Matching posts

Matching terms are highlighted

POST

DeepSeek V4.1 Flash 2.25-bit GGUF benchmarked against official API

…passed 1.1M Hugging Face downloads, and someone benchmarked it head-to-head against the official API as t…

deepseek-v4.1@DanteMMartin　Filed in No.020

22 hours agoCopy original

MiniMax M3.1 Flash on cybersecurity benchmark: 24/32 CVEs at pass@3, behind DeepSeek V4.1 Flash

An independent security benchmark found M3.1 Flash hit 24/32 CVEs at pass@3 (75%)…

minimax-m3.1@pilvar222　Filed in No.021

22 hours agoCopy original

POST

SenseTime evaluates GPT-6 Astra across 12 sim benchmarks and 8 real robots

…I just studied GPT-6-Astra across 12 simulation benchmarks and 8 real-robot platforms. They also released…

gpt-6@DataChaz　Filed in No.001

1 day agoCopy original

GPT-6.1 Terra benchmarks: Astra-level computer use at $0.29 vs $4.82 per task

Terra matches GPT-6 Astra at 57.6% on Agents' Last Exam while costing $0.29 versus $4.82 per task, and scores 85.5% on MMMU-Pro against Astra's 86.7%.

gpt-6@Marktechpost　Filed in No.001

1 day agoCopy original

Space Train benchmark: GPT-6 Astra slower and ~7x pricier than Terra

…Terra just beat GPT-6 Astra? 😱 The Space Train benchmark 🚂🪐 Same prompt for all three. • GPT-6 Astra: …

gpt-6@EnvolDev　Filed in No.001

20 hours agoCopy original

Sonnet 5.5 nears Opus 5.5 and GPT-6 Astra on a new benchmark

A user notes that on a new benchmark Sonnet 5.5 sits close to Opus 5.5 and GPT-6 Ast…

benchmark@TokenGremlin　Filed in No.001

18 hours agoCopy original

Hypersonic CFD benchmark: Opus 5.5 vs GPT-6 Astra and two others

A budget-constrained, iterative benchmark compares Claude Opus 5.5, GPT-6 Astra, DeepSeek…

gpt-6@AlicanKiraz0　Filed in No.001

13 hours agoCopy original

Gemini 4 Argon leads pathology slide benchmark at 32% pass@1

On a 100-task benchmark spanning 55 microscope slides and 7 tumor types…

gemini-4@dylantirandaz　Filed in No.008

21 hours agoCopy original

POST

600M Persian vision model claims benchmarks rival Gemini Argon

…claiming it competes with Gemini Argon on their benchmarks.

gemini-4@iamRezaSayar　Filed in No.008

15 hours agoCopy original

Video: Gemini 4 Argon beats GPT-6 Astra on new CS research benchmark

… GPT-6 Astra on a new computer-science research benchmark, with comparison footage attached.

gemini-4@Saboo_Shubham_　Filed in No.008

1 day agoCopy original

Showing10of60posts

10 per batch

Keep scrolling to reveal posts 11–20

Showing the first 60 matches. Narrow the query with a model name or tag to find more specific results.