GPT-6 Astra Low

Scores

Dimension	Score	Rank	Benchmarks
Overall: Balanced	62.8	54	8
Overall: Coding	61.3	74	7
Overall: Reasoning	65.6	27	5
Overall: Agentic work	62.4	53	7
Overall: Frontend	60.0	72	2
Coding	60.0	89	2
Agents	62.6	32	1
Reasoning	66.0	34	4
Math	65.2	18	1
Value vs price	+4.1	147

Unverified rumours 😃 Physical AI anxiety and Huawei Ascend pretraining: Sources close to DeepSeek note that OpenAI's GPT 6 Astra hitting 95% accuracy on a robotic control task (versus 40% for Claude Fable 5.1) triggered internal concern that scaling text and code LLMs alone wi…@IamEmily2050 · 28 likes · negative
TOWARD WEIGHT-SPACE PROGRAMMING MIT CSAIL researchers recently had a frontier model, GPT-6 Astra, fix another AI by editing its weights directly. No training. They call it weight-space programming. Could a model running on my own Mac do that kind of brain surgery? Test 1 The…@NickGeorgeSEO · 5 likes
Which model has the best overall intelligence? - Gemini 4 Carbon - Fable 5.2 - Opus 5.5 - GPT-6.2 Sol - GPT-6 Astra@ItsKamranK · 2 likes

Benchmark	Result	Source	Date
DeepSWE	67.0%	Epoch AI	2026-11-11
SciCode	54.1%	Epoch AI	2026-11-11

Benchmark	Result	Source	Date
Terminal-Bench 4	50.9%	Terminal-Bench	2026-09-03

Benchmark	Result	Source	Date
CritPt	26.3%	Epoch AI	2026-11-11
ARC-AGI-2	85.4%	Epoch AI	2026-11-11
ARC-AGI-1 (ARC Prize verified)	96.5%	ARC Prize	2026-11-11
ARC-AGI-1	96.5%	Epoch AI	2026-11-11
ARC-AGI-2 (ARC Prize verified)	85.4%	ARC Prize	2026-11-11
ARC-AGI-3	98.0%	ARC Prize	2026-11-11

Benchmark	Result	Source	Date
FrontierMath Tier 4	87.8%	Epoch AI	2026-08-30

Benchmark	Result	Source	Why not used
ARC-AGI-3	17.5%	ARC Prize	Lower duplicate run on the same benchmark

gpt-6-astra-low