Sixteen LLMs find new TIS-100 score frontiers on 18 of 55 puzzles
Opus 5.5 and GPT-6 Astra each solved all 55; Opus found 72 new frontier points to Astra's 32.
1
Stories per day · 30 days
3 RSS
Relatedcode-generation3evaluation2adversarial-rewriting1attack-reasoning1binary-analysis1complexity1cultural-evaluation1culturalriddles1embedded-software1frontier-models1grid-bench1health-coaching1indirect-calls1interprocedural1multilingual1np-complete1open-weights1reverse-engineering1
13 stories, newest first · one card per story
Stories tagged #llm-benchmark
RealEmbedBench scores LLMs on 5,142 embedded software tasks
Harmony-to-RT-Thread translation averages a 0.1667 pass rate, and executable state-machine code remains weak.
ICALL-BENCH tests LLM interprocedural reasoning on real binaries
On 50 C/C++ programs, five models’ verifiable success ranged from 23% to 81%, and more information access did not reliably help the hardest cases.
MoveBench evaluates 15 LLMs on sports and health coaching
Models were scored on 809 questions and 5,012 rubric criteria covering safety, validity, and personalization.
SecLog-Bench measures LLM reasoning over cybersecurity logs
With scaffolded evidence, the best of eight models reached 44.44% accuracy and 45.07% Macro-F1.
P2NPCBench finds LLMs weaker on NP-complete twins than on P problems
Twelve models score 35.4% pass@1 on NPC items versus 63.8% on paired P twins; extra time barely helps.
CulturalRiddles benchmarks LLMs on riddles from 62 cultures
Across 28 model configurations, even frontier systems reach at most 22% accuracy in some communities.
Grid-Bench: Can LLMs Predict How Discrete Worlds Change?
Grid-Bench tests whether LLMs can predict full grid states after sequences of spatial operations.
Write Like It's 1866: LLMs Relearn Telegraphese
A benchmark finds LLMs can store records in telegraph-style cablese, cutting tokens by up to 49 percent without hurting later answers.
8
Do Large Language Models Know Colombian Law? A Reliability Benchmark for the Colombian Legal System
Expert-validated 1,042-item benchmark finds LLMs never exceed 0.45 free-text correctness on Colombian law, with about half of cited legal norms wrong or nonexistent.
These Tech Workers Made ChatGPT Drive a Toyota Corolla
DrivingBench trio connected off-the-shelf LLMs to a rented Corolla's controls; only GPT-6 Astra completed their parking-lot cone course.
3
UN turns to Google to make its global data ready for AI agents
UN and Google launch UN System Data Commons for AI agents; UNICEF benchmark finds six major LLMs answered global statistics questions with just 21.2% accuracy.
1
Show HN: Pelican-bicycle alternatives (updated for 2026)
Hobbyist benchmark re-runs the pelican-bicycle SVG test on six 2026 frontier models, comparing generation time and API cost per image.
7