Models / gemini-3-pro-preview

Google

gemini-3-pro-preview

24 published results from 3 sources. Each card shows where the number comes from and what it does not measure. Results are never combined into one score.

Provider
Google
Sources
3
Our benchmarks
0
Price
Not yet published

Reported by others

Reported by Berkeley Function Calling Leaderboard (BFCL) V4
77.8%
Irrelevance detection · rank 66 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not general refusal or safety behaviour.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
85.6%
Irrelevance detection · rank 31 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not general refusal or safety behaviour.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
54.8%
Memory · rank 6 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not long-term personal memory in a product: sessions are BFCL's scripted ones.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
61.7%
Memory · rank 3 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not long-term personal memory in a product: sessions are BFCL's scripted ones.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
63.1%
Multi-turn tasks · rank 6 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
60.8%
Multi-turn tasks · rank 10 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
68.1%
Overall accuracy · rank 7 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not a neutral average: the weighting is BFCL's. Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
72.5%
Overall accuracy · rank 3 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not a neutral average: the weighting is BFCL's. Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
75.0%
Relevance detection · rank 62 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not whether the call itself was right; only that one was attempted.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
68.8%
Relevance detection · rank 80 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not whether the call itself was right; only that one was attempted.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
85.8%
Single-turn calls (curated) · rank 38 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
90.7%
Single-turn calls (curated) · rank 1 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
81.7%
Single-turn calls (user-contributed) · rank 6 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
83.1%
Single-turn calls (user-contributed) · rank 2 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
68.5%
Web search · rank 17 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not general research quality: questions have short, checkable answers.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
80.0%
Web search · rank 7 of 109
Unit
% correct, higher is better
Configuration
gemini-3-pro-preview
Measured
16 Dec 2025
Not shown
Not general research quality: questions have short, checkable answers.
Reported by UGI Leaderboard
34.0%
Requested-length error · rank 269 of 370
Unit
% off the requested word count, lower is better
Configuration
gemini-3-pro-preview
Measured
18 Nov 2025
Not shown
Not other format limits such as character counts or bullet counts.
Reported by UGI Leaderboard
33.0%
Requested-length error · rank 267 of 370
Unit
% off the requested word count, lower is better
Configuration
gemini-3-pro-preview
Measured
18 Nov 2025
Not shown
Not other format limits such as character counts or bullet counts.
Reported by UGI Leaderboard
0.37
Style adherence · rank 97 of 370
Unit
score from 0 to 1, higher is better
Configuration
gemini-3-pro-preview
Measured
18 Nov 2025
Not shown
Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
Reported by UGI Leaderboard
0.36
Style adherence · rank 146 of 370
Unit
score from 0 to 1, higher is better
Configuration
gemini-3-pro-preview
Measured
18 Nov 2025
Not shown
Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
Reported by UGI Leaderboard
66.7
Writing score · rank 53 of 370
Unit
score out of 100, higher is better
Configuration
gemini-3-pro-preview
Measured
18 Nov 2025
Not shown
Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.
Reported by UGI Leaderboard
65.6
Writing score · rank 60 of 370
Unit
score out of 100, higher is better
Configuration
gemini-3-pro-preview
Measured
18 Nov 2025
Not shown
Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.
Reported by Vectara Hallucination Leaderboard
99.4%
Answer rate · rank 58 of 108
Unit
% of documents, higher is better
Configuration
gemini-3-pro-preview
Measured
22 Sep 2026
Not shown
Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.
Reported by Vectara Hallucination Leaderboard
13.6%
Hallucination rate · rank 89 of 108
Unit
% of summaries, lower is better
Configuration
gemini-3-pro-preview
Measured
22 Sep 2026
Not shown
Not errors in open questions or other tasks: only summarisation, judged by Vectara's own model (HHEM-2.3), not by people, on news-style documents rather than your data.

Compare gemini-3-pro-preview with