Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-turn task completion on TelepathyGym
Loading...
90.2
Task Completion Score
Gemini-1.5-Pro
1.488
24.519
47.55
70.581
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
90.2
GPT-4o
Category=Closed-Source...
2026.04
85.4
Gemini-1.5-Flash
Category=Closed-Source...
2026.04
63.4
GRPO + Qwen2.5-4B
Category=RL (GRPO) Tra...
2026.04
63.4
Qwen2.5-14B + PRIME
Category=PRIME Models
2026.04
63.2
Qwen2.5-14B
Category=Open-Source LLM
2026.04
58.5
Qwen2.5-32B
Category=Open-Source LLM
2026.04
56.1
GRPO + Qwen2.5-8B
Category=RL (GRPO) Tra...
2026.04
56.1
Qwen2.5-4B + PRIME
Category=PRIME Models
2026.04
55.8
Qwen2.5-8B + PRIME
Category=PRIME Models
2026.04
52.4
Qwen2.5-8B
Category=Open-Source LLM
2026.04
51
Qwen2.5-4B
Category=Open-Source LLM
2026.04
48.8
GPT-4o-mini
Category=Closed-Source...
2026.04
4.9
Feedback
Search any
task
Search any
task