LongBench v2 B

AI benchmark · Generalization

Publisher
Official Static Html Table
Domains
Generalization
Tier
B why
Snapshot

What is LongBench v2?

LongBench v2: Measures long-context retrieval, needle finding, summarization, factual grounding, or retrieval-augmented generation quality.

Tier B

B

Established: 15 or more models scored, or curated RL directories rate it.

How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.

  • 44 models scored
  • in curated RL directories (2 pts)

On X · unclear, low buzz, from 1 post about LongBench v2 in the last month

LongBench v2 appears only as one of several evaluation suites in a small research thread on long-context fine-tuning, with no direct commentary.

@Quyet_Azir ↗

How we got to tier B
  1. Adoption: 44 models scored. Tier B.
  2. On X: unclear, low buzz. “LongBench v2 appears only as one of several evaluation suites in a small research thread on long-context fine-tuning, with no direct commentary.” No move.
  3. In curated RL directories: 2 points, a floor of C.
  4. Not yet confirmed by a line from its own site or paper.

A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.

Not on the map yet: no line from its own site or paper places it in a domain.

More Generalization AI benchmarks

Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-11 snapshot.