Grok 4.6 ties Claude Opus 5 on finance diligence bench at ~$0.84/task
karinanguyen · x · 2026-08-19
Benchmark results for Grok 4.6 on deep financial research:
- #2 on DiligenceBench finance harness at 52–53%, effectively tied with Claude Opus 5; Sonnet 5 trails at 46.2%
- Notably different behavior: Grok averaged 41 tool calls per task vs 22 for Opus, and 3,293 SEC filing searches vs 486 — broader search helped it find more evidence and follow instructions closely, while Opus was more efficient and sometimes more nuanced
- Cheaper too: $0.84/task vs $1.02 for Opus 5 despite far more searching
- Grok 4.6 also leads the General Qualitative category on Vals' Finance Agent Benchmark v2 (FAB v2), consistent with the broad evidence-gathering style DiligenceBench rewards
Related event: Grok 4.6 Ties for Second on DiligenceBench at Low Cost(2 posts)→
More from Models
- LLM-as-a-Verifier lifts Nemotron 3.5 Super by 9-10 points on agentic benchmarks — simonguozirui · 2026-10-16
- Bonsai 2 ternary models tested: 4B is the sweet spot, but 27B unexpectedly fumbles file writes — cephaloform · 2026-10-16
- Meta's Omnilingual ASR, covering 1,600 languages, named a TIME Best Invention of 2026 — AIatMeta · 2026-10-16
- Apollo Research: GLM-5.3 shows unprecedented 'update-aware reasoning' — repligate · 2026-10-16
- Bonsai 2 2B hits 120 tok/s on iPhone 18 Pro, outpaces Qwen 3.5 2B at half the memory — cephaloform · 2026-10-16
- ChatGPT's quality slips: broken extension and endless Computer Use permission prompts — sytelus · 2026-10-16