Benchmarks · agentic
EdgeBench
Uses the leaderboard's overall score at the longest (12-hour) environment-learning horizon. Score: 12-hour-horizon overall score. Collected by Jake Boggs' benchmark dashboard.
5 models · 5 results · data as of 2026-10-29 · edge-bench.org ↗
Leaderboard
Opus 4.8 max
All results
5 rows| # | Model | Effort | EdgeBench |
|---|---|---|---|
| 1 | Opus 4.8 | max | 51.3% |
| 2 | GPT-5.5 | xhigh | 48.4% |
| 3 | GPT-5.4 | xhigh | 39.3% |
| 4 | GLM 5.1 | max | 37.4% |
| 5 | DeepSeek V4 Pro | max | 31.0% |