AI Policy Wiki
Dashboard

AI Progress Measurement

medium confidence · updated 2026-06-06

Methodologies and benchmarks for tracking frontier-AI capability over time — METR time-horizons, GPQA, ARC-AGI, AIME, HCAST, GDPval, and the meta-question of which measurements actually capture policy-load-bearing capability change.

AI progress measurement is the set of methodologies and benchmarks used to track frontier-AI capability over time. It is distinct from safety frameworks, which use such measurements as inputs to release decisions, and from alignment auditing, which measures how a model reaches its outputs rather than the level of capability itself. As of the May 2026 capability landscape, different labs cite different benchmarks for different framing purposes, which makes cross-lab comparison difficult.

Benchmarks and measurement methods

Several distinct benchmarks and measurement methods are in active use as of the May 2026 capability landscape, each capturing a different dimension of capability:

BenchmarkMeasures
METR HCAST time-horizonLongest task a model can complete autonomously
GPQAGraduate-level Q&A; reasoning on hard scientific questions
ARC-AGI-2François Chollet's general-intelligence benchmark
AIME 2025Math-olympiad-level problems
HumanEval / BigCodeBenchCoding tasks
GDPvalFrontier-model economic-value evaluation
MMLU-ProMulti-domain knowledge and reasoning
Anthropic Economic IndexReal-world task-substitution rate
METR Task Substitution and UpliftMethodological counterweight to the Anthropic Economic Index

The METR HCAST time-horizon measure is referenced in connection with Claude Opus 4.5, Claude Opus 4.7, and AGI Timelines. ARC-AGI-2 is likewise associated with AGI Timelines. On GPQA, GPT-5.5 Instant scored 85.6%; on AIME 2025, the same model scored 81.2%. HumanEval and BigCodeBench coding tasks are associated with Clawed (Claude Code), and GDPval with Claude Opus 4.7. MMLU-Pro is used as a standard cross-lab measure. The Anthropic Economic Index connects to AI and Productivity. METR's Task Substitution and Uplift work, presented as a methodological counterweight to the Anthropic Economic Index, was queued for ingest as of May 2026.

Methodological tensions

Four recurring tensions complicate capability measurement:

  • Saturation. Most benchmarks reach roughly 90% or higher accuracy within two generations of a frontier release, so new benchmarks are required almost continuously.
  • Contamination. Pre-training data overlap with benchmark sets is a recurring problem, and cross-lab reproducibility suffers as a result.
  • Selection by labs. Each lab cites benchmarks favorable to its own model, so cross-lab comparison requires careful base-rate adjustment.
  • Reasoning versus capability gap. Benchmarks measure outputs, whereas alignment auditing measures how those outputs are produced. The NLA paper (May 6, 2026) shows that the two can diverge.

Relationships

Sources

Stub created 2026-05-11 during the v4.0 backlog-close pass. Foundational ingest candidates: METR HCAST methodology paper; Anthropic Economic Index quarterly publication; Epoch AI capability-trajectory analyses.