0

Agent Bench RL Env (Prime Community)

Fresh

Benchmarking model performance on SWE Bench in the Mini SWE Agent harness.

Type
RL Env
Publisher
Prime Community
Tags
Tool UseAgent
Runtime
multi-turn
License
unknown
Size
v0.1.0
Published
Mar 2026
Canonical
app.primeintellect.ai/dashboard/environments/prime-community/mini-swe-agent-bench

Cite

Notes

Only stored in your browser.

Attribution

Scores
prime-hub
Attribution policy →

Public scores on this env

3

4 vf-eval reports across 3 models

1GPT-5disputed93.3%2Claude 4 Sonnet86.7%3GPT-5 Mini80.0%
Open the scoring view →

Lift evidence

6
EvalTools known to liftSource paper
SWE-benchAgent Bench RL Env (Prime Community)-
SWE-bench LiteAgent Bench RL Env (Prime Community)-
SWE-bench VerifiedAgent Bench RL Env (Prime Community)-
SWE-bench MultimodalAgent Bench RL Env (Prime Community)-
SWE-bench MultilingualAgent Bench RL Env (Prime Community)-
SWE-bench Verified: Resolving Real-World GitHub IssuesAgent Bench RL Env (Prime Community)-