SAHM - Financial Sentiment: leaderboard
Metric: Accuracy (%) on the 80 Arabic financial report sentiment questions of SAHM, an Arabic financial and Sharia-compliance benchmark, exact match after normalizing the chosen option, greedy decoding, mean of three runs; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 81.25 |
| 2 | Gemma 3 27B (IT) | 80 |
| 3 | Llama 3.1 70B Instruct | 80 |
| 4 | GPT-5 | 78.75 |
| 5 | GPT-4o | 77.5 |
| 6 | Claude Sonnet 4.5 | 77.5 |
| 7 | Claude Haiku 4.5 | 77.5 |
| 8 | Qwen 2.5 72B Instruct | 75 |
| 9 | Gemma 3 4B (IT) | 75 |
| 10 | GPT-4o Mini | 75 |
| 11 | Claude Opus 4.5 | 75 |
| 12 | Llama 3.1 8B Instruct | 73.75 |
| 13 | Mixtral 8x7B Instruct | 70 |
| 14 | ALLaM-7B-Instruct-preview | 58.75 |
| 15 | Fanar-1-9B-Instruct | 58.75 |
Interactive version: theaggregate.ai/benchmark?slug=sahm-financial-sentiment · How It Works · Data refreshed daily, snapshot 2026-10-07.