DeepSeek V4.1 Flash posts gamed-benchmark gains; Bindu Reddy tests if it beats frontier
bindureddy · x · 2026-10-17
Bindu Reddy shared the DeepSeek V4.1 Flash benchmark table with a jab: 'looks amazing on the benchmarks that can be gamed.' The table shows V4.1-Flash-1017 leading agent benchmarks like DeepSWE v1.1 (77.0), Automation-Bench (60.5) and Apex Bench (72.1) over Kimi K3, GLM 5.3, GPT 5.6-Sol and Claude Opus 5, while still trailing Opus 5 on HLE (42.6 vs 56.3) and Terminal-Bench 4.0 (42.3 vs 51.8). He says he's testing whether it truly beats frontier models.
Related event: DeepSeek V4.1 Flash Shines in Bug Hunt Bench Amid Cheating Allegations(11 posts)→
More from Models
- MBZUAI Releases Jais 3: Six Open Arabic Models from 0.9B to 375B with Full Training Recipe — lmoroney · 2026-10-19
- Opus 5.5 hailed as a milestone: developers say they've stopped chasing new models — dreamwieber · 2026-10-19
- Six frontier AIs design egg-drop capsules; Claude Opus 5.5 survives 20 feet — 141_1337 · 2026-10-19
- Google AI Pro users from Pixel/Jio/student offers locked out of Gemini 4 Argon in Antigravity — MicahBerkley · 2026-10-19
- Gwern's "Truesight" Directory Collects LLM Stylometry De-anonymization Research — voooooogel · 2026-10-19
- SlopCodeBench: Best AI Coding Agent Solved Just 14.8% of Evolving Task Checkpoints — aj_marshall · 2026-10-19