reasoning benchmark
BFCL_v3_MultiTurn Leaderboard
BFCL_v3_MultiTurn evaluates large language models on multi-turn and multi-step function calling scenarios.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
BFCL_v3_MultiTurn Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score76.80% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelNV | Score66.90% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
BFCL_v3_MultiTurn Highlights
The leading models and scores on this benchmark.
BFCL_v3_MultiTurn Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for BFCL_v3_MultiTurn
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is BFCL_v3_MultiTurn?
What BFCL_v3_MultiTurn measures and how its scores work.
BFCL_v3_MultiTurn is the Berkeley Function Calling Leaderboard (BFCL) V3 MultiTurn benchmark, which evaluates function calling across sequential interactions and conversational turns.
It measures Score as a ratio by assessing sequential function calls, conversational context handling, dynamic function-use decisions, and the resulting state of API systems after function execution.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- BFCL_v3_MultiTurn
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about BFCL_v3_MultiTurn.
Which model scores highest on BFCL_v3_MultiTurn?
MiniMax M2.5 is currently ranked first with 76.80%.
What are the top three models on BFCL_v3_MultiTurn?
The current leaders are MiniMax M2.5 (76.80%) and Nemotron Nano 9B v2 (66.90%).
Which BFCL_v3_MultiTurn model has the lowest official input price?
MiniMax M2.5 has the lowest matched official input price at $0.30 input / $1.2 output per 1M tokens.
Which models are fastest among BFCL_v3_MultiTurn results?
The fastest matched records are MiniMax M2.5 (100.00 tok/s via MiniMax).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.