IB-bench

Investment banking analyst benchmark with public tasks covering financial modeling, data extraction, due diligence, document review, and web research workflows.

5rows
overall_scoreprimary metric
2026-05-06sampled

Metadata

ID
ib_bench
Category
Domain Specific
Release
Unknown

Metrics

Overall, Easy, Medium, Hard

Latest Results

Rows are parsed from the public IB-bench static leaderboard. Source model and provider display names are preserved.

Rank Subject Overall Model Match Provenance Sampled
1 claude-opus-4-5-20251101 30.50 Claude Opus 4.5
anthropic-claude-opus-4.5
 		Imported 2026-05-06
2 gpt-5.2-chat 10 GPT-5.2 Chat
openai-gpt-5.2-chat
 		Imported 2026-05-06
3 gpt-5.2-2025-12-11 9.20 GPT-5.2
openai-gpt-5.2
 		Imported 2026-05-06
4 Mistral-Large-3 7 — Imported 2026-05-06
5 gpt-4o 6 GPT-4o
openai-gpt-4o
 		Imported 2026-05-06