DiligenceBench benchmarks equity-research agents, with Muse Spark 1.1 reaching 57.4%

karinanguyen · x · 2026-07-22

DiligenceBench benchmarks equity-research agents

A new benchmark, DiligenceBench, evaluates whether AI agents can do real public-equity research.

• The charted results show Meta Muse Spark 1.1 leading the finance harness at 57.4%, followed by GLM 5.2, Sonnet 4.6, and GPT-5.6 Sol.
• The authors found that stronger models benefit most from generic tools that unlock execution, while weaker models need more opinionated, domain-specific scaffolding.
• For Inkling, a generic sandbox barely helped (20.9% → 22.5%), but the finance harness raised it to 32.8%, with the biggest gain coming from factual accuracy.
• The benchmark also changes the price–performance frontier: most models get both better and cheaper under the finance harness, with GLM 5.2 leading on absolute performance and MiniMax M3 appearing among the efficiency winners.

Original post →

More from Venture

• Anthropic S-1 reveals Dario can handpick a board majority forever via founder control — cocktailpeanut · 2026-10-27
• Anthropic files S-1 with SEC, kicking off its long-awaited IPO as a public benefit corporation — matt_slotnick · 2026-10-27
• Unitard Index tracks 440 fallen unicorns with over $1.4 trillion in lost valuation — AccBalanced · 2026-10-27
• a16z's Martin Casado: Anthropic S-1 shows we're at 'peak schadenfreude' — ignore the FUD — AccBalanced · 2026-10-27
• Anthropic S-1: CSP marketplace revenue jumped from 11% to 48% in three years — AccBalanced · 2026-10-27
• Indie Dev Builds Open-Source Social Scheduler, Cutting $99/Month to Under $1 — fekdaoui · 2026-10-27

Venture channel →