Tagged articles

hallucination rate

3 articles · Page 1 of 1

Oct 16, 2026 · Artificial Intelligence

Gemini 4 Argon Flops in Coding Tests: 51% Hallucination Rate, Trails Claude Opus 5.5

Hands-on testing reveals Gemini 4 Argon scores 3.95 in blind code audit with 51% hallucination rate, far behind Claude Opus 5.5's 8.40, while also struggling in 3D rendering; Google's internal success metrics rely on specialized tooling absent in external workflows.

3D renderingAI model benchmarkingClaude Opus 5.5

0 likes · 8 min read

Gemini 4 Argon Flops in Coding Tests: 51% Hallucination Rate, Trails Claude Opus 5.5

AI Engineering

Oct 1, 2026 · Artificial Intelligence

Gemini 4 Argon Matches GPT-6 Astra Benchmarks with Lowest Hallucination Rate

Google DeepMind's Gemini 4 Argon matches GPT-6 Astra on key benchmarks while achieving a 15% hallucination rate—the lowest among peers—with a 1M token output limit, aggressive introductory pricing, and a security-first rollout to network defenders.

AI benchmarksAgent CapabilitiesGPT-6 Astra

0 likes · 9 min read

Gemini 4 Argon Matches GPT-6 Astra Benchmarks with Lowest Hallucination Rate

Lao Guo's Learning Space

Apr 27, 2026 · Artificial Intelligence

DeepSeek V4 & Huawei Ascend 950PR: Is Domestic Compute Ready for Enterprise AI?

DeepSeek V4, paired with Huawei’s Ascend 950PR chip, delivers inference speed up to 2.87× that of Nvidia H20 and introduces a CSA+HCA attention compression that cuts KV cache usage to under 10%, but its 94‑96% hallucination rate and high token consumption raise concerns for production use.

AI inferenceAgent tasksCSA+HCA

0 likes · 13 min read

DeepSeek V4 & Huawei Ascend 950PR: Is Domestic Compute Ready for Enterprise AI?