Nemotron 3 Ultra Closes Gap on Opus
hwchase17 · x · 2026-07-10
Citing LangChain's claims, the post notes that in their internal deep-agents benchmark, Nemotron 3 Ultra scored 86%, just 1 percentage point behind Claude Opus 4.8 at 87%.
It emphasizes that Nemotron 3 Ultra costs about a tenth of its competitor and allows for downloadable weights for self-deployment. However, it cautions that these are self-reported benchmark results requiring third-party verification.
Related event: NVIDIA and LangChain Tune Deep Agents: Nemotron 3 Ultra Nears Opus(6 posts)→
More from Models
- Grok 4.7 lands as OpenAI suspends $200 ChatGPT Pro plans — iannuttall · 2026-09-11
- BullshitBench update: GPT-6-Astra beats all prior OpenAI models but still trails Anthropic — scaling01 · 2026-09-11
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11