Which model leads BFCL v2?

Q: Which model leads BFCL v2?

Llama 3.1 Instruct 405B tops the board at 81.1

BFCL v2 Leaderboard — 9 Models Ranked

Pro Mode — raw scores, one benchmark under the lensofficial card harness

The field · 9 measured

63.681.1

9 models measured, most on the official card harness. Llama 3.1 Instruct 405B tops the board at 81.1.

9 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 9Bars show 63.6–81.1 · ◆ solid = first-party or better · outlined = arm's-length

01Llama 3.1 Instruct 405B+1 altMeta81.1———

02Llama 3.1 70B InstructMeta77.5$0.56/M$0.56/M$0.007

03Llama 3.3 70B Instruct+1 altMeta77.3$0.71/M$0.72/M$0.009

04Llama 3.1 Nemotron Ultra 253B V1NVIDIA74.1———

05Qwen3.5 2BAlibaba68.91———

06Llama 3.2 3B InstructMeta67$0.05/M$0.33/M$0.003

07Llama 3.1 8B InstructMeta65.4$0.02/M$0.04/M$0.000

08Qwen3.5 0.8BAlibaba64.02———

09Llama 3.1 Nemotron Nano 8B V1NVIDIA63.6———

◆ solid = independently verified · aggregator attested · vendor attributed — outlined = cross-reference · source-attributed. Dimmed ◆ = confidence inferred. “+N alts” = alternate disclosures in the drawer with why-demoted. Prices per million tokens; $/point = input price ÷ score. Every row opens its model dossier.

Verification: 9 models scored · 0 independently verified · 9 vendor-reported · 0 with source disagreement. How these tiers are assigned