# BFCL v3 leaderboard

Agentic benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/agentic-bfcl-v3

Berkeley Function Calling Leaderboard v3. Every model the catalog carries a published BFCL v3 value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Tool invocation and schema evaluation |
| Tasks | Function-calling tasks |
| Difficulty | Advanced tool use |
| Published by | [The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models](https://gorilla.cs.berkeley.edu/leaderboard.html) |

A function-calling benchmark for tool selection, schema adherence, and argument correctness, covering single-turn, parallel, irrelevance and multi-turn subsets.

## BFCL v3 ranking

9 models with a published BFCL v3 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Tool invocation and schema evaluation | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Ternary Bonsai 2 27B](https://modelchoice.dev/models/ternary-bonsai-2-27b) | Prism ML | 74.9 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Qwen3 235B-A22B (Reasoning)](https://modelchoice.dev/models/qwen3-235b-a22b-reasoning) | Alibaba | 70.8 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Qwen3 32B (Reasoning)](https://modelchoice.dev/models/qwen3-32b-reasoning) | Alibaba | 70.3 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Qwen3-Coder 480B-A35B](https://modelchoice.dev/models/qwen3-coder-480b-a35b) | Alibaba | 68.7 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Nemotron 3.5 Bolt E4B BF16](https://modelchoice.dev/models/nemotron-3-5-bolt-e4b-bf16) | NVIDIA | 68.5 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Qwen3 235B-A22B](https://modelchoice.dev/models/qwen3-235b-a22b) | Alibaba | 68.0 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Nemotron 3.5 Bolt E4B](https://modelchoice.dev/models/nemotron-3-5-bolt-e4b) | NVIDIA | 67.3 | Observed 2026-11-21 · source benchlm:models |
| 8 | [QwQ-32B](https://modelchoice.dev/models/qwq-32b) | Alibaba | 66.4 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Qwen3 32B](https://modelchoice.dev/models/qwen3-32b) | Alibaba | 63.0 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
