Skip to content
Get my AI grade

Model rank

BFCL tool use configurations

109 models ranked by BFCL overall accuracy.
Recorded Apr 13, 2026Source: the Berkeley Function Calling LeaderboardHow this board is measuredCSV / JSON

77.47%

Claude-Opus-4-5-20251101 (FC) ranks first

BFCL overall accuracy

109

Models ranked

Apr 13

Snapshot recorded

2026

Follow changes

All 109 models by BFCL overall accuracy

Claude-Opus-4-5-20251101 (FC) leads at 77.47%; the middle of the board sits at 35.5%.

Ahead of second place
4.2%
Held by the top three
5%
Middle of the board
35.5%
Below half the leader
64 of 109
Highest 77.47%Middle 35.5%
1. Claude-Opus-4-5-20251101 (FC): 77.47%2. Claude-Sonnet-4-5-20250929 (FC): 73.24%3. Gemini-3-Pro-Preview (Prompt): 72.51%4. GLM-4.6 (FC thinking): 72.38%5. Grok-4-1-fast-reasoning (FC): 69.57%6. Claude-Haiku-4-5-20251001 (FC): 68.70%7. Gemini-3-Pro-Preview (FC): 68.14%8. o3-2025-04-16 (Prompt): 63.05%9. Grok-4-0709 (Prompt): 62.97%10. Grok-4-0709 (FC): 61.38%11. Moonshotai-Kimi-K2-Instruct (FC): 59.06%12. Grok-4-1-fast-non-reasoning (FC): 58.29%13. Command A Reasoning (FC): 57.06%14. DeepSeek-V3.2-Exp (Prompt + Thinking): 56.73%15. Gemini-2.5-Flash (FC): 56.24%16. GPT-5.2-2025-12-11 (FC): 55.87%17. GPT-5-mini-2025-08-07 (FC): 55.46%18. xLAM-2-32b-fc-r (FC): 54.66%19. DeepSeek-V3.2-Exp (FC): 54.12%20. GPT-4.1-2025-04-14 (FC): 53.96%21. o4-mini-2025-04-16 (FC): 53.24%22. xLAM-2-70b-fc-r (FC): 53.07%23. Qwen3-235B-A22B-Instruct-2507 (Prompt): 52.15%24. GPT-5-nano-2025-08-07 (FC): 51.45%25. Nanbeige4-3B-Thinking-2511 (FC): 51.40%26. Gemini-2.5-Flash (Prompt): 50.90%27. GPT-4.1-mini-2025-04-14 (FC): 50.45%28. o4-mini-2025-04-16 (Prompt): 50.26%29. Qwen3-32B (FC): 48.71%30. o3-2025-04-16 (FC): 48.56%31. Qwen3-235B-A22B-Instruct-2507 (FC): 47.99%32. Nanbeige3.5-Pro-Thinking (FC): 47.68%33. Qwen3-32B (Prompt): 46.78%34. xLAM-2-8b-fc-r (FC): 46.68%35. Command A (FC): 46.49%36. BitAgent-Bounty-8B: 46.23%37. Arch-Agent-32B: 45.37%38. GPT-5.2-2025-12-11 (Prompt): 45.27%39. Qwen3-8B (FC): 42.57%40. ToolACE-2-8B (FC): 42.44%41. Qwen3-30B-A3B-Instruct-2507 (FC): 41.39%42. xLAM-2-3b-fc-r (FC): 41.22%43. Qwen3-14B (FC): 41.03%44. Qwen3-8B (Prompt): 40.43%45. GPT-4.1-2025-04-14 (Prompt): 39.38%46. mistral-large-2411 (FC): 38.37%47. Qwen3-14B (Prompt): 37.77%48. Mistral-Medium-2505: 37.69%49. Mistral-Medium-2505 (FC): 37.56%50. Llama-4-Maverick-17B-128E-Instruct-FP8 (FC): 37.29%51. Mistral-small-2506 (FC): 37.15%52. Gemini-2.5-Flash-Lite (FC): 36.87%53. Qwen3-30B-A3B-Instruct-2507 (Prompt): 36.70%54. Qwen3-4B-Instruct-2507 (FC): 35.68%55. Qwen3-4B-Instruct-2507 (Prompt): 35.52%56. Arch-Agent-3B: 35.36%57. Claude-Opus-4-5-20251101 (Prompt): 33.47%58. GPT-4.1-nano-2025-04-14 (FC): 33.05%59. Mistral-Small-2506 (Prompt): 32.38%60. Arch-Agent-1.5B: 32.14%61. Command R7B (FC): 32.07%62. Llama-3.3-70B-Instruct (FC): 31.90%63. mistral-large-2411 (Prompt): 31.84%64. Hammer2.1-7b (FC): 31.67%65. xLAM-2-1b-fc-r (FC): 30.44%66. Gemma-3-12b-it (Prompt): 30.43%67. GPT-4.1-mini-2025-04-14 (Prompt): 29.73%68. Hammer2.1-3b (FC): 29.71%69. Gemma-3-27b-it (Prompt): 29.47%70. Phi-4 (Prompt): 28.79%71. Qwen3-1.7B (FC): 28.41%72. Llama-4-Scout-17B-16E-Instruct (FC): 28.13%73. Gemini-2.5-Flash-Lite (Prompt): 28.03%74. CoALM-70B: 27.99%75. Hammer2.1-1.5b (FC): 27.88%76. palmyra-x-004 (FC): 27.87%77. GPT-5-mini-2025-08-07 (Prompt): 27.83%78. Open-Mistral-Nemo-2407 (FC): 27.63%79. GPT-5-nano-2025-08-07 (Prompt): 27.55%80. Amazon-Nova-2-Lite-v1:0 (FC): 27.10%81. Granite-3.1-8B-Instruct (FC): 27.10%82. Falcon3-10B-Instruct (FC): 27.01%83. Granite-3.2-8B-Instruct (FC): 26.87%84. CoALM-8B: 26.81%85. Llama-3.1-8B-Instruct (Prompt): 25.83%86. MiniCPM3-4B-FC (FC): 25.55%87. Claude-Haiku-4-5-20251001 (Prompt): 25.26%88. Amazon-Nova-Pro-v1:0 (FC): 24.97%89. Claude-Sonnet-4-5-20250929 (Prompt): 24.90%90. GPT-4.1-nano-2025-04-14 (Prompt): 24.88%91. Falcon3-7B-Instruct (FC): 24.03%92. Qwen3-0.6B (FC): 23.93%93. Granite-20b-FunctionCalling (FC): 23.23%94. Qwen3-0.6B (Prompt): 22.38%95. Amazon-Nova-Micro-v1:0 (FC): 22.29%96. RZN-T (Prompt): 22.25%97. MiniCPM3-4B (Prompt): 22.08%98. Llama-3.2-3B-Instruct (FC): 21.95%99. Bielik-11B-v2.3-Instruct (Prompt): 21.90%100. Hammer2.1-0.5b (FC): 21.22%101. Gemma-3-4b-it (Prompt): 19.62%102. Open-Mistral-Nemo-2407 (Prompt): 19.31%103. Granite-4.0-350m (FC): 18.98%104. Falcon3-3B-Instruct (FC): 16.25%105. Ministral-8B-Instruct-2410 (FC): 11.10%106. Falcon3-1B-Instruct (FC): 11.08%107. Llama-3.2-1B-Instruct (FC): 10.82%108. Llama-3.1-Nemotron-Ultra-253B-v1 (FC): 10.00%109. Gemma-3-1b-it (Prompt): 7.17%
Rank 1One bar per published rowRank 109

Official UC Berkeley BFCL v4 leaderboard · 100% confidence across rows.

BFCL tool use configurations current rankings
RankNameBFCL overall accuracyBFCL evaluation total costBFCL format sensitivity max deltaBFCL format sensitivity standard deviationWhy
01Claude-Opus-4-5-20251101 (FC)77.47%$86.55——This rank
02Claude-Sonnet-4-5-20250929 (FC)73.24%$43.73——This rank
03Gemini-3-Pro-Preview (Prompt)72.51%$298.478.51.7This rank
04GLM-4.6 (FC thinking)72.38%$4.64——This rank
05Grok-4-1-fast-reasoning (FC)69.57%$17.26——This rank
06Claude-Haiku-4-5-20251001 (FC)68.70%$14.23——This rank
07Gemini-3-Pro-Preview (FC)68.14%$224.69——This rank
08o3-2025-04-16 (Prompt)63.05%$234.648.52.8This rank
09Grok-4-0709 (Prompt)62.97%$348.19132.9This rank
10Grok-4-0709 (FC)61.38%$355.17——This rank
11Moonshotai-Kimi-K2-Instruct (FC)59.06%$6.19——This rank
12Grok-4-1-fast-non-reasoning (FC)58.29%$16.27——This rank
13Command A Reasoning (FC)57.06%$3.04——This rank
14DeepSeek-V3.2-Exp (Prompt + Thinking)56.73%$57.75102.8This rank
15Gemini-2.5-Flash (FC)56.24%$26.36——This rank
16GPT-5.2-2025-12-11 (FC)55.87%$85.65——This rank
17GPT-5-mini-2025-08-07 (FC)55.46%$22.18——This rank
18xLAM-2-32b-fc-r (FC)54.66%$6——This rank
19DeepSeek-V3.2-Exp (FC)54.12%$6.71——This rank
20GPT-4.1-2025-04-14 (FC)53.96%$100.75——This rank
21o4-mini-2025-04-16 (FC)53.24%$81.91——This rank
22xLAM-2-70b-fc-r (FC)53.07%$25.1——This rank
23Qwen3-235B-A22B-Instruct-2507 (Prompt)52.15%$3.1282This rank
24GPT-5-nano-2025-08-07 (FC)51.45%$8.79——This rank
25Nanbeige4-3B-Thinking-2511 (FC)51.40%$14.14——This rank
26Gemini-2.5-Flash (Prompt)50.90%$33.4592.5This rank
27GPT-4.1-mini-2025-04-14 (FC)50.45%$19.25——This rank
28o4-mini-2025-04-16 (Prompt)50.26%$133.639.52.6This rank
29Qwen3-32B (FC)48.71%$153.08——This rank
30o3-2025-04-16 (FC)48.56%$133.45——Showing
31Qwen3-235B-A22B-Instruct-2507 (FC)47.99%$2.5——This rank
32Nanbeige3.5-Pro-Thinking (FC)47.68%$23.46——This rank
33Qwen3-32B (Prompt)46.78%$199.4715.53.8This rank
34xLAM-2-8b-fc-r (FC)46.68%$20.92——This rank
35Command A (FC)46.49%$91.37——This rank
36BitAgent-Bounty-8B46.23%$18.02——This rank
37Arch-Agent-32B45.37%$8.87——This rank
38GPT-5.2-2025-12-11 (Prompt)45.27%$164.58133.3This rank
39Qwen3-8B (FC)42.57%$43.32——This rank
40ToolACE-2-8B (FC)42.44%$24.4381.527.9This rank
41Qwen3-30B-A3B-Instruct-2507 (FC)41.39%$5.62——This rank
42xLAM-2-3b-fc-r (FC)41.22%$3.36——This rank
43Qwen3-14B (FC)41.03%$3.38——This rank
44Qwen3-8B (Prompt)40.43%$63.9516.55.1This rank
45GPT-4.1-2025-04-14 (Prompt)39.38%$145.8523.56.2This rank
46mistral-large-2411 (FC)38.37%$115.98——This rank
47Qwen3-14B (Prompt)37.77%$1.35144This rank
48Mistral-Medium-250537.69%$36.5121.55This rank
49Mistral-Medium-2505 (FC)37.56%$18.8——This rank
50Llama-4-Maverick-17B-128E-Instruct-FP8 (FC)37.29%$18.25——This rank
51Mistral-small-2506 (FC)37.15%$5.2——This rank
52Gemini-2.5-Flash-Lite (FC)36.87%$7.55——This rank
53Qwen3-30B-A3B-Instruct-2507 (Prompt)36.70%$1.56164.1This rank
54Qwen3-4B-Instruct-2507 (FC)35.68%$6.37——This rank
55Qwen3-4B-Instruct-2507 (Prompt)35.52%$53.66185.2This rank
56Arch-Agent-3B35.36%$3.7——This rank
57Claude-Opus-4-5-20251101 (Prompt)33.47%$88.33133.7This rank
58GPT-4.1-nano-2025-04-14 (FC)33.05%$5.66——This rank
59Mistral-Small-2506 (Prompt)32.38%$6.915013.6This rank
60Arch-Agent-1.5B32.14%$2.45——This rank
61Command R7B (FC)32.07%$1.5——This rank
62Llama-3.3-70B-Instruct (FC)31.90%$29.54——This rank
63mistral-large-2411 (Prompt)31.84%$232.4213.53.9This rank
64Hammer2.1-7b (FC)31.67%$4.99——This rank
65xLAM-2-1b-fc-r (FC)30.44%$2.79——This rank
66Gemma-3-12b-it (Prompt)30.43%$10.7767.522.4This rank
67GPT-4.1-mini-2025-04-14 (Prompt)29.73%$20.524513.3This rank
68Hammer2.1-3b (FC)29.71%$10.89——This rank
69Gemma-3-27b-it (Prompt)29.47%$11.82348.1This rank
70Phi-4 (Prompt)28.79%$8.7281.523.3This rank
71Qwen3-1.7B (FC)28.41%$4.33——This rank
72Llama-4-Scout-17B-16E-Instruct (FC)28.13%$24.68——This rank
73Gemini-2.5-Flash-Lite (Prompt)28.03%$7.0525.56.7This rank
74CoALM-70B27.99%$19.897227.8This rank
75Hammer2.1-1.5b (FC)27.88%$6.83——This rank
76palmyra-x-004 (FC)27.87%$178.15——This rank
77GPT-5-mini-2025-08-07 (Prompt)27.83%$82.74163.8This rank
78Open-Mistral-Nemo-2407 (FC)27.63%$8.12——This rank
79GPT-5-nano-2025-08-07 (Prompt)27.55%$21.478.52.6This rank
80Amazon-Nova-2-Lite-v1:0 (FC)27.10%$78.19——This rank
81Granite-3.1-8B-Instruct (FC)27.10%$9.32——This rank
82Falcon3-10B-Instruct (FC)27.01%$52.59——This rank
83Granite-3.2-8B-Instruct (FC)26.87%$25.02——This rank
84CoALM-8B26.81%$25.337934.2This rank
85Llama-3.1-8B-Instruct (Prompt)25.83%$7.4974.529.1This rank
86MiniCPM3-4B-FC (FC)25.55%$54.05——This rank
87Claude-Haiku-4-5-20251001 (Prompt)25.26%$45.1367.520.1This rank
88Amazon-Nova-Pro-v1:0 (FC)24.97%$48.44——This rank
89Claude-Sonnet-4-5-20250929 (Prompt)24.90%$47.8237.510.1This rank
90GPT-4.1-nano-2025-04-14 (Prompt)24.88%$7.427317.1This rank
91Falcon3-7B-Instruct (FC)24.03%$73.61——This rank
92Qwen3-0.6B (FC)23.93%$0.46——This rank
93Granite-20b-FunctionCalling (FC)23.23%$5.23——This rank
94Qwen3-0.6B (Prompt)22.38%$3.6560.524.4This rank
95Amazon-Nova-Micro-v1:0 (FC)22.29%$1.81——This rank
96RZN-T (Prompt)22.25%$12.3163.525.5This rank
97MiniCPM3-4B (Prompt)22.08%$29.836816.6This rank
98Llama-3.2-3B-Instruct (FC)21.95%$6.2——This rank
99Bielik-11B-v2.3-Instruct (Prompt)21.90%$22.44359.7This rank
100Hammer2.1-0.5b (FC)21.22%$2.82——This rank
101Gemma-3-4b-it (Prompt)19.62%$4.1469.523.7This rank
102Open-Mistral-Nemo-2407 (Prompt)19.31%$13.814.54.6This rank
103Granite-4.0-350m (FC)18.98%$1.44——This rank
104Falcon3-3B-Instruct (FC)16.25%$36.7——This rank
105Ministral-8B-Instruct-2410 (FC)11.10%$70.0100This rank
106Falcon3-1B-Instruct (FC)11.08%$1.72——This rank
107Llama-3.2-1B-Instruct (FC)10.82%$1.64——This rank
108Llama-3.1-Nemotron-Ultra-253B-v1 (FC)10.00%$0.72——This rank
109Gemma-3-1b-it (Prompt)7.17%$3.425.59.8This rank

Why this rank

o3-2025-04-16 (FC) on BFCL Tool-Use Configurations

Snapshot of Apr 13, 2026, 11:59 PM UTC · Link to this snapshot

Some explanation inputs are unavailable. Not published: the evidence frozen with this snapshot, comparable prior ranking.

Ranks exact model-plus-inference configurations by official UC Berkeley BFCL overall accuracy.

30

Rank on this board

48.56 percent

Score

11

Inputs behind the score

100% confidence · 1 of 1 components evidenced

What the score is built from

1 of 1 evidenced

Every component evidenced · 1 evidence record each

Components of o3-2025-04-16 (FC)'s score
ComponentContribution
BFCL overall accuracy48.56

New in this snapshot

No change in rank

no_prior_published_snapshot

No component moved since the previous snapshot.

Where each number comes from

11 public records
  • BFCL evaluation total costBFCL evaluation total cost · observed Apr 13, 2026, 11:59 PM UTC$133.45100% confidence
    Source
    Berkeley Function Calling Leaderboard
    Grade
    A
    Freshness
    fresh
    Locator
    {"csv":"https://gorilla.cs.berkeley.edu/data_overall.csv","repository":"https://github.com/ShishirPatil/gorilla/tree/main/berkeley-function-call-leaderboard","leaderboard":"https://gorilla.cs.berkeley.edu/leaderboard.html","rowIdentity":"Model","rankingColumn":"Overall Acc"}
    Open the source
  • BFCL irrelevance-detection accuracyBFCL irrelevance detection accuracy · observed Apr 13, 2026, 11:59 PM UTC86.13 percent100% confidence
    Source
    Berkeley Function Calling Leaderboard
    Grade
    A
    Freshness
    fresh
    Locator
    {"csv":"https://gorilla.cs.berkeley.edu/data_overall.csv","repository":"https://github.com/ShishirPatil/gorilla/tree/main/berkeley-function-call-leaderboard","leaderboard":"https://gorilla.cs.berkeley.edu/leaderboard.html","rowIdentity":"Model","rankingColumn":"Overall Acc"}
    Open the source
  • BFCL mean latencyBFCL latency mean seconds · observed Apr 13, 2026, 11:59 PM UTC3.5 seconds100% confidence
    Source
    Berkeley Function Calling Leaderboard
    Grade
    A
    Freshness
    fresh
    Locator
    {"csv":"https://gorilla.cs.berkeley.edu/data_overall.csv","repository":"https://github.com/ShishirPatil/gorilla/tree/main/berkeley-function-call-leaderboard","leaderboard":"https://gorilla.cs.berkeley.edu/leaderboard.html","rowIdentity":"Model","rankingColumn":"Overall Acc"}
    Open the source
  • BFCL p95 latencyBFCL latency p95 seconds · observed Apr 13, 2026, 11:59 PM UTC8.39 seconds100% confidence
    Source
    Berkeley Function Calling Leaderboard
    Grade
    A
    Freshness
    fresh
    Locator
    {"csv":"https://gorilla.cs.berkeley.edu/data_overall.csv","repository":"https://github.com/ShishirPatil/gorilla/tree/main/berkeley-function-call-leaderboard","leaderboard":"https://gorilla.cs.berkeley.edu/leaderboard.html","rowIdentity":"Model","rankingColumn":"Overall Acc"}
    Open the source
  • BFCL live accuracyBFCL live accuracy · observed Apr 13, 2026, 11:59 PM UTC66.17 percent100% confidence
    Source
    Berkeley Function Calling Leaderboard
    Grade
    A
    Freshness
    fresh
    Locator
    {"csv":"https://gorilla.cs.berkeley.edu/data_overall.csv","repository":"https://github.com/ShishirPatil/gorilla/tree/main/berkeley-function-call-leaderboard","leaderboard":"https://gorilla.cs.berkeley.edu/leaderboard.html","rowIdentity":"Model","rankingColumn":"Overall Acc"}
    Open the source
  • BFCL memory accuracyBFCL memory accuracy · observed Apr 13, 2026, 11:59 PM UTC47.31 percent100% confidence
    Source
    Berkeley Function Calling Leaderboard
    Grade
    A
    Freshness
    fresh
    Locator
    {"csv":"https://gorilla.cs.berkeley.edu/data_overall.csv","repository":"https://github.com/ShishirPatil/gorilla/tree/main/berkeley-function-call-leaderboard","leaderboard":"https://gorilla.cs.berkeley.edu/leaderboard.html","rowIdentity":"Model","rankingColumn":"Overall Acc"}
    Open the source
  • BFCL multi-turn accuracyBFCL multi turn accuracy · observed Apr 13, 2026, 11:59 PM UTC14.75 percent100% confidence
    Source
    Berkeley Function Calling Leaderboard
    Grade
    A
    Freshness
    fresh
    Locator
    {"csv":"https://gorilla.cs.berkeley.edu/data_overall.csv","repository":"https://github.com/ShishirPatil/gorilla/tree/main/berkeley-function-call-leaderboard","leaderboard":"https://gorilla.cs.berkeley.edu/leaderboard.html","rowIdentity":"Model","rankingColumn":"Overall Acc"}
    Open the source
  • BFCL non-live AST accuracyBFCL non live ast accuracy · observed Apr 13, 2026, 11:59 PM UTC40.38 percent100% confidence
    Source
    Berkeley Function Calling Leaderboard
    Grade
    A
    Freshness
    fresh
    Locator
    {"csv":"https://gorilla.cs.berkeley.edu/data_overall.csv","repository":"https://github.com/ShishirPatil/gorilla/tree/main/berkeley-function-call-leaderboard","leaderboard":"https://gorilla.cs.berkeley.edu/leaderboard.html","rowIdentity":"Model","rankingColumn":"Overall Acc"}
    Open the source
  • BFCL overall accuracyBFCL overall accuracy · observed Apr 13, 2026, 11:59 PM UTC48.56 percent100% confidence
    Source
    Berkeley Function Calling Leaderboard
    Grade
    A
    Freshness
    fresh
    Locator
    {"csv":"https://gorilla.cs.berkeley.edu/data_overall.csv","repository":"https://github.com/ShishirPatil/gorilla/tree/main/berkeley-function-call-leaderboard","leaderboard":"https://gorilla.cs.berkeley.edu/leaderboard.html","rowIdentity":"Model","rankingColumn":"Overall Acc"}
    Open the source
  • BFCL relevance-detection accuracyBFCL relevance detection accuracy · observed Apr 13, 2026, 11:59 PM UTC81.25 percent100% confidence
    Source
    Berkeley Function Calling Leaderboard
    Grade
    A
    Freshness
    fresh
    Locator
    {"csv":"https://gorilla.cs.berkeley.edu/data_overall.csv","repository":"https://github.com/ShishirPatil/gorilla/tree/main/berkeley-function-call-leaderboard","leaderboard":"https://gorilla.cs.berkeley.edu/leaderboard.html","rowIdentity":"Model","rankingColumn":"Overall Acc"}
    Open the source
  • BFCL web-search accuracyBFCL web search accuracy · observed Apr 13, 2026, 11:59 PM UTC77 percent100% confidence
    Source
    Berkeley Function Calling Leaderboard
    Grade
    A
    Freshness
    fresh
    Locator
    {"csv":"https://gorilla.cs.berkeley.edu/data_overall.csv","repository":"https://github.com/ShishirPatil/gorilla/tree/main/berkeley-function-call-leaderboard","leaderboard":"https://gorilla.cs.berkeley.edu/leaderboard.html","rowIdentity":"Model","rankingColumn":"Overall Acc"}
    Open the source
BFCL v4 tool-use configuration ranking reviewed 2026-04-13, version bfcl-v4-2026-04-13-official-v1-bfcl-tool-use-configurations-v11,279 observations · 1 source · quality passed
Snapshot
57524365-34d0-45a4-bbfa-4142294a674f
Data hash
fd7246bbd83f6cd45af19278b9c0ca93e6d1a34d38d56f10f93c35e7191b50b2
Method hash
be8373dfcda076297ac4e7e0c7a03a647edcca8bedd8d06fb7a07d005a5326d6

More in Model rank

Capability-first rankings across frontier and open models.

3 boards

See how often AI names you.

Enter your website. In about two minutes, Rank.ai asks ChatGPT, Claude and Gemini 12 questions your customers ask and grades how often they name you.

  • Your grade out of 100How often AI names you, cites your site, and how high it ranks you.
  • Who gets namedEvery competitor in the answers, most named first.
  • The pages AI readsThe sources behind each answer.
  • Three fixesWhat to fix first, with a brief for the first article.