Joel Niklaus

joelniklaus's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a Space about 7 hours ago

Running

120

Harness Leaderboard

🧭

120

Which coding-agent harness should you use for your model?

updated a bucket about 19 hours ago

joelniklaus/harness-leaderboard

256 GB

updated a dataset 6 days ago

joelniklaus/swiss-ai-research

Viewer • Updated 6 days ago • 977k • 1.22k

published an article 23 days ago

view article

Article

Switzerland Does Top AI Research, but Too Little of It Stays

• 

joelniklaus

•

23 days ago

• 2

published a Space 24 days ago

Running

120

Harness Leaderboard

🧭

120

Which coding-agent harness should you use for your model?

published a bucket 24 days ago

joelniklaus/harness-leaderboard

256 GB

published a dataset 24 days ago

joelniklaus/swiss-ai-research

Viewer • Updated 6 days ago • 977k • 1.22k

updated a bucket 27 days ago

joelniklaus/harness-optimization-results

126 GB

updated a bucket 29 days ago

joelniklaus/harness-optimization-results

126 GB

updated a Space about 1 month ago

Running on CPU Upgrade

294

The Synthetic Data Playbook: Generating Trillions of the Finest Tokens

📝

294

Explore synthetic data experiments on a bookshelf visualization

authored a paper about 1 month ago

Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior

Paper • 2609.39827 • Published Sep 30 • 11

liked a Space about 1 month ago

Running

288

The ultimate guide to multi-harness RL

🔀

288

Train open models with RL inside real agent harnesses

updated a dataset about 2 months ago

joelniklaus/LEXam-hard

Benchmark • Updated Sep 11 • 518 • 918 • 32

New activity in LiquidAI/LFM2.5-8B-A1B about 2 months ago

Add LEXam-hard evaluation result

#35 opened about 2 months ago by

joelniklaus

New activity in allenai/Olmo-3.1-32B-Think about 2 months ago

Add LEXam-hard evaluation result

#6 opened about 2 months ago by

joelniklaus

New activity in meta-llama/Llama-3.3-70B-Instruct about 2 months ago

Add LEXam-hard evaluation result

#168 opened about 2 months ago by

joelniklaus

New activity in swiss-ai/Apertus-v1.5-70B about 2 months ago

Add LEXam-hard evaluation result

👍 1

1

#7 opened about 2 months ago by

joelniklaus

New activity in Qwen/Qwen3.5-35B-A3B about 2 months ago

Add LEXam-hard evaluation result

#85 opened about 2 months ago by

joelniklaus

New activity in mistralai/Mistral-Medium-3.5-128B about 2 months ago

Add LEXam-hard evaluation result

#34 opened about 2 months ago by

joelniklaus

New activity in openai/gpt-oss-120b about 2 months ago

Add LEXam-hard evaluation result

#232 opened about 2 months ago by

joelniklaus