LLM Stats (Job Bench): leaderboard
LLM Stats mirror of Job Bench, scoring AI agents on realistic professional tasks that require multi-step planning.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around January 2027. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Muse Spark 1.3 | 64.9 | #24 |
| 2 | Muse Spark Open | 61.8 | #54 |
| 3 | Hy4 preview | 61.7 | #38 |
| 4 | Qwen3.8-Flash-Next | 55.7 | #72 |
| 5 | Muse Spark 1.1 | 54.7 | #52 |
| 6 | Qwen 3.8 Max | 53.4 | #35 |
| 7 | Kimi K3 | 52.9 | #30 |
| 8 | Qwen 3.8 27B | 33.4 | #105 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-job-bench · How It Works · Data refreshed daily, snapshot 2026-10-20.