Enter opens the highlighted result. Esc closes.

GPT-6.1 Terra vs Qwen4 Max

GPT-6.1 Terra leads Qwen4 Max on coding, 76.6 to 74.0 on the Vibe Coding Index, at about the same output price ($5.00 vs $4.275 per million). Updated November 22, 2026; 26 benchmarks have a result for both.

GPT-6.1 TerraOpenAI
Coding
76.6
Overall
76.0
Output $/M
$5.00
13
Qwen4 MaxQwen
Coding
74.0
Overall
66.6
Output $/M
$4.275
13
vs boards won of 26 shared

GPT-6.1 Terra or Qwen4 Max: which to pick

Pick GPT-6.1 Terra for coding: it scores 76.6 on the Vibe Coding Index against 74.0 for Qwen4 Max.

Pick Qwen4 Max for output tokens 1.2x cheaper ($4.275 vs $5.00 per million) and work measured by LMArena WebDev or Vibe Code Bench (Vals AI), where it leads.

Shared results
26
GPT-6.1 Terra only
60
Qwen4 Max only
0
Like-for-like categories
7 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
GPT-6.1 Terra 76.6 from 4 benchmarks, Qwen4 Max 74.0 from 4 benchmarks.
Widest category
Agentic work, 14.2 points apart on average over 6 shared benchmarks.
Widest single gap
GDPval-AA: GPT-6.1 Terra 1476 against Qwen4 Max 1809, 27.7 points apart on a 0 to 100 scale.
Output price
GPT-6.1 Terra $5.00 against Qwen4 Max $4.275 per million output tokens, 1.2x apart.
Context window
GPT-6.1 Terra takes 1.05M tokens, Qwen4 Max 1M.

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
CategoryGPT-6.1 TerraBarsQwen4 MaxTies
Coding65
Intelligence10
Agentic work24
Reasoning21
Knowledge10
Web design10
General03
All shared boards1313
CodingLike-for-likeSix of these boards feed the Vibe Coding Index65
Coding benchmarks for GPT-6.1 Terra and Qwen4 Max
BenchmarkGPT-6.1 TerraQwen4 MaxLeader
LiveBench coding89.2%69.8%GPT-6.1 Terra
LMArena WebDev16851751Qwen4 Max
Terminal-Bench 4 (Vals AI)49.5%48.5%GPT-6.1 Terra
Vibe Code Bench (Vals AI)84.0%86.7%Qwen4 Max
SciCode55.1%Not measuredOnly GPT-6.1 Terra measured
Terminal-Bench 4.0 (Artificial Analysis run)55.6%48.5%GPT-6.1 Terra
FrontierCode 2.042.3%26.5%GPT-6.1 Terra
MirrorCode76.7%Not measuredOnly GPT-6.1 Terra measured
ALE-Bench2608.81831.0GPT-6.1 Terra
LMArena Text: coding1482Not measuredOnly GPT-6.1 Terra measured
LMArena Text: software and IT1462Not measuredOnly GPT-6.1 Terra measured
LMArena WebDev: React16761785Qwen4 Max
LMArena WebDev: HTML17341752Qwen4 Max
LMArena WebDev: from an image16741675Qwen4 Max
GameBench 285.882.4GPT-6.1 Terra
Terminal-Bench 4.051.8%Not measuredOnly GPT-6.1 Terra measured
Neither model has a result on the other 36 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GPT-6.1 Terra and Qwen4 Max
BenchmarkGPT-6.1 TerraQwen4 MaxLeader
AA Intelligence Index51.342.9GPT-6.1 Terra
Epoch Capabilities Index167.7Not measuredOnly GPT-6.1 Terra measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index24
Agentic work benchmarks for GPT-6.1 Terra and Qwen4 Max
BenchmarkGPT-6.1 TerraQwen4 MaxLeader
Design Arena: agents building mobile apps1166Not measuredOnly GPT-6.1 Terra measured
Design Arena: spreadsheets992Not measuredOnly GPT-6.1 Terra measured
LiveBench research79.1%84.7%Qwen4 Max
LiveBench browser93.1%80.7%GPT-6.1 Terra
LiveBench long agentic55.3%46.6%GPT-6.1 Terra
Tax Agent Bench (Vals AI)17.1%40.4%Qwen4 Max
Legal Research Bench (Vals AI)26.0%41.4%Qwen4 Max
Harvey's Legal Agent Benchmark (Vals AI)1.7%21.3%Qwen4 Max
APEX-Agents68.3%Not measuredOnly GPT-6.1 Terra measured
SpireClimb22.3%Not measuredOnly GPT-6.1 Terra measured
Vending-Bench 2$9,107Not measuredOnly GPT-6.1 Terra measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index21
Reasoning benchmarks for GPT-6.1 Terra and Qwen4 Max
BenchmarkGPT-6.1 TerraQwen4 MaxLeader
LiveBench reasoning88.7%92.2%Qwen4 Max
Humanity's Last Exam (Artificial Analysis run)46.2%Not measuredOnly GPT-6.1 Terra measured
HLE-Diamond (Artificial Analysis run)47.3%44.9%GPT-6.1 Terra
CritPt v2, hard subset (Artificial Analysis run)68.0%43.0%GPT-6.1 Terra
GPQA Diamond (Epoch AI run)94.3%Not measuredOnly GPT-6.1 Terra measured
SimpleBench72.2%Not measuredOnly GPT-6.1 Terra measured
Mystery game puzzles74.0%Not measuredOnly GPT-6.1 Terra measured
EBR-bench78.1%Not measuredOnly GPT-6.1 Terra measured
LMArena Text: hard prompts1451Not measuredOnly GPT-6.1 Terra measured
LMArena Text: expert1479Not measuredOnly GPT-6.1 Terra measured
LMArena Text: hard prompts in English1452Not measuredOnly GPT-6.1 Terra measured
LMArena Vision: diagrams1259Not measuredOnly GPT-6.1 Terra measured
LMArena Vision: homework1308Not measuredOnly GPT-6.1 Terra measured
Humanity's Last Exam (Scale run)35.7%Not measuredOnly GPT-6.1 Terra measured
Neither model has a result on the other 12 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Math benchmarks for GPT-6.1 Terra and Qwen4 Max
BenchmarkGPT-6.1 TerraQwen4 MaxLeader
OTIS Mock AIME100.0%Not measuredOnly GPT-6.1 Terra measured
FrontierMath, tiers 1 to 390.9%Not measuredOnly GPT-6.1 Terra measured
FrontierMath, tier 492.7%Not measuredOnly GPT-6.1 Terra measured
LMArena Text: math1450Not measuredOnly GPT-6.1 Terra measured
LMArena Text: mathematical work1477Not measuredOnly GPT-6.1 Terra measured
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
Knowledge benchmarks for GPT-6.1 Terra and Qwen4 Max
BenchmarkGPT-6.1 TerraQwen4 MaxLeader
AA-Omniscience29.627.7GPT-6.1 Terra
SimpleQA Verified57.3%Not measuredOnly GPT-6.1 Terra measured
LMArena Text: science1422Not measuredOnly GPT-6.1 Terra measured
LMArena Text: medicine and healthcare1397Not measuredOnly GPT-6.1 Terra measured
LMArena Text: legal and government1455Not measuredOnly GPT-6.1 Terra measured
LMArena Text: business and finance1412Not measuredOnly GPT-6.1 Terra measured
FACTS Benchmark Suite74.1%Not measuredOnly GPT-6.1 Terra measured
Neither model has a result on the other 14 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index10
Web design benchmarks for GPT-6.1 Terra and Qwen4 Max
BenchmarkGPT-6.1 TerraQwen4 MaxLeader
Design Arena: websites1283Not measuredOnly GPT-6.1 Terra measured
Design Arena: UI components1284Not measuredOnly GPT-6.1 Terra measured
Design Arena: game dev1316Not measuredOnly GPT-6.1 Terra measured
Design Arena: data viz1165Not measuredOnly GPT-6.1 Terra measured
Design Arena: 3D1285Not measuredOnly GPT-6.1 Terra measured
Design Arena: all code categories1293Not measuredOnly GPT-6.1 Terra measured
Design Arena: SVG1298Not measuredOnly GPT-6.1 Terra measured
LiveBench design79.7%79.1%GPT-6.1 Terra
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index03
General benchmarks for GPT-6.1 Terra and Qwen4 Max
BenchmarkGPT-6.1 TerraQwen4 MaxLeader
Vals Index60.5%63.2%Qwen4 Max
LiveBench data analysis82.3%83.4%Qwen4 Max
Long context reasoning (AA-LCR)82.7%Not measuredOnly GPT-6.1 Terra measured
GDPval-AA14761809Qwen4 Max
Furniture assembly79.2%Not measuredOnly GPT-6.1 Terra measured
LMArena Text1426Not measuredOnly GPT-6.1 Terra measured
LMArena Text: instruction following1442Not measuredOnly GPT-6.1 Terra measured
LMArena Text: creative writing1401Not measuredOnly GPT-6.1 Terra measured
LMArena Vision1247Not measuredOnly GPT-6.1 Terra measured
LMArena Text: English1431Not measuredOnly GPT-6.1 Terra measured
LMArena Text: non-English1416Not measuredOnly GPT-6.1 Terra measured
LMArena Text: Chinese1466Not measuredOnly GPT-6.1 Terra measured
LMArena Text: French1445Not measuredOnly GPT-6.1 Terra measured
LMArena Text: Spanish1418Not measuredOnly GPT-6.1 Terra measured
LMArena Text: Russian1419Not measuredOnly GPT-6.1 Terra measured
LMArena Text: multi-turn1432Not measuredOnly GPT-6.1 Terra measured
LMArena Text: longer queries1445Not measuredOnly GPT-6.1 Terra measured
LMArena Text: writing and language1416Not measuredOnly GPT-6.1 Terra measured
LMArena Text: entertainment and media1414Not measuredOnly GPT-6.1 Terra measured
LMArena Vision: English1255Not measuredOnly GPT-6.1 Terra measured
LMArena Vision: reading text1262Not measuredOnly GPT-6.1 Terra measured
LMArena Vision: creative writing1215Not measuredOnly GPT-6.1 Terra measured
MultiChallenge74.2%Not measuredOnly GPT-6.1 Terra measured
Neither model has a result on the other 26 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-6.1 Terra and Qwen4 Max
BenchmarkGPT-6.1 TerraQwen4 MaxLeader
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

GPT-6.1 Terra$0.0035Fits in one request
Qwen4 Max$0.0036Fits in one request

GPT-6.1 Terra costs less

Repository review

50K input + 3K output tokens

GPT-6.1 Terra$0.065Fits in one request
Qwen4 Max$0.084Fits in one request

GPT-6.1 Terra costs less

Agent loop

200K input + 10K output tokens

GPT-6.1 Terra$0.250Fits in one request
Qwen4 Max$0.328Fits in one request

GPT-6.1 Terra 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 GPT-6.1 Terra and Qwen4 Max
SpecificationOpenAI GPT-6.1 TerraQwen4 Max
MakerOpenAIQwen
WeightsNo public weights listedNo public weights listed
ReleasedOctober 26, 2026November 16, 2026
Context window1.05M1M
Input $/Mtok$1.00$1.425
Output $/Mtok$5.00$4.275
Coding index76.674.0
Independent measurements behind it44
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-6.1 Terra better than Qwen4 Max for coding?

Pick GPT-6.1 Terra for coding: it scores 76.6 on the Vibe Coding Index against 74.0 for Qwen4 Max. Pick Qwen4 Max for output tokens 1.2x cheaper ($4.275 vs $5.00 per million) and work measured by LMArena WebDev or Vibe Code Bench (Vals AI), where it leads.

Which is cheaper, GPT-6.1 Terra or Qwen4 Max?

GPT-6.1 Terra costs $1.00 per million input tokens and $5.00 per million output tokens; Qwen4 Max costs $1.425 and $4.275. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-6.1 Terra or Qwen4 Max?

GPT-6.1 Terra, with 1.05M tokens against 1M.

How many benchmarks is the GPT-6.1 Terra vs Qwen4 Max comparison based on?

26 benchmarks have a result for both models as of November 22, 2026. GPT-6.1 Terra's coding index rests on 4 independent benchmarks and Qwen4 Max'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/gpt-6-1-terra-vs-qwen4-max" title="GPT-6.1 Terra vs Qwen4 Max, 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/gpt-6-1-terra-vs-qwen4-max">LLMBenchmark.ai, GPT-6.1 Terra vs Qwen4 Max</a></p>