Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-turn task completion on TravelGym
Loading...
57.3
Task Completion Score
GRPO + Qwen2.5-8B
7.9
20.725
33.55
46.375
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
57.3
GRPO + Qwen2.5-4B
Category=RL (GRPO) Tra...
2026.04
50.9
GPT-4o
Category=Closed-Source...
2026.04
36.4
Gemini-1.5-Pro
Category=Closed-Source...
2026.04
34.7
Gemini-1.5-Flash
Category=Closed-Source...
2026.04
25.5
Qwen2.5-14B + PRIME
Category=PRIME Models
2026.04
24.8
Qwen2.5-8B + PRIME
Category=PRIME Models
2026.04
21.5
Qwen2.5-14B
Category=Open-Source LLM
2026.04
19.2
Qwen2.5-4B + PRIME
Category=PRIME Models
2026.04
18.5
Qwen2.5-32B
Category=Open-Source LLM
2026.04
17.2
Qwen2.5-8B
Category=Open-Source LLM
2026.04
15.8
Qwen2.5-4B
Category=Open-Source LLM
2026.04
14.1
GPT-4o-mini
Category=Closed-Source...
2026.04
9.8
Feedback
Search any
task
Search any
task