# JobBench — AI model rankings

Tests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better.

8 tracked models have a published JobBench score. Higher is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | Muse Spark 1.3 | Meta | 64.9% | Lab | Sep 2 2026 |
| 2 | Qwen3.8-Max-0902 | Qwen | 64% | Lab | Sep 2 2026 |
| 3 | Qwen3.8-Flash-Next | Qwen | 55.7% | Lab | Aug 26 2026 |
| 4 | Muse Spark 1.1 | Meta | 54.7% | Lab | Jul 9 2026 |
| 5 | Qwen3.8-Max | Qwen | 53.4% | Lab | Aug 3 2026 |
| 6 | Kimi K3 | Moonshot AI | 52.9% | Lab | Jul 16 2026 |
| 7 | Qwen3.8-27B | Qwen | 33.4% | Lab | Aug 14 2026 |
| 8 | Muse Spark | Meta | 17% | Lab | Apr 8 2026 |


---

Canonical page: https://aireleasetracker.com/benchmark/jobbench
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.