BFCL v3supersededAgentsTool use
BFCL v3: Berkeley Function Calling Leaderboard v3
Metric: Function Calling Accuracy (higher is better)Introduced: 2023Superseded by: bfcl
Version 3 of Berkeley Function Calling Leaderboard, evaluating model accuracy on function and API calls. The collected April 2026 slice has limited frontier-model coverage and is superseded by the current BFCL leaderboard.
Models ranked
14
tracked on this benchmark
Score band
73.7 – 49.1
best → lowest tracked
Snapshot trend
-5.30
Apr 12 → Jun 7 · 12 models
Leaderboard
Tracked models ranked by Function Calling Accuracy (higher is better).
#Model variant and provenanceRelative to leaderScore
1
Granite 4.1 30B
73.7Version: BFCL v3 (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
2
Qwen3.5-397B-A17B
72.9Version: BFCL-V4, from official model card (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
3
Qwen3.5-122B-A10B
72.2Version: BFCL-V4, from official model card (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
4
Qwen3-Max
71.9Version: Berkeley Function Calling Leaderboard (BFCL v3)Harness: Not recordedEvaluator: Not recordedObserved: Apr 12, 2026Confidence: Not recordedSource
5
Qwen3-Coder-480B-A35B-Instruct
68.7Version: Berkeley Function Calling Leaderboard (BFCL v3)Harness: Not recordedEvaluator: Not recordedObserved: Apr 12, 2026Confidence: Not recordedSource
6
Qwen3.5-27B
68.5Version: BFCL-V4 (newest BFCL version), from official model card (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
7
Granite 4.1 8B
68.3Version: BFCL v3 (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
8
Qwen3.5-35B-A3B
67.3Version: BFCL-V4, from official model card (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
9
Mellum2 12B
66.3Version: BFCL v3 (accuracy%)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
10
Qwen3.5-9B
66.1Version: BFCL-V4, from official model card (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
11
Kimi K2.5
64.5Version: BFCL v3 (accuracy%)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
12
Granite 4.1 3B
60.8Version: BFCL v3 (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
13
Qwen3.5-4B
50.3Version: BFCL-V4, from official model card (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
14
LFM2.5 1.2B Instruct
49.1Version: BFCLv3 (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
How to read this benchmark
This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.
Trust this score when
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- The model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Be cautious when
- There is only one benchmark snapshot or the dataset appears stale.
- The benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Related benchmarks
Last reviewed: Apr 26, 2026