Forge B
AI benchmark · Reasoning
What is Forge?
Forge (OPT-BENCH) evaluates LLMs on NP-hard optimization problems, scoring both solution feasibility (Success Rate) and solution quality relative to optimal baselines (Quality Ratio).
Math mostly
“the first comprehensive framework for training and evaluating LLMs on NP-hard optimization problems through quality-aware RLVR”
arxiv.org/abs/2605.08905v1 ↗
Paper: arxiv.org/abs/2605.08905v1 ↗
Lineage
Benchmarks this one is built on and built from: versions, subsets, extensions and the indexes that combine them.
Built on
OPT-BENCH original
“Forge (OPT-BENCH) evaluates LLMs on NP-hard optimization problems, scoring both solution feasibility (Success Rate) and solution quality relative to optimal baselines (Quality Ratio).”
Tier 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.
- 21 models scored
- in curated RL directories (1 pt)
On X · unclear, none buzz, from 3 posts about Forge in the last month
Posts naming Forge concern a crypto gaming token and Halo 5 achievements, not the optimality-focused reasoning benchmark; no real discussion of the benchmark exists.
How we got to tier B
- Adoption: 21 models scored. Tier B.
- On X: unclear, none buzz. “Posts naming Forge concern a crypto gaming token and Halo 5 achievements, not the optimality-focused reasoning benchmark; no real discussion of the benchmark exists.” No move.
- In curated RL directories: 1 point, a floor of none.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where Forge sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-11-07 snapshot.