MSQA - Thai: leaderboard
MSQA asks short culture-specific questions written by native speakers in their own language, each with one verifiable answer grounded in local sources. This board covers the Thai-language questions. Answers are free-form, judged for containing the gold answer, and scored as the harmonic mean of the correct share and the correct-given-attempted share, so both wrong answers and refusals cost points (ByteDance Seed, Nanjing University and M-A-P, 2026).
Metric: F-score (%; harmonic mean of CO, the share of fully correct answers, and CGA, the correct share of attempted answers, over the 95 Thai-language questions; free-form answers to natively sourced culture-specific short questions asked in their own language, five runs per model, scored by a Gemini-3.1-Pro gold-answer containment judge). Source: arxiv.org. Saturation forecast: Around February 2027. 21 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 71 | #94 |
| 2 | GPT-5.5 | 58.5 | #49 |
| 3 | Claude Opus 4.6 | 51 | #102 |
| 4 | DeepSeek V4 Pro | 49.5 | #188 |
| 5 | GPT-5.4 | 48.6 | #123 |
| 6 | Seed 2.1 Pro | 45.9 | #135 |
| 7 | GPT-5.2 (High) | 45.1 | #176 (GPT-5.2) |
| 8 | Gemini 2.5 Flash | 40.2 | #453 |
| 9 | Qwen 3.5 Plus (Thinking) | 39.3 | #232 (Qwen 3.5 Plus) |
| 10 | DeepSeek V3.2 | 34.8 | #406 |
| 11 | GLM-5 | 34.8 | #260 |
| 12 | Seed 2.0 Lite | 34.3 | #289 |
| 13 | Seed 2.0 Pro (High) | 30.9 | #211 (Seed 2.0 Pro) |
| 14 | Kimi K2.6 | 28.3 | #178 |
| 15 | Kimi K2.5 | 27.9 | #256 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=msqa-thai · How It Works · Data refreshed daily, snapshot 2026-11-13.