pgai.MODEST PRAISE. PUBLIC NUMBERS.
← Back to the scoreboard

MRCRv2 · 128k–256k

Data as of 2026-10-14 / manually checked

4 models · 7 benchmarks · zero composite scores

pretty greatpretty okaynot yetTap a verdict for the number and source.

Finds a requested response in a long conversation with repeated requests.

Why it matters

Tests retrieving the right detail from a large context.

How to read it

Mean match ratio, 8 needles at 128k–256k tokens. Higher is better.

Run by OpenAI. Last checked 2026-10-14.

Visit the benchmark source ↗
MODEL / VENDORMRCRv2 · 128k–256klong context
OpenAI

GPT-5.2 Thinking

Pretty great at coding, abstract reasoning, science, math, long context.

MRCRv2 · 128k–256k
pretty great
77%

Vendor-reported research evaluation, maximum available reasoning effort. See source for harness and sampling.

Source ↗Observed 2026-10-14

The top score means the top sourced score in this snapshot. Different harnesses, budgets and samples can change results. A blank cell is a blank cell.