BenchLeader

GPT-6.1 Terra vs GPT-6.2 Astra Pro

Full profiles: GPT-6.1 Terra (OpenAI) and GPT-6.2 Astra Pro (OpenAI): every benchmark, price and rank.

Updated · Data from 11 sources

As of 21 Nov 2026, there are not enough shared benchmarks for a verdict, and GPT-6.1 Terra is 8.0× cheaper at $2.00 vs $16.00 per 1M tokens blended. GPT-6.2 Astra Pro leads in every category we measure both in.

GPT-6.2 Astra Pro was released on 17 Nov 2026 and has no BenchLeader Index yet (it needs five independent results across two categories). So this page gives no quality verdict: it compares what is published so far for both, price, context window, speed and the benchmarks both have results on. First results are tracked on GPT-6.2 Astra Pro's page.

Key facts (as of 21 Nov 2026)

  • GPT-6.1 Terra costs $2.00 per 1M tokens blended (list price, 21 Nov 2026).
  • GPT-6.2 Astra Pro costs $16.00 per 1M tokens blended (list price, 21 Nov 2026).

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
ReasoningGPT-6.2 Astra Pro68 vs 67 category scoreMedium
Chat quality (human preference)–Only GPT-6.1 Terra has an Arena rating (66 category score)Not comparable
Lowest costGPT-6.1 Terra$2.00 vs $16.00 per 1M blended; agentic coding session $0.080 vs $0.640–
Fastest first answerGPT-6.2 Astra Pro8.3 s (GPT-6.2 Astra Pro (max)) vs 167.7 s (GPT-6.1 Terra (max)) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Not enough shared benchmarks for a verdict.
  • GPT-6.2 Astra Pro (max) is stronger in reasoning.
  • GPT-6.1 Terra (max) is 8.0× cheaper ($2.00 vs $16.00 per 1M blended).

At a glance

SpecGPT-6.1 TerraGPT-6.2 Astra Pro
DeveloperOpenAIOpenAI
Released26 Oct 202617 Nov 2026
Context window (tokens)1,050,0001,050,000
Compared atGPT-6.1 Terra (max)GPT-6.2 Astra Pro (max)
Open weightsNoNo
Price in / out / cached input per 1M$1.00 / $5.00 / $0.050$8.00 / $40.00 / $0.400

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryGPT-6.1 Terra (max)GPT-6.2 Astra Pro (max)Leader
Reasoning67.168.1GPT-6.2 Astra Pro
Coding68.2–not comparable
Agents & tools61.6–not comparable
Maths69.3–not comparable
Knowledge60.6–not comparable
Human preference66.2–not comparable
Multimodal62.4–not comparable
Long context66.1–not comparable
Composite62.6–not comparable

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsMathsKnowledgeLong contextMultimodalHumanpreferenceGPT-6.1 Terra, Reasoning: 67.1GPT-6.1 Terra, Coding: 68.2GPT-6.1 Terra, Agents & tools: 61.6GPT-6.1 Terra, Maths: 69.3GPT-6.1 Terra, Knowledge: 60.6GPT-6.1 Terra, Long context: 66.1GPT-6.1 Terra, Multimodal: 62.4GPT-6.1 Terra, Human preference: 66.2GPT-6.2 Astra Pro, Reasoning: 68.1

Dashed: that model has no result on the axis it crosses; the line only joins its neighbours.

Not drawn, no result for these models: Instruction following.

Model, click to add or removeIndex

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureGPT-6.1 Terra (max)GPT-6.2 Astra Pro (max)
Blended price per 1M tokens$2.00$16.00
Input / output per 1M$1.00 / $5.00$8.00 / $40.00
Cached input per 1M$0.050$0.400
Price per task: chat reply$0.0019$0.015
Price per task: summarize a 30-page report$0.015$0.120
Price per task: code edit$0.013$0.108
Price per task: agentic coding session$0.080$0.640
Price per task: structured extraction$0.0030$0.024
Agentic coding session, input mostly cached$0.037$0.298
Cost per benchmark task (AA Index)$0.961–
Output tokens per task (AA Index)60k–
Of which reasoning39k–
Time per task (AA Index)16 min–
Output speed63 tok/s56 tok/s
Time to first answer167.7 s8.3 s
Time to a complete answer, last measured 13 Nov 2026375.7 s–

Each model is compared at its best-ranked reasoning-effort setting. GPT-6.1 Terra (max) scores 63.1 and takes 168 s to its first answer token; GPT-6.1 Terra (high) scores 59.8 in 12 s, GPT-6.1 Terra (xhigh) scores 59.5 in 34 s. GPT-6.2 Astra Pro (max) and takes 8 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

94 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherGPT-6.1 Terra (max)GPT-6.2 Astra Pro (max)
BenchLeader IndexBenchLeader63.1–
Agents & tools scoreBenchLeader61.6–
Coding scoreBenchLeader68.2–
Composite scoreBenchLeader62.6–
Human preference scoreBenchLeader66.2–
Knowledge scoreBenchLeader60.6–
Long context scoreBenchLeader66.1–
Maths scoreBenchLeader69.3–
Multimodal scoreBenchLeader62.4–
Reasoning scoreBenchLeader67.168.1
Blended price $/MBenchLeader$2.00$16.00
Output speedBenchLeader63 tok/s56 tok/s
Time to first answerBenchLeader167.7 s8.3 s
Context windowBenchLeader1,050,000 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub94.3%–
SimpleBenchSimpleBench72.2%†79.2%
Arena Hard PromptsArena (LMArena)1500–
LiveBench 2.0 ReasoningLiveBench88.7%–
Humanity's Last Exam (AA)Artificial Analysis46.3%–
HLE-Diamond (AA)Artificial Analysis47.3%–
CritPtArtificial Analysis28.0%–
CritPt v2 hard subset (AA)Artificial Analysis68.0%–
HLE-Diamond (Scale)Scale AI SEAL35.7%†–
Arena ExpertArena (LMArena)1516–
Mystery Game PuzzlesEpoch AI Benchmarking Hub74.0%–
Coding
SciCodeSciCode55.1%–
Arena CodingArena (LMArena)1541–
Arena WebDevArena (LMArena)1685–
LiveBench 2.0 CodingLiveBench89.2%–
Vibe Code Bench v1.1Vals AI84.0%–
SWE Atlas v1.1Scale AI SEAL57.7%–
SWE Atlas v1.1: Codebase QnAScale AI SEAL54.0%–
SWE Atlas v1.1: Test WritingScale AI SEAL63.3%–
SWE Atlas v1.1: RefactoringScale AI SEAL55.7%–
MirrorCodeEpoch AI Benchmarking Hub76.7%–
ALE-BenchEpoch AI Benchmarking Hub2608.8–
WeirdML v3WeirdML28.1%†–
Terminal-Bench 4.0 (AA)Artificial Analysis55.6%–
GameBench 2 OverallDuelLab GameBench 281.2†–
Show all 94 benchmarks
MetricPublisherGPT-6.1 Terra (max)GPT-6.2 Astra Pro (max)
Coding
GameBench 2 by reasoning settingDuelLab GameBench 285.8†–
Design Arena WebsiteDesign Arena1287†–
Design Arena CodeDesign Arena1293†–
FrontierCode 1.1 (AA)Artificial Analysis36.0%–
FrontierCode 2.0 (AA)Artificial Analysis42.3%–
Agents & tools
Terminal-BenchTerminal-Bench53.3%–
APEX-AgentsMercor68.3%–
Arena AgentArena (LMArena)10.5–
LiveBench Long AgenticLiveBench55.3%–
LiveBench BrowserLiveBench93.1%–
HiL-BenchScale AI SEAL68.0%†–
GDPval-AA v2.1Artificial Analysis1476–
Finance Agent v2.1Vals AI56.0%–
Harvey's Legal Agent Benchmark v1.1Vals AI1.7%–
Legal Research BenchVals AI26.0%–
Tax Agent BenchVals AI17.1%–
Terminal-Bench 4.0 (Vals)Vals AI49.5%–
Arena Agent Task CompletionArena (LMArena)8.5–
Vending-Bench 2Andon Labs9107.5†–
SpireClimbEpoch AI Benchmarking Hub22.3%–
AutomationBenchArtificial Analysis60.2%–
GDP.pdf (AA)Artificial Analysis28.6%–
AA-Briefcase v1.1Artificial Analysis1399–
GDPxGDPx by SemiAnalysis8.5%–
Design Arena AgenticDesign Arena1174†–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis57.6%–
MKA (AA)Artificial Analysis43.8%–
FACTS SearchGoogle92.7%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub90.9%–
FrontierMath Tier 4Epoch AI Benchmarking Hub92.7%–
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%–
Arena MathsArena (LMArena)1479–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub57.3%–
LiveBench 2.0 Data AnalysisLiveBench82.3%–
LiveBench ResearchLiveBench79.1%–
AA-Omniscience v1.1Artificial Analysis29.6–
Excel Modeling Benchmark v1.1Vals AI73.3%–
DrugDiscoveryBenchScale AI SEAL58.1%†–
Arena Text FactualityArena (LMArena)1455–
EBR-benchEpoch AI Benchmarking Hub78.1%–
AA-Omniscience v1.1: accuracyArtificial Analysis47.6%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis65.5%–
FACTS ParametricGoogle70.8%†–
Instruction following
MultiChallengeScale AI SEAL74.2%†–
Arena Instruction FollowingArena (LMArena)1468–
Human preference
Arena TextArena (LMArena)1474–
Arena Creative WritingArena (LMArena)1449–
Arena Multi-turnArena (LMArena)1477–
Arena Longer QueriesArena (LMArena)1485–
Multimodal
Arena VisionArena (LMArena)1247–
LiveBench DesignLiveBench79.7%–
MMMU-ProArtificial Analysis84.7%–
Blueprint-Bench 2Epoch AI Benchmarking Hub42.1%†–
Furniture AssemblyEpoch AI Benchmarking Hub79.2%–
VIALS-AAHandshake AI60.3%–
FACTS MultimodalGoogle48.8%†–
Long context
AA-LCR v1.1Artificial Analysis82.7%–
MLCRArtificial Analysis30.6%–
FACTS GroundingGoogle84.2%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub167.7†–
LiveBench 2.0LiveBench78.6%–
AA Intelligence Index v5.0.1Artificial Analysis51.3–
AA Intelligence Index v4.3.2Artificial Analysis48.1–
AA Progress Index v1Artificial Analysis345.2–
Vals IndexVals AI60.5–
Vals Finance IndexVals AI53.3%–
Vals Legal IndexVals AI58.8%–
Safety & honesty
FORTRESSScale AI SEAL18.2%†–
DistressBenchScale AI SEAL65.9%†–

Data as of 2026-11-21. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261119-1d7fd529faf6 (https://benchmarks.duellab.org/releases/gb2-20261119-1d7fd529faf6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • GPT-6.1 Terra (max): 4 new results (SWE Atlas v1.1, SWE Atlas v1.1: Codebase QnA, SWE Atlas v1.1: Test Writing…).
  • GPT-6.1 Terra (max): 11 new results (Arena Text, Arena Hard Prompts, Arena Coding…).
  • GPT-6.1 Terra (max): 3 score revisions.
  • GPT-6.1 Terra (max): BenchLeader Index 64.1 → 63.5.
  • GPT-6.1 Terra (max): 2 score revisions.
  • GPT-6.1 Terra (max): 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…).
  • GPT-6.1 Terra (max): BenchLeader Index 64.7 → 64.1.
  • GPT-6.1 Terra (max): 1 new result (Terminal-Bench).
  • GPT-6.1 Terra (max): BenchLeader Index 65.2 → 64.7.
  • GPT-6.1 Terra (max): 1 new result (MirrorCode).

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

GPT-6.1 Terra vs GPT-6.2 Astra Pro: questions

GPT-6.1 Terra vs GPT-6.2 Astra Pro: which is cheaper, and will that change?
GPT-6.1 Terra is cheaper today: $2.00 against $16.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Which is faster, GPT-6.1 Terra or GPT-6.2 Astra Pro?
GPT-6.1 Terra streams faster (63 vs 56 output tokens per second, Artificial Analysis 7-day median).
Which is better for long documents?
Both accept 1,050,000 tokens of context.
Which has lower latency?
GPT-6.2 Astra Pro answers first: 8.3 s against 167.7 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
When was GPT-6.2 Astra Pro released?
GPT-6.2 Astra Pro was released on 17 Nov 2026.