SWE-bench Pro leaderboard puts Ornith-1.0-397B and GLM-5.2 at the top
victormustar · x · 2026-07-22
SWE-bench Pro leaderboard update
The screenshot shows the SWE-bench Pro leaderboard on Hugging Face.
- deepreinforce-ai/Ornith-1.0-397B leads with 62.2.
- zai-org/GLM-5.2 is close behind at 62.1.
- poolside/Laguna-S-2.1 ranks third at 59.4.
- Several other models cluster around 59–58 points, including MiniMax-M3, Kimi-K2.6, GLM-5.1, Hy3, and MiMo-V2.5-Pro.
The image is a compact snapshot of how current models are stacking up on a software-engineering benchmark.
More from Models
- Meta's Muse Agent has built-in invite code logic, hinting at free-usage expansion — testingcatalog · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Claude is no longer available for minors as Anthropic rolls out age assurance — Muhammad523 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11