Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-turn task completion on SearchGym
Loading...
92.8
Task Completion Score
Gemini-1.5-Pro
32.896
48.448
64
79.552
Apr 8, 2026
Task Completion Score
Updated 3mo ago
Evaluation Results
Method
Method
Links
Task Completion Score
Gemini-1.5-Pro
Category=Closed-Source...
2026.04
92.8
Gemini-1.5-Flash
Category=Closed-Source...
2026.04
92.8
Qwen2.5-14B + PRIME
Category=PRIME Models
2026.04
89.2
GRPO + Qwen2.5-8B
Category=RL (GRPO) Tra...
2026.04
88.8
GPT-4o
Category=Closed-Source...
2026.04
88
Qwen2.5-8B + PRIME
Category=PRIME Models
2026.04
87.2
GRPO + Qwen2.5-4B
Category=RL (GRPO) Tra...
2026.04
86.4
Qwen2.5-4B + PRIME
Category=PRIME Models
2026.04
86
Qwen2.5-4B
Category=Open-Source LLM
2026.04
85.6
Qwen2.5-8B
Category=Open-Source LLM
2026.04
80.8
Qwen2.5-32B
Category=Open-Source LLM
2026.04
79.2
Qwen2.5-14B
Category=Open-Source LLM
2026.04
51.2
GPT-4o-mini
Category=Closed-Source...
2026.04
35.2
Feedback
Search any
task
Search any
task