Vibeleaderboard
← Benchmark guide

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.

Publisher results Multi-turn graders V4 methods and aggregation
← All evaluation groups

Berkeley Function Calling Leaderboard

Source
Berkeley Function Calling Leaderboard (reviewed publisher results)
Version
V4
Measurement date
Not reported
Metric
% · Higher is better
Evaluation scope
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

Exact score ties share a position. Positions do not establish statistical significance. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

  1. #1o3

    openai/o3-2025-04-16

    63.05%

    View modelEvidence independent

  2. #2o4 Mini

    openai/o4-mini-2025-04-16

    50.26%

    View modelEvidence independent

  3. #3GPT-5.2

    openai/gpt-5.2-20251211

    45.27%

    View modelEvidence independent

  4. #4GPT-4.1

    openai/gpt-4.1-2025-04-14

    39.38%

    View modelEvidence independent

  5. #5Claude Opus 4.5

    anthropic/claude-opus-4-5

    33.47%

    View modelEvidence independent

  6. #6Gemma 3 12B

    google/gemma-3-12b-it

    30.43%

    View modelEvidence independent

  7. #7GPT-4.1 Mini

    openai/gpt-4.1-mini-2025-04-14

    29.73%

    View modelEvidence independent

  8. #8Gemma 3 27B

    google/gemma-3-27b-it

    29.47%

    View modelEvidence independent

  9. #9Phi 4

    microsoft/phi-4

    28.79%

    View modelEvidence independent

  10. #10GPT-5 Mini

    openai/gpt-5-mini-2025-08-07

    27.83%

    View modelEvidence independent

  11. #11GPT-5 Nano

    openai/gpt-5-nano-2025-08-07

    27.55%

    View modelEvidence independent

  12. #12Claude Sonnet 4.5

    anthropic/claude-sonnet-4-5

    24.9%

    View modelEvidence independent

  13. #13GPT-4.1 Nano

    openai/gpt-4.1-nano-2025-04-14

    24.88%

    View modelEvidence independent

  14. #14Gemma 3 4B

    google/gemma-3-4b-it

    19.62%

    View modelEvidence independent
Berkeley Function Calling Leaderboard model results | VibeLeaderboard