Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models795Deals30d241Policy30d72, 16 pendingSources1,108

AI Research Radar

Tuesday, May 12: 2 frontier papers out of 693 read.

2 frontier20 cleared693 papers read

Frontier

Papers rated as moving the field

How we choose

SWE Atlas

“We evaluate a range of frontier and open-weight models on SWE Atlas and find that GPT-5.4 and Opus 4.7 achieve the strongest overall performance, while even the best open-weight models score poorly.”

The authors, in the abstract

Benchmarking Coding Agents Beyond Issue Resolution

BenchmarkarXivPDF

This week in research

May 6–12: 75 cleared, 4 frontier

The week’s papers have not been sorted into fields yet.

Models under test

Papers this week that name the model

  1. GPT-5.53
  2. GPT-5.42
  3. Qwen3 8B2
  4. GPT-4.12
  5. GPT-4o mini2
  6. GPT-5.22
  7. Claude Opus 4.72
  8. GPT-5.3-Codex1

Labs publishing

Papers this week with an author at the lab

  1. Alibaba2
  2. ByteDance2
  3. Microsoft2
  4. Amazon1
  5. Tencent1

Also cleared

18 papers

All 18 papers
SIGNIFICANT ON THE BOARDS
MODEL TRACKER2,648 new benchmark results across 174 models this weekDEAL FLOW$158B disclosed AI funding this week across 61 roundsPOLICY125 policy events tracked across 7 days