CryptoAnalystBench - Temporal Relevance: leaderboard
Metric: Mean judge score from 1 to 10 for temporal relevance (recent data and market conditions for the query's date) on CryptoAnalystBench's 198 production crypto and DeFi analyst queries in 11 categories, one long-form answer per model from the authors' ReAct agent harness with web search and crypto data APIs; DeepSeek V3.1 judges each answer against the tool context it was given; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K2.5 | 8.78 | #139 |
| 2 | GPT-5.2 | 8.77 | #105 |
| 3 | GLM-4.7 | 8.46 | #185 |
| 4 | GPT-OSS-120B | 8.27 | #330 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=cryptoanalystbench-temporal-relevance · How It Works · Data refreshed daily, snapshot 2026-10-11.