---
type: "post"
id: "prime-intellect-has-released-prime-rl-v0-10-2e34fd"
slug: "prime-intellect-has-released-prime-rl-v0-10-2e34fd"
title: "Prime Intellect has released prime-rl v0.10.0 and verifiers v0.4.0 ."
description: "The release makes INTELLECT Policy Optimization (IPO) the default RL loss in prime-rl v0.10.0, with ε=0.3 and no KL term."
retrieval_nugget: "The release makes INTELLECT Policy Optimization (IPO) the default RL loss in prime-rl v0.10.0, with ε=0.3 and no KL term."
published_at: "2026-10-20"
updated_at: "2026-10-20"
record_date: "2026-10-20"
date_kind: "published_at"
topics: ["models","evals","open-source"]
source_urls: ["https://github.com/PrimeIntellect-ai/prime-rl/releases/tag/v0.10.0"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:prime-intellect-has-released-prime-rl-v0-10-2e34fd"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:fb53155f2fd0a7dafabd6e34cc9223f78ec51eb39ce252fb3ea006d8f436323b","reviewed_at":"2026-10-20T08:05:15.041Z","source_evidence_count":1,"verified_claim_count":2,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":2,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"A training system’s treatment of trainer–inference disagreement is becoming an explicit algorithmic choice, not merely a nuisance to smooth over.","observed_facts":[{"text":"prime-rl v0.10.0 makes IPO the default RL loss, with ε=0.3 and no KL term.","source_urls":["https://github.com/PrimeIntellect-ai/prime-rl/releases/tag/v0.10.0"]},{"text":"The release reports Qwen3-235B-A22B SFT at 4.39 seconds per step for prime-rl versus 5.04 for torchtitan on the same stated configuration: 4 × 8 B300 and sequence length 16k.","source_urls":["https://github.com/PrimeIntellect-ai/prime-rl/releases/tag/v0.10.0"]}],"mechanism":"IPO masks a token when the absolute difference between trainer and inference probabilities exceeds ε, rather than using a ratio threshold; the release describes the mask as double-sided and independent of advantage sign.","why_now":"prime-rl v0.10.0 makes IPO its default, so teams adopting the version encounter the choice without an opt-in step.","implications":["Teams using asynchronous RL should compare IPO with their existing loss on task-specific outcomes and training stability before assuming the default is an improvement.","The published step-time comparison is tied to a specified model and setup and should not be treated as a general performance guarantee."],"evidence_boundary":"The evidence is the project’s release notes and benchmark claims; it does not establish that IPO improves every agentic RL task or that the throughput advantage transfers to other hardware and workloads.","watch_conditions":["Look for independent replications of the IPO comparison on agentic tasks that report both learning outcomes and stability, not just step speed."],"related_records":[],"new_branch_reason":"No prior New Runtime record is supplied for this specific versioned change, so this release begins a distinct analytical record."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/prime-intellect-has-released-prime-rl-v0-10-2e34fd/","markdown":"https://newruntime.com/posts/prime-intellect-has-released-prime-rl-v0-10-2e34fd.md","json":"https://newruntime.com/posts/prime-intellect-has-released-prime-rl-v0-10-2e34fd.json"}
---

# Prime Intellect has released prime-rl v0.10.0 and verifiers v0.4.0 .

## Retrieval answer

The release makes INTELLECT Policy Optimization (IPO) the default RL loss in prime-rl v0.10.0, with ε=0.3 and no KL term.

The release makes INTELLECT Policy Optimization (IPO) the default RL loss in prime-rl v0.10.0, with ε=0.3 and no KL term. IPO masks a token when the absolute difference between trainer and inference probabilities exceeds ε, rather than using a ratio threshold. The project frames this as a response to asynchronous training, where trainer and inference probabilities do not match exactly. A training system’s treatment of trainer–inference disagreement is becoming an explicit algorithmic choice, not merely a nuisance to smooth over.

IPO masks a token when the absolute difference between trainer and inference probabilities exceeds ε, rather than using a ratio threshold; the release describes the mask as double-sided and independent of advantage sign. This changes which tokens contribute to updates under asynchronous RL. prime-rl v0.10.0 makes IPO its default, so teams adopting the version encounter the choice without an opt-in step. Teams using asynchronous RL should compare IPO with their existing loss on task-specific outcomes and training stability before assuming the default is an improvement.

The release reports a Qwen3-235B-A22B SFT comparison on identical stated hardware: 4.39 seconds per step for prime-rl versus 5.04 for torchtitan, using 4 × 8 B300 and sequence length 16k. It also reports additional performance gains for other configurations. These are project-reported measurements tied to named workloads and settings, not independent validation or a general guarantee. The evidence is the project’s release notes and benchmark claims; it does not establish that IPO improves every agentic RL task or that the throughput advantage transfers to other hardware and workloads.

Look for independent replications of the IPO comparison on agentic tasks that report both learning outcomes and stability, not just step speed. No prior New Runtime record is supplied for this specific versioned change, so this release begins a distinct analytical record.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- topic hub: [Evals](https://newruntime.com/topics/evals.md): Explore the evals topic hub.
- topic hub: [Open Source](https://newruntime.com/topics/open-source.md): Explore the open-source topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)