Benchmark checker Agents and computer use

Is GDPval-AA still meaningful?

Still useful Checked against the report, 5 November 2026

Yes, with care. Aggregators print it on different scales.

Why still useful: The chapter lists GDPval-AA v2.1 as active. Labs moved to it from OpenAI's original GDPval board.^{[1][1] Introducing Claude Opus 5.5 Anthropic Vendor}

What “Still useful” means

Known problems

Aggregators print different scales (single source).^{[2][2] GDPval-AA BenchLM Secondary}
The original GDPval board is stale. Its last top score was 70.9% win-or-tie for GPT-5.2 (Dec 2025).^{[3][3] Benchmark data bundle Epoch AI Primary}

What to look at instead

The report names no direct successor.

Where it appears in the report

Chapter 1, Benchmarks

Table 3. How each area replaced its saturated benchmarks, oldest first in “Go deeper: Lineage of replacements, by area”
Table 7. General and computer-use agent benchmarks, November 2026 in “Go deeper: General and computer-use agent benchmarks (18)”
Figure 14. OpenAI and Anthropic share only five headline benchmarks

Sources

Copied from the chapter source lists. Each number links back to the source in its chapter.

[1]
Introducing Claude Opus 5.5, Anthropic. It gives Anthropic's launch table and caveats. Vendor anthropic.com Chapter 1, source 12
[2]
GDPval-AA, BenchLM. It lists GDPval-AA leaders on 29 Oct 2026. Secondary benchlm.ai Chapter 1, source 57
[3]
Benchmark data bundle, Epoch AI. Dated scores (5 Nov 2026) and ceilings for most benchmarks here. Primary epoch.ai Chapter 1, source 1