ContextEcho: leaderboard
Metric: Delta (self-reported). Source: benchmarklist.com. 23 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2.6 | 100 |
| 2 | Claude Haiku 4.5 | 83 |
| 3 | Claude Sonnet 4.6 | 72 |
| 4 | GPT-5 Mini | 65 |
| 5 | DeepSeek V3 | 65 |
| 6 | Claude Sonnet 4.5 | 63 |
| 7 | Mistral Large | 50 |
| 8 | GPT-4.1 | 47 |
| 9 | Command A | 47 |
| 10 | Mistral Medium | 47 |
| 11 | Gemini 2.5 Flash | 43 |
| 12 | Qwen 3 235B A22B | 40 |
| 13 | GPT-4o | 38 |
| 14 | Gemini 2.5 Pro | 38 |
| 15 | GPT-5 | 28 |
Interactive version: theaggregate.ai/benchmark?slug=contextecho · How It Works · Data refreshed daily, snapshot 2026-09-05.