agents benchmark
BFCL-V4 Leaderboard
Berkeley Function Calling Leaderboard V4 (BFCL-V4) evaluates LLMs on their ability to accurately call functions and APIs, including simple, multiple, parallel, and nested function calls across diverse programming scenarios.
Updated Aug 17, 2026
Models15
Model coverage15
MetricScore
EvidenceB
BFCL-V4 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score75.0% | Percentile100.0% | Participants15 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score72.9% | Percentile92.9% | Participants15 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score72.9% | Percentile85.7% | Participants15 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score72.2% | Percentile78.6% | Participants15 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score68.5% | Percentile71.4% | Participants15 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score67.3% | Percentile64.3% | Participants15 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score66.1% | Percentile57.1% | Participants15 | EvidenceC | Evaluated |
| Rank08 | ModelAM Nova 2 ProAmazon | Score61.6% | Percentile50.0% | Participants15 | EvidenceC | Evaluated |
| Rank09 | ModelAMNova 2 LiteAmazon | Score60.3% | Percentile42.9% | Participants15 | EvidenceC | Evaluated |
| Rank10 | ModelAMNova 2 OmniAmazon | Score58.3% | Percentile35.7% | Participants15 | EvidenceC | Evaluated |
| Rank11 | ModelLA | Score56.9% | Percentile28.6% | Participants15 | EvidenceC | Evaluated |
| Rank12 | ModelAC | Score50.3% | Percentile21.4% | Participants15 | EvidenceC | Evaluated |
| Rank13 | ModelAC | Score43.6% | Percentile14.3% | Participants15 | EvidenceC | Evaluated |
| Rank14 | ModelLA | Score32.5% | Percentile7.1% | Participants15 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score25.3% | Percentile0.0% | Participants15 | EvidenceC | Evaluated |
BFCL-V4 Highlights
The leading models and scores on this benchmark.
BFCL-V4 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for BFCL-V4
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis bfcl-v4 AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ACQwen3.7 MaxAlibaba Cloud / Qwen Team
- Score
- 75.0%
- Price
- $2.5 input / $7.5 output per 1M tokens
- Speed
- Up to 5.8 tok/s via Together
Strengths
- Ranks #1 of 15 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures BFCL-V4, not total model capability
- 02ACQwen3.5-397B-A17BAlibaba Cloud / Qwen Team
- Score
- 72.9%
- Price
- $0.60 input / $3.6 output per 1M tokens
Strengths
- Ranks #2 of 15 compared models
- 93th percentile on this benchmark
- C evidence result
Considerations
- This result measures BFCL-V4, not total model capability
- 03ACQwen3.7-PlusAlibaba Cloud / Qwen Team
- Score
- 72.9%
- Price
- $0.50 input / $3.0 output per 1M tokens
Strengths
- Ranks #3 of 15 compared models
- 86th percentile on this benchmark
- C evidence result
Considerations
- This result measures BFCL-V4, not total model capability
- 04ACQwen3.5-122B-A10BAlibaba Cloud / Qwen Team
- Score
- 72.2%
- Price
- $0.40 input / $3.2 output per 1M tokens
Strengths
- Ranks #4 of 15 compared models
- 79th percentile on this benchmark
- C evidence result
Considerations
- This result measures BFCL-V4, not total model capability
- 05ACQwen3.5-27BAlibaba Cloud / Qwen Team
- Score
- 68.5%
- Price
- $0.30 input / $2.4 output per 1M tokens
- Speed
- Up to 6.7 tok/s via Novita
Strengths
- Ranks #5 of 15 compared models
- 71th percentile on this benchmark
- C evidence result
Considerations
- This result measures BFCL-V4, not total model capability
Selection summary
Best AI Models for BFCL-V4
Qwen3.7 Max currently leads BFCL-V4 with 75.0%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is BFCL-V4?
What BFCL-V4 measures and how its scores work.
Berkeley Function Calling Leaderboard V4 (BFCL-V4) evaluates LLMs on their ability to accurately call functions and APIs, including simple, multiple, parallel, and nested function calls across diverse programming scenarios.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- BFCL-V4
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- bfcl-v4|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about BFCL-V4.
Which model scores highest on BFCL-V4?
Qwen3.7 Max is currently ranked first with 75.0%.
What does BFCL-V4 measure?
Berkeley Function Calling Leaderboard V4 (BFCL-V4) evaluates LLMs on their ability to accurately call functions and APIs, including simple, multiple, parallel, and nested function calls across diverse programming scenarios.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
15 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.