 | |
| 38 | 1287.3 | |
| 39 | 1268.5 | |
| 40 | 1249.5 | |
| 41 | 1249.4 | |
| 42 | 1244.3 | |
| 43 | 1237.8 | |
| 44 | 1204.3 | |
| 45 | 1201.3 | |
| 46 | 1164.8 |
Score distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Benchmarks that track with Chatbot Arena Elo · Coding
Pearson correlation across models scored on both benchmarks. Closer to 1 = strongly predictive.
Frequently asked
About Chatbot Arena Elo · Coding
What does Chatbot Arena Elo · Coding measure?
Chatbot Arena Elo · Coding is a knowledge benchmark in the BenchGecko catalog. 46 AI models have been tested on it. Scores range from 1164.8 to 1653.9 out of 1600.
Which model leads on Chatbot Arena Elo · Coding?
Claude Fable 5 from Anthropic leads Chatbot Arena Elo · Coding with a score of 1653.9. The median score across 46 tested models is 1408.0.
Is Chatbot Arena Elo · Coding saturated?
Yes · the top model on Chatbot Arena Elo · Coding has reached 1653.9 out of 1600, within 5% of the theoretical ceiling. This benchmark is approaching saturation and may be replaced by a harder successor.
Does Chatbot Arena Elo · Coding predict performance on other benchmarks?
Yes · Chatbot Arena Elo · Coding scores correlate 0.86 with Artificial Analysis · Coding Index across 31 shared models. Models that do well on Chatbot Arena Elo · Coding tend to do well on Artificial Analysis · Coding Index.
How often is Chatbot Arena Elo · Coding data refreshed?
BenchGecko pulls updates daily. New model scores on Chatbot Arena Elo · Coding appear as soon as they are published by Epoch AI or the model provider.
- Category
- Knowledge
- Max score
- 1600
- Models
- 46
- Updated
- 2026-06-16
Top on Chatbot Arena Elo · Coding
Claude Fable 5 · 1653.9GLM 5.2 · 1593.3Claude Opus 4.7 · 1556.9Claude Opus 4.8 · 1542.3Claude Opus 4.6 (Fast) · 1542.2More knowledge benchmarks
Same category · related evaluations