Jais 3 Model Cards - APEX-Agents (Pass@1): leaderboard
APEX-Agents long-horizon professional workflows, pass@1, as labelled on the Jais-3-3.7B card (which does not name the task subset). MBZUAI's Institute of Foundation Models reported this on the Jais-3-3.7B model card (released October 15, 2026), comparing it with size-matched reference models. The card states that all reported results use high reasoning effort. Vendor-reported. Metric: Pass@1 (%). Higher is better. Source: https://huggingface.co/collections/IFM/jais-3-6abba9df4f1173ec7ce2929d
Metric: Pass@1 (%). Source: huggingface.co. Saturation forecast: Around July 2028. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 4B | 6.4 | #473 |
| 2 | granite-4.0-h-3B-ar | 0.5 | #1133 |
| 3 | Falcon-H1-3B-Instruct | 0.2 | #1425 |
| 4 | Gemma 4 E2B | 0 | #1076 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=jais-3-model-cards-apex-agents-pass-1 · How It Works · Data refreshed daily, snapshot 2026-10-19.