OpenAINovember 17, 2026

GPT-6.2 Astra

OpenAI GPT-6.2 Astra

OpenAI released GPT-6.2 Astra on November 17, 2026 for complex professional work, scientific reasoning, and demanding software projects.

Text + Image inputText outputClosed / API only

At a glance

Context window
1.05M tokens
Max output
128K tokens
Text input / output · per 1M tokens
$8.00 / $40.00
Knowledge cutoff
2026-05-18

Benchmark snapshot

Best result in 6 of 10 categories

View benchmark details (34)

Benchmark details

34 results · Best published score per benchmark, grouped by category

Benchmark · settingScoreRank
Academic
FrontierMath Erdős

Max (With Tools) · Mathematics

Source: Epoch AI (epoch.ai)
10.31 / 14
FrontierMath Tier 4 v2

Max (With Tools) · Mathematics

Source: Epoch AI (epoch.ai)
100.01 / 73
FrontierMath v2

Max (With Tools) · Mathematics

Source: Epoch AI (epoch.ai)
92.64 / 85
GPQA Diamond

Thinking (No Tools) · Scientific Reasoning

97.01 / 200
HLE-Diamond

Max (No Tools) · Knowledge Exams

72.22 / 16
MysteryMechanism

Max (With Tools) · Scientific Reasoning

Source: Vals AI. © 2026 Vals AI. All rights reserved. No affiliation or endorsement.
53.21 / 32
Terminal-Bench-Science 0.1

Extra-High (With Tools) · Scientific Computing

Source: Artificial Analysis (artificialanalysis.ai)
78.61 / 32
Coding
FrontierCode 2.0

Extra-High (With Tools) · Repository Engineering

49.02 / 36
Terminal-Bench 4.0

Extra-High (With Tools) · Agentic Development

Source: Artificial Analysis (artificialanalysis.ai)
64.15 / 90
Vibe Code Bench v1.1

Max (With Tools) · Code Generation & Editing

Source: Vals AI — Vibe Code Bench v1.1. © 2026 Vals AI. All rights reserved. No affiliation or endorsement.
89.99 / 121
Computer Use
AutomationBench-AA

Max (With Tools) · limited comparability · Tool Orchestration

Source: Artificial Analysis (artificialanalysis.ai)
77.24 / 18
General Evaluation
AA Intelligence Index v5.0.1

Max (task-specific tools) · Capability Indices

62.12 / 62
Agent Arena Index

Max (With Tools + Internet) · Preference Arenas

Source: Arena Agent Arena Index
12916 / 36
ECI

Reported best (effort unspecified) · Capability Indices

Source: Epoch AI (epoch.ai)
1741 / 168
Vals Index v2.2

Max (With Tools) · Capability Indices

Source: Vals AI — Vals Index v2.2. © 2026 Vals AI. All rights reserved. No affiliation or endorsement.
67.77 / 36
Vals RSI Index

Max (task-specific tools) · Capability Indices

Source: Vals AI
293 / 3
Long Context
EBR-bench

Max (No Tools) · Memory & Persistence

Source: Epoch AI (epoch.ai)
92.41 / 30
Multimodal
GDP.pdf

Max (No Tools) · Documents & Charts

Source: Artificial Analysis (artificialanalysis.ai)
29.89 / 96
MMMU-Pro

Max (No Tools) · Visual Understanding

Source: Artificial Analysis (artificialanalysis.ai)
89.53 / 136
Professional
AA-AnalystAgent

Max (With Tools + Internet) · Data Analysis

Source: Artificial Analysis (artificialanalysis.ai)
62.51 / 39
BenchCAD 2.1 Core

Max (With Tools) · Design & Engineering

82.52 / 7
EMB (Excel Modeling)

Max (With Tools) · Finance

Source: Vals AI — EMB (Excel Modeling). © 2026 Vals AI. All rights reserved. No affiliation or endorsement.
76.03 / 78
Harvey LAB-AA v1.1 (All-pass)

Max (With Tools) · Legal

Source: Artificial Analysis (artificialanalysis.ai)
15.01 / 12
Harvey's Legal Agent Benchmark

Max (With Tools) · Legal

Source: Vals AI — Harvey's Legal Agent Benchmark. © 2026 Vals AI. All rights reserved. No affiliation or endorsement.
16.35 / 52
Legal Research Bench

Max (With Tools + Internet) · Legal

Source: Vals AI — Legal Research Bench. © 2026 Vals AI. All rights reserved. No affiliation or endorsement.
42.829 / 91
Tax Agent Bench

Max (With Tools + Internet) · Finance

21.852 / 74
Reasoning
ARC-AGI-1

Thinking Low (No Tools) · Abstract Generalization

98.51 / 87
ARC-AGI-2

Extra-High (No Tools) · Abstract Generalization

95.81 / 80
ARC-AGI-3

Extra-High (No Tools) · Provider Adapter · limited comparability · Abstract Generalization

100.01 / 15
ARC-AGI-3

Max (No Tools) · Standard · Abstract Generalization

70.32 / 26
SimpleBench

Reported best (effort unspecified) · Commonsense

Source: SimpleBench
77.316 / 106
Safety & Alignment
SimpleQA Verified

Max (No Tools) · Honesty & Factuality

Source: Epoch AI (epoch.ai)
78.52 / 5
Science & Health
BioMysteryBench

Max (With Tools) · Biology & Genomics

Source: Vals AI — BioMysteryBench. © 2026 Vals AI. All rights reserved. No affiliation or endorsement.
80.75 / 28
HealthBench Professional

Max (No Tools) · length-adjusted · limited comparability · Clinical Workflows

66.33 / 19
24 more results in Computer Use, General Evaluation, Long Context and 5 more

Rank is this model's position among every model with a published result on that leaderboard; the bar shows how far up the field that is. Orange marks first place on leaderboards with at least 5 models. Unranked leaderboards publish a composite or direction-less score.

Back to benchmark snapshot ↑

API price vs benchmark score

Score (higher is better)This modelPareto frontier24 priced models
0$025.31$6.4850.62$12.9675.92$19.44Blended API price / 1M tokens (4:1 input/output, uncached)GPT-6.2 Astra
GPT-6.2 Astra$14.40 / 1M70.3Max (No Tools)Pareto frontier
Result source
Methodology & notes

Uses listed uncached text API rates at a 4:1 input/output mix against one published protocol and setting (arc3-semi-private-standard). API rates are separate from evaluation token costs and do not measure cost per solved task. Selected point basis: Standard pricing. Up to 272,000 input tokens Official OpenAI per-million-token pricing. Full request uses the applicable input-token band.

API pricing

Listed text rates, USD per million tokens · effective 2026-11-17

Input
$8.00
Output
$40.00
Cached input
$0.40

Blended price4:1 input:output · 90% of input tokens cached · same basis as the price ranking

$8.928/ 1M tokens

Estimate running cost for GPT-6.2 Astra

Specifications

Provider
OpenAI
Model type
Reasoning model
Released
November 17, 2026
Architecture
Undisclosed
Context window
1.05M tokens
Max output
128K tokens
Knowledge cutoff
2026-05-18
Input
Text, Image
Output
Text
Weights
Closed / API only
Commercial use
Proprietary

Capabilities

ReasoningCodingFunction callingTool useStructured outputComputer useWeb searchLong context

Model analysis

OpenAI released GPT-6.2 Astra on November 17, 2026 for complex professional work, scientific reasoning, and demanding software projects. OpenAI launch announcement

Task difficulty and cost shape model selection

Vals measured Astra at 68.44% on its Science Index, up from 65.09% for GPT-6 Astra, while average test cost fell from USD 8.03 to USD 4.76. Evaluation source

In the independent Artificial Analysis Intelligence Index v5.0.1, max effort scored about 62, at 10.7 minutes and USD 4.00 per task. For repeatable workloads, Sol offers lower rates. Astra is an option where better deliverables or fewer revisions justify higher cost. Independent model results

Coding and engineering benchmarks measure different outcomes

On Cognition’s FrontierCode 2.0, both models ran at max effort in Codex. Astra scored about 44.2% and Sol about 43.8%. On BenchCAD 2.1 Core with a customized Codex harness, Astra scored 82.5 at USD 5.43 per case and Sol scored 73.1 at USD 1.60 per case. FrontierCode · BenchCAD 2.1

In the independent Artificial Analysis Coding Agent Index with Codex at max effort, Astra is level with GPT-6 Astra and Sol trails GPT-6.1 Sol by three points, driven mainly by repository question answering. On the Vals Science Index, Astra scored 68.44% and Sol 57.76%, at USD 4.76 and USD 1.12 per test, respectively. Artificial Analysis release tests · Vals Science Index

The API supports a 1.05 million token context

gpt-6.2-astra accepts text and images and returns text. Maximum input and output are 922,000 and 128,000 tokens. The knowledge cutoff is 2026-05-18. Responses, Chat Completions, and Batch are supported, with function calling, structured outputs, file and web search, and computer use. The Responses API offers multi-agent and discounted background completion features in beta. OpenAI has not disclosed parameter counts or a language inventory. Official model documentation

Long requests and faster tiers change the bill

Standard short-context rates per million tokens are USD 8 input, 0.4 cached input, and 40 output. Above 272,000 input tokens, input and cache rates double and output costs 1.5 times the short-context rate for the full request. Batch is half the Standard price and Fast is twice the Standard price. Ultrafast costs three times Standard through February 28, 2027 and six times Standard from March 1, Pacific time. ChatGPT Work and Codex serve Plus, Pro, Enterprise, and Edu users, with Ultrafast access depending on plan and workspace settings. Official API pricing

Pro 500 supports Ultrafast on both models. Pro 200 supports it on Sol at launch. Enterprise and Edu access depends on workspace settings. ChatGPT availability details

Tool calling uses the Responses API. Eligible background requests can choose a two-hour completion window at 30% below Standard rates or an eight-hour window at 40% below Standard. OpenAI API changelog

Amazon Bedrock and Microsoft Foundry also announced general availability for both base models on launch day. Region and deployment options vary by platform. AWS announcement · Microsoft Foundry model documentation

OpenAI tightened safeguards for higher-risk requests

The system card describes deployment safeguards and remaining limitations in how the models report blockers. GPT-6.2 system card

Last reviewed 2026-11-18

GPT-6.2 Astra vs competitors

Comparable results only · record is GPT-6.2 Astra's wins–losses

GPT-6.2 Astra benchmark scores against competitors
BenchmarkGPT-6.2 AstraThis modelvs Claude Fable 5.2Record 9–17–2
GPQA Diamond97.093.9
ECI174174
Vibe Code Bench v1.189.993.8
SimpleBench77.394.9
GDP.pdf29.826.8
Legal Research Bench42.846.2
Terminal-Bench 4.064.167.6
ARC-AGI-198.598.5
FrontierMath v292.695.1
EMB (Excel Modeling)76.077.4

Lineage

Predecessors and successors · oldest to newest

  1. GPT-6 AstraSep 3, 2026
  2. GPT-6.2 AstraThis model · Nov 17, 2026vs GPT-6 Astra

Generational jump vs GPT-6 Astra

Showing the 2 largest gains and 2 smallest gains or drops out of 16 like-for-like benchmarks.

Full head-to-head
GPT-6.2 AstraGPT-6 AstraOther ranked models

Max (With Tools) · 14 ranked

2.9%→10.3%
07.51510.3GPT-6.2 AstraGPT-6.1 Sol2.9GPT-6 AstraClaude Opus 5.5Claude Sonnet…GPT-6 SolClaude Fable 5Claude Fable 5…Claude Opus 5Gemini 3.8 Fla…GPT-5.5GPT-5.6 Sol+7.4% · #3→#1
Hover or focus any bar to inspect rank & scoreRank #3 → #1

Max (With Tools) · 49 ranked

5.4%→16.3%
0153025.4Muse Spark 1.2Muse Spark 1.3Muse Spark 1.1Gemini 4 Argon16.3GPT-6.2 AstraGrok 4.6Mistral Large 4Grok 4.5Kimi K3GLM-5.3-Flash5.4GPT-6 AstraGPT-6.1 Sol+10.8% · #24→#5
Hover or focus any bar to inspect rank & scoreRank #24 → #5
MysteryMechanismSmallest gain

Max (With Tools) · 31 ranked

53.1%→53.2%
0306053.2GPT-6.2 Astra53.1GPT-6 AstraClaude Fable 5…Claude Opus 5.5Claude Sonnet…Claude Fable 5…GPT-6.1 SolGemini 4 ArgonGemini 4 NeonClaude Opus 5Gemini 3.8 Fla…Muse Spark 1.3+0.003% · #2→#1
Hover or focus any bar to inspect rank & scoreRank #2 → #1

Max (With Tools) · 82 ranked

93.7%→92.6%
05010095.1Claude Fable 5…93.7GPT-6 AstraGPT-6.1 Sol92.6GPT-6.2 AstraClaude Opus 5.5GPT-6.1 TerraClaude Fable 5…GPT-6 SolGPT-5.6 SolClaude Sonnet…GPT-5.5 ProClaude Fable 5−1.1% · #2→#4
Hover or focus any bar to inspect rank & scoreRank #2 → #4
4 of 16 shared benchmarks shown

Price & benchmark trends

Across curated predecessors and successors, ordered by release date. Points use listed rates and published results, not a history of price changes within one model. Related branches may appear; adjacent points do not imply direct succession. Undated models appear last.

API price across generations

Text inputText outputUSD / 1M tokens
$0$27$54GPT-6 AstraGPT-6.2 Astra

Input and output share one linear USD axis · uncached text rates · lower is cheaper. Retired models may retain their last recorded price. Rate tiers and context limits can differ; inspect each model's pricing conditions.

Benchmark performance across generations

094.05188.1GPT-6 AstraGPT-6.2 Astra

ECI score (capability index, higher is better) · Higher is better. Same recorded metric, protocol and setting; review exclusions are respected. Score gaps do not establish statistical significance.

Inspect ECI →

Orange marks this model. Hover, tap or focus the chart to see exact values. Missing values leave gaps. Horizontal spacing shows release order, not elapsed time.

Listed prices and selected benchmark scores across model generations
Model · releasedInput / 1MOutput / 1MPrice effectiveECI
1GPT-6 AstraSep 3, 2026$10.00$50.002026-09-03167 ↗
2GPT-6.2 AstraNov 17, 2026 · This model$8.00$40.002026-11-17174 ↗

Community discussion

Share the API, setup, and tradeoffs you actually tested. Rate the model once; comment as often as you like.

Used this model? Sign in with Google to rate it and share what worked, what did not, and which API or setup you tested.

No community comments yet.