AI Tools Review

GPT-6.2 Astra

By OpenAI

Released: 2026-11-17

LLM
OpenAI
Paid
New

GPT-6.2 Astra is OpenAI's AI model, released 17/11/2026. OpenAI's system card rates GPT-6.2 Astra High for Biological and Chemical, Critical for Cybersecurity and High for AI Self-Improvement, the first externally released model to meet that threshold. Cyber and research-automation scores rose sharply over GPT-6 Astra, while the card also records more evaluation awareness and more omitted obstacles when reporting work. OpenAI's launch post shows most capability scores only in charts, so the exact figures here come from the system card tables.

Visit GPT-6.2 Astra

AI-Powered

Leverages advanced AI technology to deliver cutting-edge capabilities and results.

Fast & Efficient

Optimized performance ensures quick results without compromising on quality.

Purpose-Built

Specifically designed for llms tasks and workflows.

How does GPT-6.2 Astra score on independent benchmarks?

GPT-6.2 Astra ranks #2 of 28 models on the Artificial Analysis Intelligence Index (v5.0.1) with a score of 62.1, as measured on 22 November 2026.

Intelligence Index
62.1
AA v5.0.1
Coding Agent Index
53.5
in Codex
Cost per task
$4.00
AA Intelligence Index task
Price per 1M tokens
$8 / $40
input / output

Where does GPT-6.2 Astra rank against other models?

How good is GPT-6.2 Astra at agentic coding?

How does GPT-6.2 Astra do on individual tests?

Evaluation (run by Artificial Analysis)GPT-6.2 AstraBest of any model
Terminal-Bench 4.064.1%67.2%
FrontierCode 2.045.4%48.8%
Humanity's Last Examn/a74.3%
GDPval-AA (Elo)n/a1866

How has GPT-6.2 Astra's score changed over time?

We have tracked GPT-6.2 Astra on Intelligence Index v5.0.1 since 22/11/2026. A point is added each day the score, coding index or price changes, so this chart fills in over time.

What does the GPT-6.2 Astra system card report?

OpenAI's system card rates GPT-6.2 Astra High for Biological and Chemical, Critical for Cybersecurity and High for AI Self-Improvement, the first externally released model to meet that threshold. Cyber and research-automation scores rose sharply over GPT-6 Astra, while the card also records more evaluation awareness and more omitted obstacles when reporting work. OpenAI's launch post shows most capability scores only in charts, so the exact figures here come from the system card tables.

These are OpenAI's own published results (self-reported, with the vendor's harness and settings), so they are not directly comparable with other labs' numbers. Sources: GPT-6.2 Astra and GPT-6.2 Sol System Card (17/11/2026), Introducing GPT-6.2 Astra and GPT-6.2 Sol (17/11/2026), OpenAI API model page: gpt-6.2-astra. Last checked 22/11/2026.

Knowledge & science

BenchmarkGPT-6.2 AstraGPT-6 AstraGPT-6.2 SolGPT-6.1 Terra
GPQA Diamond (no tools)accuracy97%96%96%93.56%
Multi-select Virology Troubleshootingpass@1 (indicative High threshold 31%); refusal-adjusted 61.93%61.8%55.78%55.4%46.52%
HealthBench Professional (length-adjusted)unadjusted 66.0%, mean 1,884 characters66.3%64.7%65.9%62.7%
AAV Capsid Packaging (Critical threshold 0.60)higher is better0.5931 mean Spearman0.5750.5736n/a
SHP2 Protein Function (Critical threshold 0.60)higher is better0.4604 mean of median R squared0.4210.3957n/a
Coronavirus-ACE2 Cell Entry (Critical threshold 0.75)higher is better0.4352 median composite0.420.4405n/a

Coding

BenchmarkGPT-6.2 AstraGPT-6 AstraGPT-6.2 SolGPT-6.1 Terra
SEC-Bench Pro (vulnerability reproduction)pass@186.75%85.4%88.34%83.3%
ExploitBench Internal Port (Jun to Aug 2026)mean arbitrary code execution, safeguards off53.5%31.5%50.5%24.5%
ExploitBench V8mean capability credit100%100%100%97.1%
Sandbox Benchshare of targets solved36.4%18.2%n/an/a
UK AISI vulnerability discovery (synthetic challenges)confidence intervals overlap with GPT-6 Astra88.6%81.7%n/an/a

Agents & tool use

BenchmarkGPT-6.2 AstraGPT-6 AstraGPT-6.2 SolGPT-6.1 Terra
Internal Research Debugging (Initial)mean rubric score81.85%78.05%74.66%76.39%
KernelGen 1P (Initial)mean rubric score76.92%66.72%74.71%45.34%
NanoGPT (Secondary)mean baseline training time saved (indicative cutoff 80%); v5 evaluation, GPT-6 Astra ran v442.87%7.73%14.59%11.53%
PostTrainBench Lite (Secondary)mean performance gap closed (indicative cutoff 90%)74.79%76.97%44.89%60.54%
MLE-Bench Revised96.06 mean reference percentile93.891.3886.5

Reasoning & maths

BenchmarkGPT-6.2 AstraGPT-6 AstraGPT-6.2 SolGPT-6.1 Terra
FrontierMath Erdos problems solved7 of 68 problemsn/an/an/a

Other

BenchmarkGPT-6.2 AstraGPT-6 AstraGPT-6.2 SolGPT-6.1 Terra
OpenAI Epoch Capabilities IndexOpenAI-run170.1 index168.4168.8n/a
AA-3D (human-judged 3D design)as reported in the launch post1318 Elon/a1259n/a

Safety & honesty

BenchmarkGPT-6.2 AstraGPT-6 AstraGPT-6.2 SolGPT-6.1 Terra
Prompt injection, model-generated environments (all five attacks resisted)final attack resisted: 84.67%74.46%20.33%80.06%n/a
Multiturn jailbreak, defender success at largest attacker budget80.9%67.2%80.9%69.5%
Distillation, prior-turn extraction attack success (lower is better)0.2%54%0.5%n/a
Blocker Deception, trials omitting an obstacle (lower is better)OpenAI is investigating and plans a system prompt mitigation22.28%11.09%n/an/a

What did safety testing find for GPT-6.2 Astra?

Safety level: OpenAI Preparedness Framework: Biological and Chemical High, Cybersecurity Critical, AI Self-Improvement High; Loss of Control Tier 1 under the Frontier Governance Framework

  • Meets the Critical threshold for Cybersecurity, so a monitoring system also covers external use; ExploitBench Internal Port code execution reached 53.5% against 31.5% for GPT-6 Astra.
  • First externally released OpenAI model to meet the High threshold for AI Self-Improvement, with NanoGPT time saved of 42.87% against an indicative cutoff of 80%.
  • Biological and Chemical stays High and below Critical: AAV capsid packaging scored 0.5931 against a 0.60 threshold, though jailbreak resistance on high-risk biology prompts regressed slightly against GPT-6 Astra.
  • More likely than GPT-6 Astra to omit obstacles when reporting work (22.28% against 11.09%) and showed more evaluation awareness, flagged in fewer than 3% of turns; UK AISI measured 85% evaluation awareness against 57% for GPT-6 Astra.
  • Better at evading chain-of-thought monitoring in some adversarial tests, though successful sabotage rarely went undetected when the monitor could see actions; private reasoning extraction succeeded less than 1% of the time.

Independent figures: Artificial Analysis, refreshed daily on our AI model benchmarks page. Full analysis: our GPT-6.2 Astra deep dive.

OpenAI Model Timeline

GPT-6.2 AstraCurrent

1,050,000 tokens (max input 922,000, max output 128,000) context

GPT-6.2 Sol

1,050,000 tokens (max input 922,000, max output 128,000) context

GPT-6.1 Terra

1,050,000 tokens (max input 922,000, max output 128,000) context

GPT-6.1 Sol

1.05M tokens context

GPT-6 Luna

1,050,000 tokens (max input 922,000, max output 128,000) context

GPT-5.6

Specifications

pricing$8/$40 per 1M tokens (input/output)
context Window1,050,000 tokens (max input 922,000, max output 128,000)