List your company

Collaborative Group Problem Solving on CGPST 10 Scenarios

144CGPST Scenario 1 Scoregpt-5
98.76110.505122.25133.995Apr 8, 2026

Evaluation results

MethodLinks
gpt-5Framework=TeamLLM2026.04144139.5139.5138156143156150130132142.8
gpt-4oFramework=TeamLLM2026.04137134.5118121136.5138.5124135118123128.55
qwen3-instructFramework=TeamLLM2026.04135.5142127123.5120.5142156135.5137134.5135.35
kimi-k2Framework=TeamLLM2026.04134134133120122129107.5117127116.5124
claude-4-opusFramework=TeamLLM2026.04133.5134.5140.5132138.5144.5150.5147.5116.5129136.7
gpt-5Framework=baseline2026.04133126130.5127130126.5142139119127.5130.05
gemini-2.5-proFramework=TeamLLM2026.04130.5123121.5117.5143142.5117.5143116120127.45
deepseek-v3Framework=TeamLLM2026.04129137130.5116.5124.5114121.5102.5124.5130123
deepseek-r1Framework=TeamLLM2026.04126.5132.5114.5131135.5120.5126116119107122.85
qwen3-instructFramework=baseline2026.04116113110122.5107.5127.5125.5113117110116.2
gemini-2.5-proFramework=baseline2026.04115.5111124.5124.5115121.5123.5118116118118.75
qwen3-thinkingFramework=TeamLLM2026.04115133.5135124117.5140.5146.5111116112125.1
deepseek-v3Framework=baseline2026.04114.5104.591104.5110110116105.5104109.5106.95
deepseek-r1Framework=baseline2026.04109.599109.510497.5110119106.5103112107
claude-4-opusFramework=baseline2026.04108.5100123.5128118.5127.5133123.5109114.5118.6
kimi-k2Framework=baseline2026.04108113.5119124.5110127.5129124.5116.5115118.75
gpt-4oFramework=baseline2026.0410291104.5109.59611812410994.5110105.85
llama-4-scoutFramework=baseline2026.04101.586105.5105.591.510111010671104.598.25
llama-4-scoutFramework=TeamLLM2026.04101120.512991111116105.593107.5120109.45
qwen3-thinkingFramework=baseline2026.04100.5108.5121120.5115126.5130.5111.5103.5108114.55