MAWARITH - Share Assignment: leaderboard

Metric: Share assignment score S_shares (0-1, times 100): share of the gold eligible heirs whose predicted fractional share is within 0.1 of the gold share, on the 500 held-out test cases of Arabic Islamic inheritance problems (calculator-generated, expert-annotated), zero-shot Arabic prompt asking for the full structured solution, temperature 0.1, 4,096-token context; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 6 models tracked.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Flash92.9#237
2Qwen 3 32B (Thinking)44.6#424 (Qwen 3 32B)
3GPT-OSS-120B32.7#330
4Fanar-C-2-27B31.4#614

No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.

Interactive version: theaggregate.ai/benchmark?slug=mawarith-share-assignment · How It Works · Data refreshed daily, snapshot 2026-10-11.