Enter opens the highlighted result. Esc closes.

Claude Sonnet 5 vs GPT-6.2 Astra

GPT-6.2 Astra leads Claude Sonnet 5 on coding, 87.0 to 54.7 on the Vibe Coding Index, and Claude Sonnet 5 costs 4.0x less per output token ($10.00 vs $40.00 per million). Updated November 22, 2026; 50 benchmarks have a result for both.

Claude Sonnet 5Anthropic
Coding
54.7
Overall
66.3
Output $/M
$10.00
15
GPT-6.2 AstraOpenAI
Coding
87.0
Overall
86.4
Output $/M
$40.00
35
vs boards won of 50 shared

Claude Sonnet 5 or GPT-6.2 Astra: which to pick

Pick GPT-6.2 Astra for coding: it scores 87.0 on the Vibe Coding Index against 54.7 for Claude Sonnet 5, though on 4 benchmarks against 5.

Pick Claude Sonnet 5 for output tokens 4.0x cheaper ($10.00 vs $40.00 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Shared results
50
Claude Sonnet 5 only
73
GPT-6.2 Astra only
26
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Claude Sonnet 5 54.7 from 5 benchmarks, GPT-6.2 Astra 87.0 from 4 benchmarks.
Widest category
Math, 34.3 points apart on average over 3 shared benchmarks.
Widest single gap
FrontierMath, tier 4: Claude Sonnet 5 29.3% against GPT-6.2 Astra 100.0%, 70.7 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 5 $10.00 against GPT-6.2 Astra $40.00 per million output tokens, 4.0x apart.
Context window
Claude Sonnet 5 takes 1M tokens, GPT-6.2 Astra 1.05M.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryClaude Sonnet 5BarsGPT-6.2 AstraTies
Coding29
Intelligence01
Agentic work19
Reasoning24
Math03
Knowledge31
Web design05
General73
All shared boards1535
CodingLike-for-likeSix of these boards feed the Vibe Coding Index29
Coding benchmarks for Claude Sonnet 5 and GPT-6.2 Astra
BenchmarkClaude Sonnet 5GPT-6.2 AstraLeader
LiveBench codingNot measured91.9%Only GPT-6.2 Astra measured
LMArena WebDev15391766GPT-6.2 Astra
LiveCodeBench (Vals AI)82.4%Not measuredOnly Claude Sonnet 5 measured
SWE-bench Verified (Vals AI)79.6%Not measuredOnly Claude Sonnet 5 measured
Terminal-Bench 4 (Vals AI)10.6%63.1%GPT-6.2 Astra
Vibe Code Bench (Vals AI)81.3%89.9%GPT-6.2 Astra
Code migration (Vals AI)44.4%Not measuredOnly Claude Sonnet 5 measured
ProgramBench (Vals AI)0.0%Not measuredOnly Claude Sonnet 5 measured
IOI (Vals AI)45.0%Not measuredOnly Claude Sonnet 5 measured
Terminal-Bench 2.1 (Vals AI)74.5%Not measuredOnly Claude Sonnet 5 measured
Vibe Code Bench 1-100 (Vals AI)13.8%Not measuredOnly Claude Sonnet 5 measured
SkillsBench (Vals AI)46.5%Not measuredOnly Claude Sonnet 5 measured
CyberBench (Vals AI)70.3%Not measuredOnly Claude Sonnet 5 measured
SciCode54.3%Not measuredOnly Claude Sonnet 5 measured
Terminal-Bench 4.0 (Artificial Analysis run)14.1%64.1%GPT-6.2 Astra
FrontierCode 2.017.8%49.0%GPT-6.2 Astra
FrontierCode42.7%Not measuredOnly Claude Sonnet 5 measured
GSO-Bench37.3%Not measuredOnly Claude Sonnet 5 measured
WeirdML69.0%Not measuredOnly Claude Sonnet 5 measured
MirrorCode63.3%67.8%GPT-6.2 Astra
ALE-Bench1463.1Not measuredOnly Claude Sonnet 5 measured
LMArena Text: coding14831450Claude Sonnet 5
LMArena Text: software and IT14741443Claude Sonnet 5
LMArena WebDev: React15391770GPT-6.2 Astra
LMArena WebDev: HTML15261854GPT-6.2 Astra
LMArena WebDev: from an image1539Not measuredOnly Claude Sonnet 5 measured
SciCode10.7%Not measuredOnly Claude Sonnet 5 measured
SWE-Bench Pro V293.2%Not measuredOnly Claude Sonnet 5 measured
GameBench 254.097.2GPT-6.2 Astra
Terminal-Bench 2.174.6%Not measuredOnly Claude Sonnet 5 measured
Terminal-Bench 3.014.6%Not measuredOnly Claude Sonnet 5 measured
Terminal-Bench 4.012.4%Not measuredOnly Claude Sonnet 5 measured
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Claude Sonnet 5 and GPT-6.2 Astra
BenchmarkClaude Sonnet 5GPT-6.2 AstraLeader
AA Intelligence IndexNot measured62.1Only GPT-6.2 Astra measured
Epoch Capabilities Index156.9172.8GPT-6.2 Astra
Agentic workLike-for-likePublic boards, shown as published, kept out of the index19
Agentic work benchmarks for Claude Sonnet 5 and GPT-6.2 Astra
BenchmarkClaude Sonnet 5GPT-6.2 AstraLeader
Design Arena: agents building web apps12101334GPT-6.2 Astra
Design Arena: agents building full-stack apps12261351GPT-6.2 Astra
Design Arena: agents building mobile apps12021305GPT-6.2 Astra
Design Arena: agents building Android apps12081257GPT-6.2 Astra
Design Arena: agents building Godot games1191Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building games1170Not measuredOnly Claude Sonnet 5 measured
Design Arena: HTML slides1118Not measuredOnly Claude Sonnet 5 measured
Design Arena: PowerPoint slides1179Not measuredOnly Claude Sonnet 5 measured
Design Arena: spreadsheets10321278GPT-6.2 Astra
LiveBench researchNot measured91.5%Only GPT-6.2 Astra measured
LiveBench browserNot measured93.0%Only GPT-6.2 Astra measured
LiveBench long agenticNot measured70.8%Only GPT-6.2 Astra measured
SREBench (Vals AI)0.4%Not measuredOnly Claude Sonnet 5 measured
Finance Agent (Vals AI)53.9%Not measuredOnly Claude Sonnet 5 measured
Tax Agent Bench (Vals AI)29.4%21.8%Claude Sonnet 5
Legal Research Bench (Vals AI)41.8%42.8%GPT-6.2 Astra
Harvey's Legal Agent Benchmark (Vals AI)Not measured16.3%Only GPT-6.2 Astra measured
Excel Modeling Benchmark (Vals AI)66.3%Not measuredOnly Claude Sonnet 5 measured
BioMysteryBench (Vals AI)Not measured80.7%Only GPT-6.2 Astra measured
Terminal-Bench-Science (Vals AI)5.7%71.4%GPT-6.2 Astra
Vals Science IndexNot measured68.4%Only GPT-6.2 Astra measured
Robo-bench (Vals AI)Not measured32.7%Only GPT-6.2 Astra measured
APEX-Agents54.5%72.2%GPT-6.2 Astra
SpireClimbNot measured41.3%Only GPT-6.2 Astra measured
Vending-Bench 2$6,378Not measuredOnly Claude Sonnet 5 measured
LMArena Search11871191GPT-6.2 Astra
Toolathlon-Verified71.6%Not measuredOnly Claude Sonnet 5 measured
Neither model has a result on the other 17 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index24
Reasoning benchmarks for Claude Sonnet 5 and GPT-6.2 Astra
BenchmarkClaude Sonnet 5GPT-6.2 AstraLeader
GPQA Diamond88.9%Not measuredOnly Claude Sonnet 5 measured
LiveBench reasoningNot measured91.6%Only GPT-6.2 Astra measured
MysteryMechanism (Vals AI)Not measured53.1%Only GPT-6.2 Astra measured
MMMU Pro (Vals AI)83.0%Not measuredOnly Claude Sonnet 5 measured
GPQA Diamond (Artificial Analysis run)91.1%Not measuredOnly Claude Sonnet 5 measured
Humanity's Last Exam (Artificial Analysis run)41.3%Not measuredOnly Claude Sonnet 5 measured
HLE-Diamond (Artificial Analysis run)Not measured72.2%Only GPT-6.2 Astra measured
CritPt v2, hard subset (Artificial Analysis run)Not measured71.5%Only GPT-6.2 Astra measured
GPQA Diamond (Epoch AI run)90.5%96.8%GPT-6.2 Astra
ARC-AGINot measured98.5%Only GPT-6.2 Astra measured
ARC-AGI-2Not measured95.8%Only GPT-6.2 Astra measured
SimpleBench60.6%77.3%GPT-6.2 Astra
Chess puzzles45.0%78.0%GPT-6.2 Astra
Mystery game puzzles35.0%95.0%GPT-6.2 Astra
EBR-benchNot measured92.4%Only GPT-6.2 Astra measured
LMArena Text: hard prompts14611425Claude Sonnet 5
LMArena Text: expert1488Not measuredOnly Claude Sonnet 5 measured
LMArena Text: hard prompts in English14651426Claude Sonnet 5
LMArena Vision: diagrams1293Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: homework1310Not measuredOnly Claude Sonnet 5 measured
Humanity's Last Exam (Scale run)Not measured66.9%Only GPT-6.2 Astra measured
GoBenchNot measured2493Only GPT-6.2 Astra measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Claude Sonnet 5 and GPT-6.2 Astra
BenchmarkClaude Sonnet 5GPT-6.2 AstraLeader
OTIS Mock AIME94.7%100.0%GPT-6.2 Astra
FrontierMath, tiers 1 to 365.6%92.6%GPT-6.2 Astra
FrontierMath, tier 429.3%100.0%GPT-6.2 Astra
ProofBench77.0%Not measuredOnly Claude Sonnet 5 measured
LMArena Text: math1466Not measuredOnly Claude Sonnet 5 measured
LMArena Text: mathematical work1479Not measuredOnly Claude Sonnet 5 measured
MathArenaNot measured92.9%Only GPT-6.2 Astra measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index31
Knowledge benchmarks for Claude Sonnet 5 and GPT-6.2 Astra
BenchmarkClaude Sonnet 5GPT-6.2 AstraLeader
MMLU Pro87.5%Not measuredOnly Claude Sonnet 5 measured
LegalBench (Vals AI)83.9%Not measuredOnly Claude Sonnet 5 measured
CorpFin (Vals AI)67.0%Not measuredOnly Claude Sonnet 5 measured
TaxEval (Vals AI)75.6%Not measuredOnly Claude Sonnet 5 measured
MortgageTax (Vals AI)70.0%Not measuredOnly Claude Sonnet 5 measured
MedCode (Vals AI)47.5%Not measuredOnly Claude Sonnet 5 measured
AA-OmniscienceNot measured50.0Only GPT-6.2 Astra measured
SimpleQA Verified33.7%78.5%GPT-6.2 Astra
GeoBench74.0%Not measuredOnly Claude Sonnet 5 measured
LMArena Text: science14601415Claude Sonnet 5
LMArena Text: medicine and healthcare1442Not measuredOnly Claude Sonnet 5 measured
LMArena Text: legal and government14511415Claude Sonnet 5
LMArena Text: business and finance14371413Claude Sonnet 5
Neither model has a result on the other 8 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index05
Web design benchmarks for Claude Sonnet 5 and GPT-6.2 Astra
BenchmarkClaude Sonnet 5GPT-6.2 AstraLeader
Design Arena: websites12641333GPT-6.2 Astra
Design Arena: UI components12601341GPT-6.2 Astra
Design Arena: game dev12561501GPT-6.2 Astra
Design Arena: data viz1246Not measuredOnly Claude Sonnet 5 measured
Design Arena: 3D12241430GPT-6.2 Astra
Design Arena: all code categories12601389GPT-6.2 Astra
Design Arena: SVG1178Not measuredOnly Claude Sonnet 5 measured
Design Arena: ASCII art1190Not measuredOnly Claude Sonnet 5 measured
LiveBench designNot measured82.8%Only GPT-6.2 Astra measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index73
General benchmarks for Claude Sonnet 5 and GPT-6.2 Astra
BenchmarkClaude Sonnet 5GPT-6.2 AstraLeader
Vals IndexNot measured67.7%Only GPT-6.2 Astra measured
LiveBench data analysisNot measured84.1%Only GPT-6.2 Astra measured
Public Benefits Bench (Vals AI)66.0%Not measuredOnly Claude Sonnet 5 measured
MedScribe (Vals AI)76.0%Not measuredOnly Claude Sonnet 5 measured
Vals Multimodal Index68.8%Not measuredOnly Claude Sonnet 5 measured
Long context reasoning (AA-LCR)82.0%Not measuredOnly Claude Sonnet 5 measured
GDPval-AA1470Not measuredOnly Claude Sonnet 5 measured
DTBench92.5%Not measuredOnly Claude Sonnet 5 measured
LMCA50.0%Not measuredOnly Claude Sonnet 5 measured
Surface Evolver Bench60.0%Not measuredOnly Claude Sonnet 5 measured
Furniture assemblyNot measured89.2%Only GPT-6.2 Astra measured
LMArena Text14421414Claude Sonnet 5
LMArena Text: instruction following14531423Claude Sonnet 5
LMArena Text: creative writing14141417GPT-6.2 Astra
LMArena Vision1272Not measuredOnly Claude Sonnet 5 measured
LMArena Text: English14501417Claude Sonnet 5
LMArena Text: non-English14301404Claude Sonnet 5
LMArena Text: Chinese1476Not measuredOnly Claude Sonnet 5 measured
LMArena Text: German1441Not measuredOnly Claude Sonnet 5 measured
LMArena Text: Japanese1422Not measuredOnly Claude Sonnet 5 measured
LMArena Text: Korean1400Not measuredOnly Claude Sonnet 5 measured
LMArena Text: French1463Not measuredOnly Claude Sonnet 5 measured
LMArena Text: Spanish1442Not measuredOnly Claude Sonnet 5 measured
LMArena Text: Russian14471437Claude Sonnet 5
LMArena Text: Polish1428Not measuredOnly Claude Sonnet 5 measured
LMArena Text: multi-turn14541425Claude Sonnet 5
LMArena Text: longer queries14621431Claude Sonnet 5
LMArena Text: writing and language14351440GPT-6.2 Astra
LMArena Text: entertainment and media14101413GPT-6.2 Astra
LMArena Vision: English1273Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: Chinese1334Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: reading text1285Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: humor1255Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: creative writing1246Not measuredOnly Claude Sonnet 5 measured
LMArena Document1460Not measuredOnly Claude Sonnet 5 measured
MultiChallengeNot measured73.2%Only GPT-6.2 Astra measured
EQ-Bench 41221Not measuredOnly Claude Sonnet 5 measured
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 5 and GPT-6.2 Astra
BenchmarkClaude Sonnet 5GPT-6.2 AstraLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Claude Sonnet 5$0.0070Fits in one request
GPT-6.2 Astra$0.028Fits in one request

Claude Sonnet 5 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 5$0.130Fits in one request
GPT-6.2 Astra$0.520Fits in one request

Claude Sonnet 5 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 5$0.500Fits in one request
GPT-6.2 Astra$2.00Fits in one request

Claude Sonnet 5 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Claude Sonnet 5 and GPT-6.2 Astra
SpecificationAnthropic Claude Sonnet 5OpenAI GPT-6.2 Astra
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedJune 30, 2026November 17, 2026
Context window1M1.05M
Input $/Mtok$2.00$8.00
Output $/Mtok$10.00$40.00
Coding index54.787.0
Independent measurements behind it54
Cost per solved task$1.87Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 5 better than GPT-6.2 Astra for coding?

Pick GPT-6.2 Astra for coding: it scores 87.0 on the Vibe Coding Index against 54.7 for Claude Sonnet 5, though on 4 benchmarks against 5. Pick Claude Sonnet 5 for output tokens 4.0x cheaper ($10.00 vs $40.00 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, Claude Sonnet 5 or GPT-6.2 Astra?

Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; GPT-6.2 Astra costs $8.00 and $40.00. Cost per solved task is known for Claude Sonnet 5 only.

Which has the bigger context window, Claude Sonnet 5 or GPT-6.2 Astra?

GPT-6.2 Astra, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 5 vs GPT-6.2 Astra comparison based on?

50 benchmarks have a result for both models as of November 22, 2026. Claude Sonnet 5's coding index rests on 5 independent benchmarks and GPT-6.2 Astra's on 4. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/claude-sonnet-5-vs-gpt-6-2-astra" title="Claude Sonnet 5 vs GPT-6.2 Astra, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/claude-sonnet-5-vs-gpt-6-2-astra">LLMBenchmark.ai, Claude Sonnet 5 vs GPT-6.2 Astra</a></p>