A 600k-token relationship test compares how models comment on personal context
cis_female · x · 2026-07-21
A user shared evaluation results for a relationship-understanding prompt, graded by Fable 5.
The post says the test used about 600k tokens of messages with a friend over the past year, then asked multiple models to comment on the relationship with a few specific prompts.
The actual score table is shown in the attached image, but the post itself is mainly a pointer to the eval setup and results.
Related event: Testing LLMs on Relationship Understanding with 600k Tokens(6 posts)→
More from Models
- 6TB of Fable data sold with leaked SSH keys, cloud creds tied to Xiaomi, Huawei, NIO — teortaxesTex · 2026-09-11
- AI Sextet offers 6 models free and unlimited for 14 days, including DeepSeek and Qwen — airesearch12 · 2026-09-11
- BullshitBench update: GPT-6-Astra beats all prior OpenAI models but still trails Anthropic — scaling01 · 2026-09-11
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11