Edition of Sunday 15 November 2026

Reading JSON at 277 GB/s in Python

Comments on “Reading JSON at 277 GB/s in Python”

Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked

Daniel Lemire's post reports that fastsimdjson, a threaded JSON library for Python 3.14's free-threaded build, counts GitHub star events across 7.6 GB of NDJSON in 55 milliseconds, about 138 GB/s on a 192-core AWS instance.

Read the original at lemire.me. 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. 26 of 62 with a score of 0.61. The panel rated it highest on new information (0.89) and technical depth (0.84), lowest on audience breadth (0.53). Placed No. 26, No. 33 by score alone: the fourth Programming & dev tools story of the day (−0.020). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Concrete, benchmarked technical write-up on parsing JSON in free-threaded Python with specific numbers and reproducible code; narrow audience and a self-promoting library lower breadth and significance.
AI judgeJudge 3gpt-5.6-luna
A highly actionable Python performance benchmark with concrete hardware, versions, methodology, comparative results, and code availability. Its main limitation is narrow applicability: exceptional throughput depends on large parallel hardware and favorable workloads.

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

0.61total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.55
  • Reader interest0.72
  • Audience breadth0.53
  • Practical relevance0.70
  • Substantiated0.83
  • Technical depth0.84
  • New information0.89
  • Counts against: Promotional0.15
  • Counts against: Overclaim0.31

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?0.540.400.700.550.30+0.24+0.131
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.710.600.850.720.25+0.26+0.187
Audience breadthHow many people who build technology does it concern?0.570.400.620.530.22+0.13+0.069
Practical relevanceHow useful is it to someone who builds software or tech products?0.780.500.820.700.32+0.22+0.154
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.0.940.700.860.830.24+0.05+0.042
Technical depthHow technically substantive is it?0.930.800.780.840.15+0.05+0.042
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.830.900.950.890.12+0.05+0.045
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.0.070.300.080.150.23−0.19−0.028
OverclaimDo the headline or conclusions claim more than the body supports?0.340.400.180.310.22−0.11−0.034
Sum of contributions+0.607
Claim-check penalty0.000
Total, as published0.607

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 #26 on Rubric, 15 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-15/26/"><img src="https://rubric.hrih.si/badge/2026-11-15/26.svg" alt="Ranked #26 on Rubric, 15 Nov 2026" width="245" height="28"></a>

Claim check

Claim check: 8 no source given. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.

  1. No source givenNumber

    The standard json.loads loop in Python reads the 7.6 GB file at 0.28 GB/s, taking 27 seconds.

    The article gives no link or citation for it.

    The article says

    “It runs at 0.28 GB/s: 27 seconds for this file”

    The source says

    No source to compare with.

  2. No source givenNumber

    On one core, fastsimdjson reads at 8 GB/s, three and a half times as fast as msgspec.

    The article gives no link or citation for it.

    The article says

    “On one core, fastsimdjson reads 8 GB/s, three and a half times as fast as msgspec”

    The source says

    No source to compare with.

  3. No source givenBenchmark result

    With 192 threads, fastsimdjson counts the stars in the 7.6 GB file in 55 milliseconds, which is 138 GB/s.

    The article gives no link or citation for it.

    The article says

    “With 192 threads, fastsimdjson counts the stars in the 7.6 GB in 55 milliseconds: 138 GB/s”

    The source says

    No source to compare with.

  4. No source givenBenchmark result

    The best pool of msgspec processes reaches 116 GB/s at 96 processes, and more processes make it slower.

    The article gives no link or citation for it.

    The article says

    “The best pool of msgspec processes reaches 116 GB/s, at 96 processes. More processes make it slower”

    The source says

    No source to compare with.

  5. No source givenGeneralization

    fastsimdjson is ahead of msgspec at every worker count, with the lead shrinking from three and a half times on one core to about 20%.

    The article gives no link or citation for it.

    The article says

    “fastsimdjson is ahead at every worker count. The lead shrinks from three and a half times on one core to about 20%”

    The source says

    No source to compare with.

  6. No source givenBenchmark result

    On the twitter file from the Pison benchmark, fastsimdjson reaches 277 GB/s, and four of the six files pass 100 GB/s.

    The article gives no link or citation for it.

    The article says

    “On the twitter file, fastsimdjson reaches 277 GB/s. Four of the six files pass 100 GB/s”

    The source says

    No source to compare with.

  7. No source givenBenchmark result

    Of the two slower files, one stays near 20 GB/s, about four times as fast as msgspec, and one is a tie with msgspec.

    The article gives no link or citation for it.

    The article says

    “one stays near 20 GB/s, still about four times as fast as msgspec, and one is a tie”

    The source says

    No source to compare with.

  8. No source givenNumber

    The orjson package is twice as fast as the json module, and msgspec is eight times as fast.

    The article gives no link or citation for it.

    The article says

    “The orjson package is twice as fast. The msgspec package, which decodes only the fields you declare, is eight times as fast”

    The source says

    No source to compare with.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 2 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 15 Nov 2026, 20:46 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 “Reading JSON at 277 GB/s in Python”

More on Rubric

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