gwBenchmarks — leaderboard
Metric: Waveform (self-reported). Source: benchmarklist.com. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Haiku 4.5 | 59.3 |
| 2 | DeepSeek V4 Pro | 48.3 |
| 3 | GPT-5.4 Mini | 36 |
| 4 | Gemini 3.1 Pro (Preview) | 34.3 |
| 5 | Gemini 3 Flash (Preview) | 21.3 |
| 6 | GPT-5.2 | 19.4 |
| 7 | GPT-5.5 (High) | 17.8 |
| 8 | GPT-5.3 Codex | 17.8 |
| 9 | Claude Opus 4.7 | 16.5 |
| 10 | Claude Opus 4.6 | 14.7 |
| 11 | Claude Sonnet 4.6 | 14.2 |
Interactive version: theaggregate.ai/benchmark?slug=gwbenchmarks · How the rankings work · Data refreshed daily, snapshot 2026-07-22.