Benchmarks - DEV Community

Skip to content

DEV Community

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Jonathan Murray

Aug 12

We hit 99.95% on the LoCoMo memory benchmark. Here's the catch, and why it still matters.

#ai #benchmarks #webdev #software

4 min read

Tommy Leonhardsen

Aug 11

Twelve LLMs Played Werewolf. The Real Wolf Was the Thinking Knob.

#llm #benchmarks #reasoning #latency

8 min read

Peremptory

Aug 7

Meta's Muse Code Clears 59% on Deep Software Engineering

#modelrelease #developertools #benchmarks #codingmodels

2 min read

Lola Lin

Jul 28

Kimi K3 for Coding: Real-World Performance Tests and Benchmarks (2026)

#kimik3 #coding #benchmarks #softwareengineering

9 min read

Pneumetron

Jul 17

SynthDocBench: A New Benchmark for Long-Context Visual Document Understanding Reveals VLM Weaknesses

#visionlanguagemodels #vlm #documentunderstanding #benchmarks

4 min read

Pneumetron

Jul 13

UniClawBench: A New Benchmark for Proactive AI Agents in Real-World Scenarios

#aiagents #benchmarks #llms #mllms

3 min read

Jul 11

AI News Roundup: Grok 4.5 Hits Tesla, Perplexity's Orchestrator Beats Opus, and Meta Undercuts Pricing

#news #industry #benchmarks #launches

2 min read

Muhammed Rasin O M

Jul 10

Half the answer keys in text-to-SQL benchmarks are wrong. So I generated the database from the answer key.

#evaluation #dataagents #benchmarks #syntheticdata

7 min read

Levash0v

Jul 7

Agent Leaderboards Measure Score. We Added Price.

#ai #agents #llm #benchmarks

5 min read

Aliaksei Zelianouski

Aug 6

How I tried to write an article about slow Chinese LLMs

#ai #llm #benchmarks #latency

10 min read

Breach Protocol

Jul 2

Turn the camera away, and the AI's world freezes

#worldmodels #videogeneration #robotics #benchmarks

3 min read

Breach Protocol

Jul 1

Reliable, and still wrong

#evaluation #llmasjudge #benchmarks

3 min read

Breach Protocol

Jul 1

Put AI agents in charge of a Civilization game and they reach for the nukes

#agents #alignment #safety #benchmarks

3 min read

Peremptory

Jun 12

Claude Fable 5 Scores 95% on SWE-bench, Then Hands Off to Opus 4.8

#anthropic #claude #benchmarks #safety

3 min read

Arthur

Jun 11

An LLM benchmark is only useful for as long as it's hard

#llm #evaluation #benchmarks #humaneval

10 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.