Edition of Tuesday 17 November 2026

Benchmarking OSS inference vendors on cost/latency

Comments on “Benchmarking OSS inference vendors on cost/latency”

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

The powerset-co inference-bench repo is a beta benchmark that compares open-source LLM inference providers on speed and list-price cost while serving a single AI research agent. It replays recorded FRAMES-based Wikipedia research conversations across providers, timing only model calls, with quality deliberately unmeasured.

Read the original at github.com. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Why it ranked

No. 76 of 122 with a score of 0.60. The panel rated it highest on new information (0.89) and substantiated (0.75), lowest on significance (0.47). The judges disagreed most on substantiated (spread 0.44), so the story is marked contested. Placed No. 76, No. 66 by score alone: the 22nd AI & machine learning story of the day (−0.080). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
On-topic for AI infrastructure builders; beta benchmark of provider latency and cost for open-source LLMs with transparent methodology and caveats, but limited scope and significance for most readers.
AI judgeJudge 3gpt-5.6-luna
A reproducible, open benchmark compares OSS inference providers on latency and list-price cost, with methodology, caveats, raw data, and code. It is directly useful for AI infrastructure decisions, though beta scope and single-agent workloads limit significance.

Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.

Score

0.60total under rubric v2.3Contestedjudges differ by 0.44 on substantiated

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.47
  • Reader interest0.65
  • Audience breadth0.53
  • Practical relevance0.74
  • Substantiated0.75
  • Technical depth0.71
  • New information0.89
  • Counts against: Promotional0.09
  • Counts against: Overclaim0.12

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.520.300.580.470.28+0.24+0.112
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.640.500.800.650.30+0.26+0.168
Audience breadthHow many people who build technology does it concern?0.580.400.620.530.22+0.13+0.069
Practical relevanceHow useful is it to someone who builds software or tech products?0.810.600.820.740.22+0.22+0.163
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.940.500.800.750.44 , above the contested threshold+0.05+0.037
Technical depthHow technically substantive is it?0.820.550.770.710.27+0.05+0.036
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.840.900.920.890.08+0.05+0.044
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.080.150.030.090.12−0.19−0.016
OverclaimDo the headline or conclusions claim more than the body supports?0.140.200.020.120.18−0.11−0.013
Sum of contributions+0.601
Claim-check penalty0.000
Total, as published0.601

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.

Ranked #76 on Rubric, 17 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-17/76/"><img src="https://rubric.hrih.si/badge/2026-11-17/76.svg" alt="Ranked #76 on Rubric, 17 Nov 2026" width="245" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 1 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 17 Nov 2026, 05:47 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “Benchmarking OSS inference vendors on cost/latency”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.