aiaimodel.cards
← All benchmarks

GDPval-AA v2.1

Professional work products (documents, analyses, plans) from many occupations, graded by head-to-head comparison; reported as Elo.

Your workloadRAG over docs · 12K in · 600 out · 50K requests/mo · 30% cached
  1. 1Claude Opus 5.5 · Anthropicbest value
    1846 Elo
  2. 2Claude Sonnet 5.5 · Anthropicbest value
    1844 Elo
  3. 3Claude Haiku 5.5 · Anthropicbest value
    1620 Elo

“Best value”: no other model here reports a higher score at a lower cost for your workload. Scores are self-reported by each maker with different settings, so treat close calls as ties.

How each maker reported it

  • Claude Opus 5.5 Table 8.1.A, p.174

    Claude results use adaptive thinking at max effort, averaged over five trials (Terminal-Bench 4.0 at xhigh). Competitor figures come from the developers' own published results.

  • Claude Sonnet 5.5 Table 8.1.A, p.109

    Claude results use adaptive thinking at max effort with default sampling, averaged over five trials. Competitor figures come from the developers' own published system cards or leaderboards.

  • Claude Haiku 5.5 Table 8.1.A, p.111

    Haiku 5.5 results use adaptive thinking at max effort with default sampling, averaged over five trials. FrontierCode is shown at max effort (Sonnet 5.5 scores 52.1 at xhigh). OSWorld is the offline subset; GPT-6 Luna was run by Anthropic on the same tasks. Other competitor figures come from the developers' own published results.

Only each model's own maker's number is shown; scores a maker reports for rival models are left out.