List your company

Instruction Following on AdvancedIF

71AccuracyBRAID
25.2437.124960.88Dec 17, 2025Jan 3, 2026Jan 21, 2026Feb 8, 2026Feb 26, 2026Mar 16, 2026Apr 3, 2026

Evaluation results

MethodLinks
BRAIDGenerator=gpt-5 mini minimal, Solver=gpt-5.1 medium2025.12711.44———
BRAIDGenerator=gpt-5 medium, Solver=gpt-5.1 medium2025.12701.75———
BRAIDGenerator=gpt-4o, Solver=gpt-5 medium2025.12691.05———
BRAIDGenerator=gpt-5 mini medium, Solver=gpt-5 medium2025.12660.9———
BRAIDGenerator=gpt-5 mini minimal, Solver=gpt-5 medium2025.12661.04———
BRAIDGenerator=gpt-5 minimal, Solver=gpt-5.1 medium2025.12661.63———
BRAIDGenerator=gpt-5.1 none, Solver=gpt-5.1 medium2025.12661.67———
BRAIDGenerator=gpt-5 nano minimal, Solver=gpt-5.1 medium2025.12651.44———
BRAIDGenerator=gpt-5.1 medium, Solver=gpt-5 medium2025.12651.11———
BRAIDGenerator=gpt-5.1 medium, Solver=gpt-5.1 medium2025.12651.55———
BRAIDGenerator=gpt-5 mini medium, Solver=gpt-5.1 medium2025.12641.26———
BRAIDGenerator=gpt-5 minimal, Solver=gpt-5 mini medium2025.12647.07———
BRAIDGenerator=gpt-5.1 none, Solver=gpt-5 medium2025.12631.01———
BRAIDGenerator=gpt-5 medium, Solver=gpt-5 medium2025.12621.04———
BRAIDGenerator=gpt-5 minimal, Solver=gpt-5 medium2025.12621.01———
BRAIDGenerator=gpt-4o, Solver=gpt-5.1 medium2025.12611.4———
BRAIDGenerator=gpt-4o, Solver=gpt-5 mini medium2025.12605.94———
BRAIDGenerator=gpt-5 medium, Solver=gpt-5 mini medium2025.12606.51———
BRAIDGenerator=gpt-5 nano medium, Solver=gpt-5 medium2025.12601.11———
BRAIDGenerator=gpt-5.1 none, Solver=gpt-5 mini medium2025.12606.6———
BRAIDGenerator=gpt-5 medium, Solver=gpt-5 minimal2025.12583.53———
BRAIDGenerator=gpt-5 nano medium, Solver=gpt-5.1 medium2025.12581.31———
BRAIDGenerator=gpt-5 medium, Solver=gpt-5 nano medium2025.125716.23———
BRAIDGenerator=gpt-5 medium, Solver=gpt-5.1 none2025.12572.53———
BRAIDGenerator=gpt-5 mini minimal, Solver=gpt-5 mini medium2025.12575.21———
BRAIDGenerator=gpt-5 nano minimal, Solver=gpt-5 medium2025.12571.31———
BRAIDGenerator=gpt-5 mini medium, Solver=gpt-5 minimal2025.12562.97———
BRAIDGenerator=gpt-5 nano minimal, Solver=gpt-5.1 none2025.12562.81———
BRAIDGenerator=gpt-5 medium, Solver=gpt-5 mini minimal2025.125515.34———
BRAIDGenerator=gpt-5 minimal, Solver=gpt-5 mini minimal2025.125514.7———
BRAIDGenerator=gpt-5 minimal, Solver=gpt-5.1 none2025.12552.52———
BRAIDGenerator=gpt-5 nano minimal, Solver=gpt-5 mini medium2025.12555.8———
BRAIDGenerator=gpt-5.1 medium, Solver=gpt-5 mini medium2025.12556.38———
BRAIDGenerator=gpt-5 mini medium, Solver=gpt-5 mini medium2025.12545.14———
BRAIDGenerator=gpt-5 minimal, Solver=gpt-5 nano medium2025.125414.97———
BRAIDGenerator=gpt-5.1 none, Solver=gpt-5 minimal2025.12533.18———
BRAIDGenerator=gpt-5.1 none, Solver=gpt-5 nano medium2025.125314.23———
BRAIDGenerator=gpt-5.1 medium, Solver=gpt-5 mini minimal2025.125214.47———
BRAIDGenerator=gpt-5.1 medium, Solver=gpt-5 nano medium2025.125214.57———
BRAIDGenerator=gpt-4o, Solver=gpt-5.1 none2025.12512.62———
BRAIDGenerator=gpt-5 medium, Solver=gpt-4o2025.12512.73———
BRAIDGenerator=gpt-5.1 medium, Solver=gpt-5.1 none2025.12512.36———
BRAIDGenerator=gpt-5 mini medium, Solver=gpt-5.1 none2025.12502.08———
BRAIDGenerator=gpt-5 mini minimal, Solver=gpt-5 nano medium2025.125013.71———
BRAIDGenerator=gpt-5 mini minimal, Solver=gpt-5.1 none2025.12501.99———
BRAIDGenerator=gpt-5 nano medium, Solver=gpt-5 mini medium2025.12495.07———
BRAIDGenerator=gpt-5.1 medium, Solver=gpt-5 minimal2025.12492.93———
RTT-CSR (Ours)Backbone=Qwen3-4B-Instruct2026.0448.39—80.77——
BRAIDGenerator=gpt-4o, Solver=gpt-5 mini minimal2025.124815.54———
RTT-AON (Ours)Backbone=Qwen3-4B-Instruct2026.0447.48—80.79——
RL-AONBackbone=Qwen3-4B-Instruct2026.0447.29—79.69——
BRAIDGenerator=gpt-5 mini medium, Solver=gpt-5 nano medium2025.124711.45———
BRAIDGenerator=gpt-5 nano medium, Solver=gpt-5 nano medium2025.124713.19———
BRAIDGenerator=gpt-5 nano minimal, Solver=gpt-5 minimal2025.12473.8———
RL-CSRBackbone=Qwen3-4B-Instruct2026.0446.02—79.81——
BRAIDGenerator=gpt-5 minimal, Solver=gpt-4o2025.124612.76———
BRAIDGenerator=gpt-5.1 medium, Solver=gpt-4o2025.12462.36———
BRAIDGenerator=gpt-5.1 none, Solver=gpt-4o2025.12462.34———
DPOBackbone=Qwen3-4B-Instruct2026.0445.71—79.33——
SFTBackbone=Qwen3-4B-Instruct2026.0445.07—79.23——
BRAIDGenerator=gpt-4o, Solver=gpt-5 minimal2025.12453.02———
BRAIDGenerator=gpt-5 mini minimal, Solver=gpt-5 minimal2025.12452.33———
BRAIDGenerator=gpt-5 nano medium, Solver=gpt-5 mini minimal2025.124513.39———
Qwen3-4B-Instruct†Backbone=Qwen3-4B-Instruct2026.0444.31—79.17——
BRAIDGenerator=gpt-4o, Solver=gpt-5 nano medium2025.124411.74———
BRAIDGenerator=gpt-5 minimal, Solver=gpt-5 minimal2025.12442.81———
BRAIDGenerator=gpt-5 nano medium, Solver=gpt-5 minimal2025.12443.29———
BRAIDGenerator=gpt-5.1 none, Solver=gpt-5 mini minimal2025.124411.89———
BRAIDGenerator=gpt-5.1 none, Solver=gpt-5.1 none2025.12442.03———
BRAIDGenerator=gpt-5 nano medium, Solver=gpt-5.1 none2025.12431.89———
BRAIDGenerator=gpt-5 nano minimal, Solver=gpt-5 mini minimal2025.124212.29———
BRAIDGenerator=gpt-5 medium, Solver=gpt-5 nano minimal2025.124061.69———
BRAIDGenerator=gpt-5 mini medium, Solver=gpt-5 mini minimal2025.12399.88———
BRAIDGenerator=gpt-5 mini minimal, Solver=gpt-5 mini minimal2025.12399.87———
BRAIDGenerator=gpt-5 mini medium, Solver=gpt-4o2025.12386.22———
BRAIDGenerator=gpt-5 mini minimal, Solver=gpt-4o2025.12383.05———
BRAIDGenerator=gpt-5 nano minimal, Solver=gpt-5 nano medium2025.123810.36———
RTT-AON (Ours)Backbone=Llama3.2-3B-Instruct2026.0437.99—74.07——
RTT-CSR (Ours)Backbone=Llama3.2-3B-Instruct2026.0437.57—74.37——
BRAIDGenerator=gpt-5 mini minimal, Solver=gpt-5 nano minimal2025.123753.51———
BRAIDGenerator=gpt-5.1 none, Solver=gpt-5 nano minimal2025.123753.78———
RL-CSRBackbone=Llama3.2-3B-Instruct2026.0436.29—73.47——
RL-AONBackbone=Llama3.2-3B-Instruct2026.0435.32—73.53——
BRAIDGenerator=gpt-5 minimal, Solver=gpt-5 nano minimal2025.123553.25———
BRAIDGenerator=gpt-5.1 medium, Solver=gpt-5 nano minimal2025.123553.27———
BRAIDGenerator=gpt-4o, Solver=gpt-4o2025.12342.39———
RTT-CSR (Ours)Backbone=Qwen2.5-7B-Instruct2026.0433.74—73.72——
Llama3.2-3B-Instruct⋆Backbone=Llama3.2-3B-Instruct2026.0433.37—72.01——
SFTBackbone=Llama3.2-3B-Instruct2026.0432.89—72.18——
RTT-AON (Ours)Backbone=Qwen2.5-7B-Instruct2026.0432.51—72.7——
DPOBackbone=Llama3.2-3B-Instruct2026.0432.28—71.14——
RL-AONBackbone=Qwen2.5-7B-Instruct2026.0432.1—72.33——
BRAIDGenerator=gpt-5 nano medium, Solver=gpt-4o2025.12322.17———
BRAIDGenerator=gpt-5 nano minimal, Solver=gpt-4o2025.12322.17———
BRAIDGenerator=gpt-5 mini medium, Solver=gpt-5 nano minimal2025.123145.39———
RL-CSRBackbone=Qwen2.5-7B-Instruct2026.0430.91—72——
DPOBackbone=Qwen2.5-7B-Instruct2026.0430.82—70.9——
SFTBackbone=Qwen2.5-7B-Instruct2026.0429.71—69.61——
Qwen2.5-7B-Instruct†Backbone=Qwen2.5-7B-Instruct2026.0429.48—71.31——
BRAIDGenerator=gpt-4o, Solver=gpt-5 nano minimal2025.122751.47———