---
type: "post"
id: "independent-lab-run-of-flint-skipped-coding-scores-963341"
slug: "independent-lab-run-of-flint-skipped-coding-scores-963341"
title: "Independent lab run of Flint skipped coding scores after calling 89.7 implausible"
description: "FreshContext published results from a local run of Recursive Flint, a 39.8-billion-parameter mixture-of-experts model with about 2.5 billion active parameters per token."
retrieval_nugget: "FreshContext published results from a local run of Recursive Flint, a 39.8-billion-parameter mixture-of-experts model with about 2.5 billion active parameters per token."
published_at: "2026-10-27"
updated_at: "2026-10-27"
record_date: "2026-10-27"
date_kind: "published_at"
topics: ["harness-engineering","agent-runtime"]
entities: ["FreshContext","Recursive","Flint","llama.cpp","SWE-bench Pro v2","SWE-bench Verified"]
related_patterns: ["harness-architecture-outlives-model-choice"]
novelty_label: "new_fact"
what_changed: "FreshContext’s independent Flint evaluation skipped coding scores after judging the 89.7 claim implausible; its tests instead found strong structured extraction but tool use that needed explicit prompting."
prior_refs: ["memory:b92d08d3-3119-8f13-a6fd-92ebe76fc281","memory:bedacec7-1089-8a65-a26e-b64203923903"]
source_url: "https://freshcontext.io/benchmarks/models/flint"
source_urls: ["https://freshcontext.io/benchmarks/models/flint"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:independent-lab-run-of-flint-skipped-coding-scores-963341"
status: "published"
visuals: []
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/independent-lab-run-of-flint-skipped-coding-scores-963341/","markdown":"https://newruntime.com/posts/independent-lab-run-of-flint-skipped-coding-scores-963341.md","json":"https://newruntime.com/posts/independent-lab-run-of-flint-skipped-coding-scores-963341.json"}
---

# Independent lab run of Flint skipped coding scores after calling 89.7 implausible

## Retrieval answer

FreshContext published results from a local run of Recursive Flint, a 39.8-billion-parameter mixture-of-experts model with about 2.5 billion active parameters per token.

FreshContext published results from a local run of Recursive Flint, a 39.8-billion-parameter mixture-of-experts model with about 2.5 billion active parameters per token. The lab used Recursive’s official Q4_1 GGUF file, llama.cpp b11846, a Mac Studio, one conversation at a time, and 64K context. Its recorded run peaked at 26.4 GB of memory.

Across 15 scored tests, FreshContext reported 98.3% (59/60) on checking extractions and 100% (15/15) on choosing and chaining named tools. Flint was much less likely to call a tool without explicit instruction: it scored 2/12 when a tool held the answer but was not mentioned, and 1/12 when no tool was mentioned. Median generation speed was 74.2 tokens per second; the lab estimated that reading a fresh 32,000-token prompt took about 70 seconds.

FreshContext did not run coding benchmarks. It says Recursive’s reported 89.7 SWE-bench Pro v2 result looked implausibly high beside a 74.2 SWE-bench Verified result, but its own work neither reproduces nor disproves either coding score. The source also does not establish how Flint compares with Qwen3.6-35B-A3B on coding or whether llama.cpp matches Recursive’s own runtime results.

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: [Harness Engineering](https://newruntime.com/topics/harness-engineering.md): Explore the harness-engineering topic hub.
- topic hub: [Agent Runtime](https://newruntime.com/topics/agent-runtime.md): Explore the agent-runtime 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)