L3Cube-IndicQuest v2 (English) - Sports: leaderboard
Metric: Accuracy (%; the 273 Sports questions; closed-book short answers to curriculum-grounded India-specific factual questions in English, judged correct or incorrect by Gemma 3 12B against the gold answer (paraphrases and transliterations accepted)). Source: arxiv.org. Saturation forecast: Around December 2026. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash | 81 |
| 2 | GPT-5.4 Mini | 41.8 |
| 3 | Gemma 4 31B | 38.1 |
| 4 | Sarvam 30B | 34.1 |
| 5 | Gemma 2 9B | 27.1 |
| 6 | Llama 3.1 8B | 24.5 |
Interactive version: theaggregate.ai/benchmark?slug=l3cube-indicquest-v2-english-sports · How It Works · Data refreshed daily, snapshot 2026-09-29.