ParetoRSI-Gym evaluates multi-domain recursive self-improvement
Claude Code with Opus-5 raised equal-weighted generalization scores 9.2% relative, or 2.3 absolute points, over the starting models.
48
- Mentions · 7d1
- Mentions · 30d2
- All mentions3
- First seenSep 10, 2026
- Last mentioned6d ago
Timeline
3 articles · newest firstBlenderWorld benchmarks frontier models on real-world 3D creation
GPT-6-Astra scored 79.9 overall, ahead of Opus-5 at 73.0 and GPT-5.6-Sol at 67.7.
44
DeepSeek AI Released DeepSeek-V4.1-Flash with 1M Context, FP4 KV Cache, and Cross-Layer Attention Reuse
DeepSeek released open-weight V4.1-Flash, a 552B MoE model with 1M context and FP4 KV cache, beating Opus-5 and GPT-5.6 Sol on agent benchmarks.
80
Appears with
- DeepSeek-V4-Flashai model · 1
- Transformersproduct · 1
- DeepSeek-V4.1-Flashai model · 1
- Ministral-3-3Bai model · 1
- Claude Codeproduct · 1
- Hugging Faceorganization · 1
- GPT-6-Astraai model · 1
- DeepSeekvendor · 1
- GPT-5.6-Solai model · 1
- SGLangproduct · 1
- BlenderWorldproduct · 1
- GPT-5.6ai model · 1
- Blenderproduct · 1
- vLLMproduct · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.