Atlas

Benchmarks

← All benchmarks

OpenAI-MRCR 2-needle - 256K

General QA · 2025-04-14

OpenAI-MRCR (multi-round co-reference resolution) inserts two identical needle requests into a long synthetic conversation and asks the model to reproduce the response to a specified needle. This row is the 256K bin, averaging the string match ratio over prompts with 128K-256K input tokens (256K = 262,144 tokens). Higher is better.

Top models (higher is better)

ModelScore
GPT-586.8
GPT-5 Mini58.8
GPT-4.156.2
GPT-4.1 Mini45.5
GPT-5 Nano34.9
GPT-4.1 Nano22.6
Loading Atlas data…