Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-turn task completion on TurtleGym
Loading...
29.2
Task Completion Score
GPT-4o
7.672
13.261
18.85
24.439
Apr 8, 2026
Task Completion Score
Updated 3mo ago
Evaluation Results
Method
Method
Links
Task Completion Score
GPT-4o
Category=Closed-Source...
2026.04
29.2
Gemini-1.5-Pro
Category=Closed-Source...
2026.04
27.4
Gemini-1.5-Flash
Category=Closed-Source...
2026.04
19.6
GRPO + Qwen2.5-8B
Category=RL (GRPO) Tra...
2026.04
19.2
GRPO + Qwen2.5-4B
Category=RL (GRPO) Tra...
2026.04
18.4
Qwen2.5-14B + PRIME
Category=PRIME Models
2026.04
16.8
Qwen2.5-32B
Category=Open-Source LLM
2026.04
15.1
Qwen2.5-14B
Category=Open-Source LLM
2026.04
14.2
Qwen2.5-8B + PRIME
Category=PRIME Models
2026.04
14.2
Qwen2.5-4B + PRIME
Category=PRIME Models
2026.04
13.2
Qwen2.5-8B
Category=Open-Source LLM
2026.04
9.8
GPT-4o-mini
Category=Closed-Source...
2026.04
9.1
Qwen2.5-4B
Category=Open-Source LLM
2026.04
8.5
Feedback
Search any
task
Search any
task