PulseAugur
EN
LIVE 13:24:54

GLM-5.3 (Low) achieves 36.6% on Humanity's Last Exam, shows cost efficiency

By PulseAugur Editorial · [1 sources] ·

The GLM-5.3 (Low) model achieved a score of 36.6% on the Humanity's Last Exam benchmark. Notably, it demonstrated a cost-efficiency of 10.7 intelligence points per dollar, running at a speed of 75.7 tokens per second. AI

IMPACT Demonstrates a specific cost-efficiency metric for LLMs, potentially influencing future model development and deployment strategies.

RANK_REASON Model benchmark results published on a social media platform. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

GLM-5.3 (Low) achieves 36.6% on Humanity's Last Exam, shows cost efficiency

How we ranked this

Signal score
12 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Model benchmark results published on a social media platform. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · opensourceaitech ·

    📊 GLM-5.3 (Low) scores 36.6% on Humanity's Last Exam while running at 75.7 tokens/sec. The standout is 10.7 intelligence points per dollar — a real cost-efficie

    📊 GLM-5.3 (Low) scores 36.6% on Humanity's Last Exam while running at 75.7 tokens/sec. The standout is 10.7 intelligence points per dollar — a real cost-efficiency figure, measured independently. That's the math worth checking. https:// olud.ai/leaderboard.html # LLM # Benchmarks…

    LINKS olud.ai/leaderboard.html

RELATED ENTITIES

RELATED TOPICS