Jais 3 Model Cards - GATmath (IFM-audited): leaderboard
GATmath Arabic aptitude-test math questions, on IFM's audited set. MBZUAI's Institute of Foundation Models reported this on the Jais 3 model cards (released October 15, 2026), comparing each Jais 3 size with size-matched reference models; this board collects all six cards. The cards state that all reported results use high reasoning effort. Vendor-reported. Metric: Accuracy (%). Higher is better. Source: https://huggingface.co/collections/IFM/jais-3-6abba9df4f1173ec7ce2929d
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 29 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 397B A17B | 98.6 | #144 |
| 2 | Gemma 4 31B (IT) | 98.6 | #174 |
| 3 | Qwen3.8-Flash-Next | 98.5 | #69 |
| 4 | Muse Glimmer 30B | 98.5 | #178 |
| 5 | Qwen 3.8 27B | 98.4 | #104 |
| 6 | Nemotron 3 Ultra | 98.4 | #234 |
| 7 | Gemma 4 12B (IT) | 98 | #371 |
| 8 | MiniMax-M3 | 97.8 | #137 |
| 9 | Qwen 3.5 9B | 97.3 | #377 |
| 10 | Qwen 3.5 4B | 95.9 | #473 |
| 11 | gemma-4-E4B-it | 94.4 | #566 |
| 12 | Gemma 4 E2B | 90.5 | #1076 |
| 13 | Qwen 3.5 2B | 87.4 | #1145 |
| 14 | Falcon-H1-34B-Instruct | 63.4 | #666 |
| 15 | Falcon-H1-7B-Instruct | 45.5 | #1043 |
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-gatmath-ifm-audited · How It Works · Data refreshed daily, snapshot 2026-10-19.