Verus-SpecBench — leaderboard
Metric: Pass@1 (self-reported). Source: benchmarklist.com. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 77.8 |
| 2 | GPT-5.3 Codex | 57.8 |
| 3 | Claude Opus 4.6 | 51.1 |
| 4 | DeepSeek V4 Pro | 24.3 |
| 5 | GLM-5.1 | 21.5 |
Interactive version: theaggregate.ai/benchmark?slug=verus-specbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.