RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

GPT-3.5-turbo-16K

1 benchmarks · 4 observations · 1 sources

Scores at a glance

1 benchmarks · large dot: GPT-3.5-turbo-16K; small dots: closest models where reported

LoCoMo (Long-Term Conversational Memory) ↗24.1 F1 points
24.124.1

GPT-3.5-turbo-16K · LoCoMo (Long-Term Conversational Memory) · Overall answer F1 · base and long-context comparison ↗

3 more reported results

25.2 F1 points · GPT-3.5-turbo-16K · LoCoMo (Long-Term Conversational Memory) · Overall answer F1 · base and long-context comparison · Evaluating Very Long-Term Conversational Memory of LLM Agents ↗

33.5 F1 points · GPT-3.5-turbo-16K · LoCoMo (Long-Term Conversational Memory) · Overall answer F1 · base and long-context comparison · Evaluating Very Long-Term Conversational Memory of LLM Agents ↗

37.8 F1 points · GPT-3.5-turbo-16K · LoCoMo (Long-Term Conversational Memory) · Overall answer F1 · base and long-context comparison · Evaluating Very Long-Term Conversational Memory of LLM Agents ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

There are not enough shared scored settings to identify close comparisons reliably.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. Evaluating Very Long-Term Conversational Memory of LLM Agents — published result table ↗

    Maharana, Adyasha, Lee, Dong-Ho, Tulyakov, Sergey, Bansal, Mohit, Barbieri, Francesco, Fang, Yuwei · 2024

Names used in source tables

GPT-3.5-turbo-16K