Perplexity early evals: Gemini 4 Carbon tops WANDR benchmark for long-form research
AravSrinivas · x · 2026-10-31
Perplexity CEO Arav Srinivas shared early evals of Gemini 4 Carbon, calling it the strongest model they've seen for long-form research and answer quality, with a new SoTA on the Wide-And-Deep-Research (WANDR) benchmark.
The score-vs-cost chart shows Gemini 4 Carbon at 0.857 for $5.86 per task, ahead of Gemini 4 Argon (0.802/$7.88), GPT-6 Astra (0.735/$13.34), and Claude Opus 5.5 (0.647/$3.69); DeepSeek V4 Pro 0813 trails at 0.359 for just $0.75.
It will roll out to all Perplexity Pro and Max users inside Computer once token capacity allows.
More from Models
- Qwenputer: a full RISC-V CPU inside Qwen3.5-4B weights, running C in forward passes — armand_ruiz · 2026-10-31
- OpenAI blocks weapons details for teens, adds auto-ending chats fixated on violence — rohanpaul_ai · 2026-10-31
- Granite Switch 4.1.1 ships: update models like you update software — krvarshney · 2026-10-31
- Mistral Open-Sources Le Chonk: Top Open Model on FrontierCode, Cyberdefense-Tested by CrowdStrike and Cloudflare — tensorqt · 2026-10-31
- Stanford CS336 Lecture Explains Why DPO Compares Against a Reference, Not Two Current Probabilities — stanfordnlp · 2026-10-31
- ik_llama.cpp PR #2808 adds native runtime for China Telecom's Xing4.0-29B-A4B MoE with mHC and MLA — Any_Bus9205 · 2026-10-31