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 The collected April 2026 slice has limited frontier-model coverage and is superseded by the current BFCL leaderboard.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
18
tracked on this benchmark
Score band
74.9 – 49.1
best → lowest tracked
Snapshot trend
+17.31
Oct 6 → Oct 13 · 1 models
Leaderboard
Tracked models ranked by Function Calling Accuracy (higher is better).
#Model variant and provenanceRelative to leaderScore
174.9
Version: BFCL v3 (thinking mode)Harness: Not recordedEvaluator: Not recordedObserved: Oct 13, 2026Confidence: Not recordedSource
273.7
Version: BFCL v3 (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
372.9
Version: BFCL-V4, from official model card (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
472.2
Version: BFCL-V4, from official model card (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
571.9
Version: Berkeley Function Calling Leaderboard (BFCL v3)Harness: Not recordedEvaluator: Not recordedObserved: Apr 12, 2026Confidence: Not recordedSource
668.7
Version: Berkeley Function Calling Leaderboard (BFCL v3)Harness: Not recordedEvaluator: Not recordedObserved: Apr 12, 2026Confidence: Not recordedSource
768.5
Version: BFCL-V4 (newest BFCL version), from official model card (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
868.3
Version: BFCL v3 (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
967.3
Version: BFCL-V4, from official model card (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
1066.9
Version: BFCL v3, reasoning on (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Oct 8, 2026Confidence: Not recordedSource
1166.3
Version: BFCL v3 (accuracy%)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
1266.1
Version: BFCL-V4, from official model card (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
1364.5
Version: BFCL v3 (accuracy%)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
1460.8
Version: BFCL v3 (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
1557.6
Version: From official IBM HuggingFace model card (BFCL v3)Harness: Not recordedEvaluator: Not recordedObserved: Oct 6, 2026Confidence: Not recordedSource
1657.6
Version: From official IBM HuggingFace model card (BFCL v3)Harness: Not recordedEvaluator: Not recordedObserved: Oct 6, 2026Confidence: Not recordedSource
1750.3
Version: BFCL-V4, from official model card (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
1849.1
Version: 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