JamSet/JamBench — leaderboard
Metric: Task 1a SCS (self-reported). Source: benchmarklist.com. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 46 |
| 2 | Claude Opus 4.6 | 42 |
| 3 | Gemini 3.1 Pro (Preview) | 37 |
| 4 | GLM-5 | 37 |
| 5 | Qwen 3.5 397B A17B | 35 |
| 6 | DeepSeek V4 Pro | 34 |
| 7 | Qwen 3.5 27B | 27 |
Interactive version: theaggregate.ai/benchmark?slug=jamset-jambench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.