Model results

Berkeley Function Calling Leaderboard

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Reviewed recommendation and limits

Start with the relevant BFCL task category for function selection, arguments and multi-turn API use. Inspect category results before the overall score.

BFCL V4 with pinned evaluator revision and interface. Preserve single-turn, multi-turn, web-search and memory categories. Keep V3 and V4 totals separate.. Imported groups below may use different protocols; this review does not certify each run. AST matching, state checks and required-call checks measure different failure modes. Native function calling and prompted interfaces differ. The current V4 methods specify weighted categories, while the leaderboard summary says unweighted; preserve the exact revision and do not recompute a headline from that summary.

Publisher results Multi-turn graders V4 methods and aggregation

← All evaluation groups

BFCL v3

Source: PrismML model card (vendor-reported)
Version: v3
Measurement date: 2026-09-17
Metric: % · Higher is better
Evaluation scope: Vendor-reported; thinking mode; EvalScope + vLLM on NVIDIA H100; temperature 1.0, top_p 0.95, top_k 20; result date not stated by the publisher, dated to the model-card publication; same-run FP16 Qwen3.8-27B reference: 76.74

Positions are withheld because at least one result lacks explicit independent provenance or a documented evaluation scope. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

Ternary Bonsai 2 27B
prism-ml/ternary-bonsai-2-27b-20260918
74.92%
View modelEvidence model-card-reported