EnterpriseArena runs 11 LLMs through a 132-month CFO simulation tracking survival, terminal valuation, and book-closing rates. Only Qwen3.5-9B survives 80% of runs; GPT-5.4 and DeepSeek-V3.1 hit 0%. Human experts achieve 100% survival at 5× the terminal value. The critical bottleneck: LLMs skip ledger reconciliation 80% of the time, acting on stale financial state.
WildToolBench (ICLR 2026) evaluates 57 LLMs on 1,024 tasks drawn from real user behavior — no model exceeds 15% session accuracy, with compositional orchestration, hidden intent, and instruction transitions as the three sharpest failure modes.
JSONSchemaBench tests 9,558 real-world JSON schemas against six constrained decoding frameworks and finds that schema complexity causes coverage to collapse from 86% on simple schemas to 3% on complex ones, with XGrammar silently emitting 38 non-compliant outputs and no framework covering all 45 JSON Schema feature categories.
FinMCP-Bench evaluates six LLM models on 613 real-world financial tool-use tasks backed by 65 MCP servers — the best model scores 3.08% exact match on multi-turn tasks, revealing a 20× performance collapse from single-tool to multi-turn scenarios.
FinTrace benchmarks 13 LLMs on 800 expert-annotated financial task trajectories across 9 metrics, finding that frontier models achieve strong tool selection (F1 ~0.9) but score only 3.23/5 on information utilization — the step where agents reason over what tools return.
FinToolBench поєднує 760 активних фінансових інструментів API з 295 виконуваними запитами для тестування агентів LLM на реальних фінансових завданнях — виявивши, що консервативна частота викликів GPT-4o у 22,7% забезпечує вищу якість відповідей (CSS 0,670), ніж агресивна TIR Qwen3-8B у 87,1%, тоді як невідповідність намірів перевищує 50% у всіх протестованих моделях.
OmniEval (EMNLP 2025) benchmarks RAG systems across 5 task types × 16 financial topics using 11.4k auto-generated test cases. The best systems achieve only 36% numerical accuracy — concrete evidence that RAG pipelines need validation layers before writing to structured financial ledgers.
A training-free inference-time calibration subtracts positional bias from LLM attention weights, recovering up to 15 percentage points of RAG accuracy when retrieved documents are buried mid-context — and what it means for finance-specific agent pipelines.
ReDAct runs a small model by default and escalates to an expensive model only when token-level perplexity signals uncertainty, achieving 64% cost savings over GPT-5.2-only while matching or exceeding its accuracy — a directly applicable pattern for Beancount transaction-categorization agents.
OpenHands is an MIT-licensed, Docker-sandboxed agent platform where CodeAct achieves 26% on SWE-Bench Lite — a sobering benchmark that establishes what AI agents can reliably do today, and why the first productive finance deployments should be tightly scoped rather than autonomous.
Take control of your finances with our open-source double-entry accounting system. Start your ledger today.
© 2019 - 2026 Beancount.io
