← all tags

#benchmarks

3 posts tagged benchmarks.

News & Updates

DeepSeek R1 vs Claude 3.5: a head-to-head on real tasks

Ran both models through the same set of coding and reasoning tasks. Results were closer than expected.

deepseek claude benchmarks comparison

Testing Kimi k1.5: the reasoning model nobody's talking about

Moonshot AI's Kimi k1.5 quietly dropped and it's genuinely impressive on long reasoning tasks.

kimi reasoning benchmarks moonshot-ai

Thoughts

Agent benchmarks are just unit tests for unpredictable systems

We're measuring agent performance like it's deterministic software when the whole point is emergent behaviour.

agentic-ai benchmarks testing evaluation