HELM Arabic Enterprise - Arabic Finance Mcq: leaderboard
The "Arabic Finance Mcq" subtask of HELM Arabic Enterprise. Stanford HELM's Arabic Enterprise project: business-facing Arabic tasks — content generation, summarisation, translation, dialect handling and customer-support style requests — scored by rubric and judge metrics rather than exact match.
Metric: EM. Source: crfm.stanford.edu. Saturation forecast: Around March 2027. 35 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.1 (2025-11-13) | 100 | #106 |
| 2 | Claude Sonnet 4.6 | 95.65 | #93 |
| 3 | Claude Opus 4.7 | 95.65 | #51 |
| 4 | GPT-5.4 (2026-03-05) | 95.65 | #58 |
| 5 | DeepSeek V4 Pro | 91.3 | #107 |
| 6 | Gemma 4 31B (IT) | 86.96 | #179 |
| 7 | Claude Haiku 4.5 (20251001) | 86.96 | #254 |
| 8 | Mistral Large 3 | 86.96 | #409 |
| 9 | Gemini 2.5 Flash (Non-reasoning) | 86.96 | #247 (Gemini 2.5 Flash) |
| 10 | GPT-5.4 Mini (2026-03-17) | 86.96 | #173 |
| 11 | Qwen 3.5 9B | 82.61 | #388 |
| 12 | Qwen 3.5 397B A17B | 82.61 | #148 |
| 13 | Mistral Large 2 (Nov) Instruct (2411) | 82.61 | #471 |
| 14 | AceGPT-v2-8B-Chat | 82.61 | #740 |
| 15 | Llama 3.3 70B Instruct | 78.26 | #537 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=helm-arabic-enterprise-arabic-finance-mcq · How It Works · Data refreshed daily, snapshot 2026-10-24.