TIDE (Evolving Documents, Gold Context) - Temporal MCQ: leaderboard

Metric: Strict accuracy (%; 4-option temporal multiple-choice questions (354), correct when the chosen option matches; TIDE, 3,050 expert-verified questions over 644 Bangladesh customs instruments (1969-2025); free-form answers are judged by a council of Claude Opus 4.6, Gemini 3.5 Flash and GPT-5.1 by majority vote with a hard date gate, deterministic tasks by exact match; strict accuracy without the partial-rubric credit; thinking enabled, temperature 0; gold context: the governing instrument text is supplied in the prompt). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.

Top models

#ModelScore
1GPT-5.2 (Thinking)91.88
2Gemini 3.5 Flash91.07
3Kimi K2.5 (Thinking)90.49
4Qwen 3.6 35B A3B86.76
5Claude Sonnet 4.5 (Thinking)86.08
6Gemma 4 31B (Reasoning)85.37
7GPT-OSS-120B82.28
8GLM-4.677.26

Interactive version: theaggregate.ai/benchmark?slug=tide-evolving-documents-gold-context-temporal-mcq · How It Works · Data refreshed daily, snapshot 2026-09-29.