Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-turn task completion on IntentionGym
Loading...
1.903
Task Completion Score
GRPO + Qwen2.5-8B
0.18388
0.63019
1.0765
1.52281
Apr 8, 2026
Task Completion Score
Updated 3mo ago
Evaluation Results
Method
Method
Links
Task Completion Score
GRPO + Qwen2.5-8B
Category=RL (GRPO) Tra...
2026.04
1.903
GPT-4o
Category=Closed-Source...
2026.04
1.898
Qwen2.5-32B
Category=Open-Source LLM
2026.04
1.83
Qwen2.5-8B + PRIME
Category=PRIME Models
2026.04
1.825
GRPO + Qwen2.5-4B
Category=RL (GRPO) Tra...
2026.04
1.808
Qwen2.5-14B + PRIME
Category=PRIME Models
2026.04
1.782
Qwen2.5-4B + PRIME
Category=PRIME Models
2026.04
1.772
Qwen2.5-4B
Category=Open-Source LLM
2026.04
1.74
Qwen2.5-8B
Category=Open-Source LLM
2026.04
1.725
Qwen2.5-14B
Category=Open-Source LLM
2026.04
1.7
Gemini-1.5-Flash
Category=Closed-Source...
2026.04
1.685
Gemini-1.5-Pro
Category=Closed-Source...
2026.04
1.59
GPT-4o-mini
Category=Closed-Source...
2026.04
0.25
Feedback
Search any
task
Search any
task