SWE-bench

mentions 82 type Organization page 5/5 feed RSS

// recent coverage 82 mentions

19:57

2026-05-27

deepswe.datacurve.ai

ai-agents

DeepSWE Measuring frontier coding agents

DataCurve released DeepSWE, a new benchmark for evaluating frontier coding agents on original, long-horizon software engineering tasks. The benchmark features contamination-free tasks written from scr…

01:01

2026-05-20

dev.to

artificial-intelligence

DeepSeek V4 vs Claude Opus 4.5 for coding: benchmark comparison

Claude Opus 4.5 achieves an 80.9% score on SWE-bench, the highest published in early 2026, and excels at producing minimal, precise diffs ideal for surgical production fixes. DeepSeek V4 is stronger f…

← prev page 5 / 5

// co-occurs with top 8 entities

Anthropic 21 Claude Code 16 GitHub 12 OpenAI 10 HumanEval 7 Claude Fable 5 6 Cursor 6 Claude Opus 4.8 5

// topics top 6 topics

ai agents 56 large language models 53 ai research 46 artificial intelligence 44 ai tools 37 developer tools 35