Models / minicpm3-4b

Openbmb

minicpm3-4b

16 published results from 1 source. Each card shows where the number comes from and what it does not measure. The overall leaderboard combines them; here each stands alone.

Provider: Openbmb
Sources: 1
Our benchmarks: 0
Price: Not yet published

Reported by others

Reported by Berkeley Function Calling Leaderboard (BFCL) V4

73.7%

Irrelevance detection · rank 79 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl prompt)
Measured: 16 Dec 2025
Not shown: Not general refusal or safety behaviour.

Reported by Berkeley Function Calling Leaderboard (BFCL) V4

72.8%

Irrelevance detection · rank 81 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl fc)
Measured: 16 Dec 2025
Not shown: Not general refusal or safety behaviour.

Reported by Berkeley Function Calling Leaderboard (BFCL) V4

9.5%

Memory · rank 74 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl prompt)
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

12.0%

Memory · rank 67 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl fc)
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

3.5%

Multi-turn tasks · rank 87 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl prompt)
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

3.9%

Multi-turn tasks · rank 84 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl fc)
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

22.1%

Overall accuracy · rank 97 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl prompt)
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

25.6%

Overall accuracy · rank 86 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl fc)
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

56.2%

Relevance detection · rank 96 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl prompt)
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: minicpm3-4b (bfcl fc)
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

70.5%

Single-turn calls (curated) · rank 85 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl prompt)
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

81.8%

Single-turn calls (curated) · rank 68 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl fc)
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

43.1%

Single-turn calls (user-contributed) · rank 104 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl prompt)
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

65.2%

Single-turn calls (user-contributed) · rank 80 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl fc)
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

2.0%

Web search · rank 76 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl prompt)
Measured: 16 Dec 2025
Not shown: Not general research quality: questions have short, checkable answers.

Reported by Berkeley Function Calling Leaderboard (BFCL) V4

0.0%

Web search · rank 92 of 109

Unit: % correct, higher is better
Configuration: minicpm3-4b (bfcl fc)
Measured: 16 Dec 2025
Not shown: Not general research quality: questions have short, checkable answers.