TIDE (Evolving Documents, Gold Context) - Scenario Short Answer: leaderboard

Metric: Strict accuracy (%; 562 scenario short-answer questions judged by the council with the hard date gate; 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: Estimated already saturated. 9 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.5 (Thinking)88.04
2GPT-5.2 (Thinking)86.58
3Qwen 3.6 35B A3B84.92
4Gemini 3.5 Flash84.79
5Kimi K2.5 (Thinking)83.56
6Gemma 4 31B (Reasoning)79.42
7GPT-OSS-120B75.46
8GLM-4.674.02

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