Claude Opus 5 posts 96.0% on SWE-bench Verified in new score chart
connoraxiotes · x · 2026-07-25
- The post references a chart from Claude showing Opus 5 as highly efficient on SWE-bench.
- In the image, Opus 5 is reported at 96.0% on SWE-bench Verified, 79.2% on SWE-bench Pro, 89.5% on SWE-bench Multilingual, and 59.4% on SWE-bench Multimodal.
- The joke is that the benchmark graph feels decisive enough to “rest easy” on SWE-bench Verified.
- This is a model-performance post, with the benchmark numbers doing the real work.
Related event: Anthropic Releases Claude Opus 5: SOTA Performance at Half the Price(128 posts)→
More from Models
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11