List your company

Function Calling on BFCL (Berkeley Function Calling Leaderboard)

41.8Base ScoreGenEnv
-1.6729.61420.932.186Dec 22, 2025Dec 26, 2025Dec 30, 2025Jan 3, 2026Jan 7, 2026Jan 11, 2026Jan 15, 2026

Evaluation results

MethodLinks
GenEnvScale group=7B Models, Model Size=7B2025.1241.8——————
Qwen 2.5 72BScale group=Large Scale Models (> 10B), Model Size=72B2025.1235.3——————
Qwen 3 32BScale group=Large Scale Models (> 10B), Model Size=32B2025.1233.8——————
Qwen 3 14BScale group=Large Scale Models (> 10B), Model Size=14B2025.1229.4——————
GPT-OSS 20BScale group=Large Scale Models (> 10B), Model Size=20B2025.1224.4——————
GPT-OSS 120BScale group=Large Scale Models (> 10B), Model Size=120B2025.1221.9——————
Llama 3.1 70BScale group=Large Scale Models (> 10B), Model Size=70B2025.1213.4——————
Qwen 2.5 7BScale group=7B Models, Model Size=7B2025.127——————
Llama 3.1 405BScale group=Large Scale Models (> 10B), Model Size=405B2025.125.5——————
ReSearchScale group=7B Models, Model Size=7B2025.125——————
SearchR1Scale group=7B Models, Model Size=7B2025.125——————
MatchTIR (KM)Backbone=Qwen3-8B2026.010.60.490.390.4050.170.26020.3432
MatchTIR (OT)Backbone=Qwen3-8B2026.010.5550.520.3850.360.180.23870.3322
GRPOBackbone=Qwen3-8B2026.010.5250.4550.3450.3650.1450.18920.2948
FTRL-SBackbone=Qwen3-8B2026.010.5150.450.3550.340.1250.17420.2823
MatchTIR (KM)Backbone=Qwen3-4B2026.010.5050.470.2850.3650.1750.22150.3023
FTRL-MBackbone=Qwen3-8B2026.010.5050.510.350.3350.150.21940.3049
ToolRL-MBackbone=Qwen3-4B2026.010.50.3750.290.30.1050.2280.2664
MatchTIR (OT)Backbone=Qwen3-4B2026.010.50.4050.2650.350.120.21720.2743
ToolRL-MBackbone=Qwen3-8B2026.010.50.470.3950.320.1550.16770.2913
VanillaBackbone=Qwen3-8B2026.010.4750.460.3750.3450.10.20430.283
GRPOBackbone=Qwen3-4B2026.010.450.3750.2650.2950.0950.21940.2517
FTRL-MBackbone=Qwen3-4B2026.010.4450.410.3250.2950.0650.2280.2576
FTRL-SBackbone=Qwen3-4B2026.010.430.3550.310.280.0650.23440.2467
VanillaBackbone=Qwen3-4B2026.010.4150.310.2650.2750.090.19570.2296
ToolRL-SBackbone=Qwen3-8B2026.010.410.3950.3150.250.0750.17630.2341
ToolRL-SBackbone=Qwen3-4B2026.010.3250.310.2250.20.0750.19140.1991
ToRLScale group=7B Models, Model Size=7B2025.120——————