# Does a high BFCL score mean an agent will work in production?

Not fully. BFCL scores whether a model picks the right function and fills the right arguments against a fixed set of curated requests, a controlled setting where the correct call is known in advance. Your production traffic won't phrase requests the way a benchmark does, and your own tool definitions carry quirks BFCL never tested against.

The 70% of the V4 score that's Multi-Turn and Agentic doesn't close that gap either. Both categories run against a handful of mock backends Berkeley built for the benchmark, a file system, a vehicle-control system, a trading bot, a travel-booking system, each with a known starting state and a known correct end state. None of them ever time out, rate-limit, or hand back a malformed result, so a model can top those categories without once having [handled a tool call that actually failed](/answers/reliabilitybench/how-do-you-test-an-agent-against-tool-failures).

---

Sources:
- BFCL changelog, V4 release (Gorilla / ShishirPatil, GitHub): https://github.com/ShishirPatil/gorilla/blob/main/berkeley-function-call-leaderboard/CHANGELOG.md (fetched 2026-09-19)
- BFCL V3: Multi-Turn & Multi-Step Function Calling (Gorilla blog): https://gorilla.cs.berkeley.edu/blogs/13_bfcl_v3_multi_turn.html (fetched 2026-09-19)

Source: https://tessary.ai/answers/bfcl/does-a-high-bfcl-score-mean-an-agent-will-work-in-production
More on Bfcl: https://tessary.ai/answers/bfcl
From Tessary, agent reliability for AI agents in production: https://tessary.ai