GDP.pdf mean criteria pass rate with tools (GDP.pdf (tools))
We show this table for reference; we do not rank on it.
Professional document understanding with a container, standard libraries, and image cropping.
Benchmark score on GDP.pdf (tools) — September 27, 2026
We compile the GDP.pdf (tools) rows from provider self-reports. Claude Opus 5 leads the table at 85.5%. We do not use these results to rank models overall.
1 modelMultimodal & GroundedCurrentDisplay onlyUpdated September 27, 2026
Benchmark score table (1 model)
ScoreAbout GDP.pdf (tools)
Year
2026
Tasks
100 professional document prompts
Format
Mean criteria pass rate with tools
Difficulty
Professional document reasoning
Section 8.12.4 reports a five-run mean criteria pass rate from Anthropic's corrected internal harness with tools, using Opus 4.7 as judge.
Freshness and provenance
Version
GDP.pdf (tools) 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does GDP.pdf (tools) measure?
Professional document understanding with a container, standard libraries, and image cropping.
Which model scores highest on GDP.pdf (tools)?
Claude Opus 5 by Anthropic currently leads with a score of 85.5% on GDP.pdf (tools).
How many models are evaluated on GDP.pdf (tools)?
1 AI models have been evaluated on GDP.pdf (tools) on BenchLM.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.