Model results
Berkeley Function Calling Leaderboard
Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.
Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.
Reviewed recommendation and limits
Start with the relevant BFCL task category for function selection, arguments and multi-turn API use. Inspect category results before the overall score.
BFCL V4 with pinned evaluator revision and interface. Preserve single-turn, multi-turn, web-search and memory categories. Keep V3 and V4 totals separate.. Imported groups below may use different protocols; this review does not certify each run. AST matching, state checks and required-call checks measure different failure modes. Native function calling and prompted interfaces differ. The current V4 methods specify weighted categories, while the leaderboard summary says unweighted; preserve the exact revision and do not recompute a headline from that summary.
Evaluation groups
Open a group to see its exact protocol and scores. Different configurations remain separate.
Model rankings
Open a group to compare scores within its reported protocol. Positions do not establish statistical significance.
- Berkeley Function Calling LeaderboardV4
Berkeley Function Calling Leaderboard (reviewed publisher results)
16 models with scores
Measurement date not reported
Scope · Overall accuracy; configuration (FC); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10…
Overall accuracy; configuration (FC); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10%, Non-Live 10%, Hallucination Measurement 10%; publisher-declared evaluation revision f7cf7359b7ac615a0b294831c5ba2bc95ee4a000, bfcl-eval 2025.12.17; publisher model-specific adapters and default request policy, not equal compute or fixed reasoning budgets; reasoning-model provider-default effort unspecified in published requests; raw execution responses, weight revisions, full launch settings, and per-run dates unverified; result date not supplied
- Berkeley Function Calling LeaderboardV4
Berkeley Function Calling Leaderboard (reviewed publisher results)
14 models with scores
Measurement date not reported
Scope · Overall accuracy; configuration (Prompt); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Liv…
Overall accuracy; configuration (Prompt); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10%, Non-Live 10%, Hallucination Measurement 10%; publisher-declared evaluation revision f7cf7359b7ac615a0b294831c5ba2bc95ee4a000, bfcl-eval 2025.12.17; publisher model-specific adapters and default request policy, not equal compute or fixed reasoning budgets; reasoning-model provider-default effort unspecified in published requests; raw execution responses, weight revisions, full launch settings, and per-run dates unverified; result date not supplied
Other reported results
These reports have no model ranking. Open a group for its evidence and the reason positions are withheld.
- GLM 4.6V4
Berkeley Function Calling Leaderboard · Berkeley Function Calling Leaderboard (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Overall accuracy; configuration (FC thinking); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%…
Overall accuracy; configuration (FC thinking); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10%, Non-Live 10%, Hallucination Measurement 10%; publisher-declared evaluation revision f7cf7359b7ac615a0b294831c5ba2bc95ee4a000, bfcl-eval 2025.12.17; publisher model-specific adapters and default request policy, not equal compute or fixed reasoning budgets; reasoning-model provider-default effort unspecified in published requests; raw execution responses, weight revisions, full launch settings, and per-run dates unverified; result date not supplied
- Qwen3 8BV4
Berkeley Function Calling Leaderboard · Berkeley Function Calling Leaderboard (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Overall accuracy; configuration (FC); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10…
Overall accuracy; configuration (FC); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10%, Non-Live 10%, Hallucination Measurement 10%; publisher-declared evaluation revision f7cf7359b7ac615a0b294831c5ba2bc95ee4a000, bfcl-eval 2025.12.17; publisher model-specific adapters and default request policy, not equal compute or fixed reasoning budgets; reasoning-model provider-default effort unspecified in published requests; raw execution responses, weight revisions, full launch settings, and per-run dates unverified; result date not supplied; held model qwen/qwen3-8b-04-28: duplicate API and local HF configurations share the publisher display label, scored registry key unresolved; exact request adaptation and execution route unverified
- Qwen3 8BV4
Berkeley Function Calling Leaderboard · Berkeley Function Calling Leaderboard (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Overall accuracy; configuration (Prompt); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Liv…
Overall accuracy; configuration (Prompt); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10%, Non-Live 10%, Hallucination Measurement 10%; publisher-declared evaluation revision f7cf7359b7ac615a0b294831c5ba2bc95ee4a000, bfcl-eval 2025.12.17; publisher model-specific adapters and default request policy, not equal compute or fixed reasoning budgets; reasoning-model provider-default effort unspecified in published requests; raw execution responses, weight revisions, full launch settings, and per-run dates unverified; result date not supplied; held model qwen/qwen3-8b-04-28: duplicate API and local HF configurations share the publisher display label, scored registry key unresolved; exact request adaptation and execution route unverified
- Qwen3 14BV4
Berkeley Function Calling Leaderboard · Berkeley Function Calling Leaderboard (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Overall accuracy; configuration (FC); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10…
Overall accuracy; configuration (FC); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10%, Non-Live 10%, Hallucination Measurement 10%; publisher-declared evaluation revision f7cf7359b7ac615a0b294831c5ba2bc95ee4a000, bfcl-eval 2025.12.17; publisher model-specific adapters and default request policy, not equal compute or fixed reasoning budgets; reasoning-model provider-default effort unspecified in published requests; raw execution responses, weight revisions, full launch settings, and per-run dates unverified; result date not supplied; held model qwen/qwen3-14b-04-28: duplicate API and local HF configurations share the publisher display label, scored registry key unresolved; exact request adaptation and execution route unverified
- Qwen3 14BV4
Berkeley Function Calling Leaderboard · Berkeley Function Calling Leaderboard (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Overall accuracy; configuration (Prompt); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Liv…
Overall accuracy; configuration (Prompt); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10%, Non-Live 10%, Hallucination Measurement 10%; publisher-declared evaluation revision f7cf7359b7ac615a0b294831c5ba2bc95ee4a000, bfcl-eval 2025.12.17; publisher model-specific adapters and default request policy, not equal compute or fixed reasoning budgets; reasoning-model provider-default effort unspecified in published requests; raw execution responses, weight revisions, full launch settings, and per-run dates unverified; result date not supplied; held model qwen/qwen3-14b-04-28: duplicate API and local HF configurations share the publisher display label, scored registry key unresolved; exact request adaptation and execution route unverified
- Qwen3 30B A3B Instruct 2507V4
Berkeley Function Calling Leaderboard · Berkeley Function Calling Leaderboard (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Overall accuracy; configuration (FC); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10…
Overall accuracy; configuration (FC); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10%, Non-Live 10%, Hallucination Measurement 10%; publisher-declared evaluation revision f7cf7359b7ac615a0b294831c5ba2bc95ee4a000, bfcl-eval 2025.12.17; publisher model-specific adapters and default request policy, not equal compute or fixed reasoning budgets; reasoning-model provider-default effort unspecified in published requests; raw execution responses, weight revisions, full launch settings, and per-run dates unverified; result date not supplied; held model qwen/qwen3-30b-a3b-instruct-2507: duplicate API and local HF configurations share the publisher display label, scored registry key unresolved; exact request adaptation and execution route unverified
- Qwen3 30B A3B Instruct 2507V4
Berkeley Function Calling Leaderboard · Berkeley Function Calling Leaderboard (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Overall accuracy; configuration (Prompt); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Liv…
Overall accuracy; configuration (Prompt); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10%, Non-Live 10%, Hallucination Measurement 10%; publisher-declared evaluation revision f7cf7359b7ac615a0b294831c5ba2bc95ee4a000, bfcl-eval 2025.12.17; publisher model-specific adapters and default request policy, not equal compute or fixed reasoning budgets; reasoning-model provider-default effort unspecified in published requests; raw execution responses, weight revisions, full launch settings, and per-run dates unverified; result date not supplied; held model qwen/qwen3-30b-a3b-instruct-2507: duplicate API and local HF configurations share the publisher display label, scored registry key unresolved; exact request adaptation and execution route unverified
- Qwen3 32BV4
Berkeley Function Calling Leaderboard · Berkeley Function Calling Leaderboard (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Overall accuracy; configuration (FC); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10…
Overall accuracy; configuration (FC); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10%, Non-Live 10%, Hallucination Measurement 10%; publisher-declared evaluation revision f7cf7359b7ac615a0b294831c5ba2bc95ee4a000, bfcl-eval 2025.12.17; publisher model-specific adapters and default request policy, not equal compute or fixed reasoning budgets; reasoning-model provider-default effort unspecified in published requests; raw execution responses, weight revisions, full launch settings, and per-run dates unverified; result date not supplied; held model qwen/qwen3-32b-04-28: duplicate API and local HF configurations share the publisher display label, scored registry key unresolved; exact request adaptation and execution route unverified
- Qwen3 32BV4
Berkeley Function Calling Leaderboard · Berkeley Function Calling Leaderboard (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Overall accuracy; configuration (Prompt); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Liv…
Overall accuracy; configuration (Prompt); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10%, Non-Live 10%, Hallucination Measurement 10%; publisher-declared evaluation revision f7cf7359b7ac615a0b294831c5ba2bc95ee4a000, bfcl-eval 2025.12.17; publisher model-specific adapters and default request policy, not equal compute or fixed reasoning budgets; reasoning-model provider-default effort unspecified in published requests; raw execution responses, weight revisions, full launch settings, and per-run dates unverified; result date not supplied; held model qwen/qwen3-32b-04-28: duplicate API and local HF configurations share the publisher display label, scored registry key unresolved; exact request adaptation and execution route unverified
- Qwen3 235B A22B Instruct 2507V4
Berkeley Function Calling Leaderboard · Berkeley Function Calling Leaderboard (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Overall accuracy; configuration (FC); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10…
Overall accuracy; configuration (FC); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10%, Non-Live 10%, Hallucination Measurement 10%; publisher-declared evaluation revision f7cf7359b7ac615a0b294831c5ba2bc95ee4a000, bfcl-eval 2025.12.17; publisher model-specific adapters and default request policy, not equal compute or fixed reasoning budgets; reasoning-model provider-default effort unspecified in published requests; raw execution responses, weight revisions, full launch settings, and per-run dates unverified; result date not supplied; held model qwen/qwen3-235b-a22b-07-25: duplicate API and local HF configurations share the publisher display label, scored registry key unresolved; exact request adaptation and execution route unverified
- Qwen3 235B A22B Instruct 2507V4
Berkeley Function Calling Leaderboard · Berkeley Function Calling Leaderboard (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Overall accuracy; configuration (Prompt); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Liv…
Overall accuracy; configuration (Prompt); BFCL V4 weighted overall: Agentic 40%, Multi-Turn 30%, Live 10%, Non-Live 10%, Hallucination Measurement 10%; publisher-declared evaluation revision f7cf7359b7ac615a0b294831c5ba2bc95ee4a000, bfcl-eval 2025.12.17; publisher model-specific adapters and default request policy, not equal compute or fixed reasoning budgets; reasoning-model provider-default effort unspecified in published requests; raw execution responses, weight revisions, full launch settings, and per-run dates unverified; result date not supplied; held model qwen/qwen3-235b-a22b-07-25: duplicate API and local HF configurations share the publisher display label, scored registry key unresolved; exact request adaptation and execution route unverified
- Ternary Bonsai 2 27Bv3
BFCL v3 · PrismML model card (vendor-reported)
Single-model result · Positions withheld
Measurement date 2026-09-17
Scope · Vendor-reported; thinking mode; EvalScope + vLLM on NVIDIA H100; temperature 1.0, top_p 0.95, top_k …
Vendor-reported; thinking mode; EvalScope + vLLM on NVIDIA H100; temperature 1.0, top_p 0.95, top_k 20; result date not stated by the publisher, dated to the model-card publication; same-run FP16 Qwen3.8-27B reference: 76.74