Enter opens the highlighted result. Esc closes.

GPT-6.1 Sol vs GPT-6 Sol

Updated October 21, 2026. 90 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-6.1 Sol Replace GPT-6 Sol
GPT-6.1 SolOpenAI
Coding
88.7
Overall
51.8
Output $/M
$10.00
82
GPT-6 SolOpenAI
Coding
82.8
Overall
47.6
Output $/M
$10.00
7
vs boards won of 90 shared, 1 tied

Decision reading

Pick GPT-6.1 Sol for coding: it scores 88.7 on the Vibe Coding Index against 82.8 for GPT-6 Sol.

Pick GPT-6 Sol when what matters is CyberBench (Vals AI) or SciCode, where it leads.

Model AGPT-6.1 SolOpenAI88.7/1002 independent benchmarksNo cost per solved taskModel BGPT-6 SolOpenAI82.8/1002 independent benchmarksNo cost per solved task
Shared results
90
GPT-6.1 Sol only
5
GPT-6 Sol only
10
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 Sol 88.7 from 2 benchmarks, GPT-6 Sol 82.8 from 2 benchmarks.
Widest category
Knowledge, 9.8 points apart on average over 6 shared benchmarks.
Widest single gap
CyberBench (Vals AI): GPT-6.1 Sol 39.3% against GPT-6 Sol 78.0%, 38.7 points apart on a 0 to 100 scale.
Output price
Both cost $10.00 per million output tokens.
Context window
Both take 1.05M tokens.

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 SolBarsGPT-6 SolTies
Coding142
Intelligence20
Agentic work113
Reasoning140
Math501 tie
Knowledge60
Web design61
General241
All shared boards8271 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index142
Coding benchmarks for GPT-6.1 Sol and GPT-6 Sol
BenchmarkGPT-6.1 SolGPT-6 SolLeader
LiveBench coding96.0%93.1%GPT-6.1 Sol
LMArena WebDev17531683GPT-6.1 Sol
Terminal-Bench 4 (Vals AI)55.0%44.4%GPT-6.1 Sol
Vibe Code Bench (Vals AI)88.9%87.8%GPT-6.1 Sol
Code migration (Vals AI)65.1%57.2%GPT-6.1 Sol
ProgramBench (Vals AI)3.0%2.0%GPT-6.1 Sol
IOI (Vals AI)96.9%82.6%GPT-6.1 Sol
Terminal-Bench 2.1 (Vals AI)Not measured83.2%Only GPT-6 Sol measured
SWE-bench Multimodal (Vals AI)43.5%Not measuredOnly GPT-6.1 Sol measured
CyberBench (Vals AI)39.3%78.0%GPT-6 Sol
SciCode55.8%57.6%GPT-6 Sol
FrontierCode50.2%49.3%GPT-6.1 Sol
ALE-Bench2743.82462.0GPT-6.1 Sol
LMArena Text: coding14781448GPT-6.1 Sol
LMArena Text: software and IT14761433GPT-6.1 Sol
LMArena WebDev: React17541685GPT-6.1 Sol
LMArena WebDev: HTML18001685GPT-6.1 Sol
LMArena WebDev: from an image17021660GPT-6.1 Sol
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-6.1 Sol and GPT-6 Sol
BenchmarkGPT-6.1 SolGPT-6 SolLeader
AA Intelligence Index51.847.6GPT-6.1 Sol
Epoch Capabilities Index168.4163.7GPT-6.1 Sol
Agentic workLike-for-likePublic boards, shown as published, kept out of the index113
Agentic work benchmarks for GPT-6.1 Sol and GPT-6 Sol
BenchmarkGPT-6.1 SolGPT-6 SolLeader
Design Arena: agents building web appsNot measured1232Only GPT-6 Sol measured
Design Arena: agents building full-stack appsNot measured1238Only GPT-6 Sol measured
Design Arena: agents building mobile apps11901216GPT-6 Sol
Design Arena: spreadsheets1250Not measuredOnly GPT-6.1 Sol measured
LiveBench research83.5%69.3%GPT-6.1 Sol
LiveBench browser88.0%92.0%GPT-6 Sol
LiveBench long agentic73.0%66.9%GPT-6.1 Sol
SREBench (Vals AI)50.8%30.5%GPT-6.1 Sol
Finance Agent (Vals AI)52.0%49.0%GPT-6.1 Sol
Tax Agent Bench (Vals AI)21.8%15.0%GPT-6.1 Sol
Legal Research Bench (Vals AI)38.5%28.9%GPT-6.1 Sol
Harvey's Legal Agent Benchmark (Vals AI)6.3%Not measuredOnly GPT-6.1 Sol measured
Excel Modeling Benchmark (Vals AI)70.8%71.5%GPT-6 Sol
BioMysteryBench (Vals AI)79.6%74.8%GPT-6.1 Sol
Terminal-Bench-Science (Vals AI)52.9%30.0%GPT-6.1 Sol
Vals Science Index59.6%45.0%GPT-6.1 Sol
Robo-bench (Vals AI)28.3%Not measuredOnly GPT-6.1 Sol measured
APEX-Agents60.0%54.3%GPT-6.1 Sol
SpireClimb24.7%7.5%GPT-6.1 Sol
Vending-Bench 2Not measured$14,428Only GPT-6 Sol measured
Neither model has a result on the other 19 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index140
Reasoning benchmarks for GPT-6.1 Sol and GPT-6 Sol
BenchmarkGPT-6.1 SolGPT-6 SolLeader
LiveBench reasoning92.6%88.7%GPT-6.1 Sol
MysteryMechanism (Vals AI)46.4%30.2%GPT-6.1 Sol
Humanity's Last Exam (Artificial Analysis run)52.9%47.9%GPT-6.1 Sol
GPQA Diamond (Epoch AI run)95.4%94.3%GPT-6.1 Sol
ARC-AGI98.5%95.5%GPT-6.1 Sol
ARC-AGI-294.2%89.6%GPT-6.1 Sol
Chess puzzles68.0%56.0%GPT-6.1 Sol
Mystery game puzzles80.0%56.0%GPT-6.1 Sol
EBR-bench54.3%53.3%GPT-6.1 Sol
LMArena Text: hard prompts14631422GPT-6.1 Sol
LMArena Text: expert14891437GPT-6.1 Sol
LMArena Text: hard prompts in English14651420GPT-6.1 Sol
LMArena Vision: diagrams13061270GPT-6.1 Sol
LMArena Vision: homework13561286GPT-6.1 Sol
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index50
Math benchmarks for GPT-6.1 Sol and GPT-6 Sol
BenchmarkGPT-6.1 SolGPT-6 SolLeader
OTIS Mock AIME100.0%100.0%Tie
FrontierMath, tiers 1 to 393.7%89.8%GPT-6.1 Sol
FrontierMath, tier 4100.0%90.0%GPT-6.1 Sol
ProofBench99.0%83.0%GPT-6.1 Sol
LMArena Text: math14891407GPT-6.1 Sol
LMArena Text: mathematical work15131424GPT-6.1 Sol
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
Knowledge benchmarks for GPT-6.1 Sol and GPT-6 Sol
BenchmarkGPT-6.1 SolGPT-6 SolLeader
MedCode (Vals AI)48.8%47.1%GPT-6.1 Sol
SimpleQA Verified73.9%60.7%GPT-6.1 Sol
LMArena Text: science14441389GPT-6.1 Sol
LMArena Text: medicine and healthcare14331366GPT-6.1 Sol
LMArena Text: legal and government14711396GPT-6.1 Sol
LMArena Text: business and finance14451380GPT-6.1 Sol
Neither model has a result on the other 11 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index61
Web design benchmarks for GPT-6.1 Sol and GPT-6 Sol
BenchmarkGPT-6.1 SolGPT-6 SolLeader
Design Arena: websites13211292GPT-6.1 Sol
Design Arena: UI components13211292GPT-6.1 Sol
Design Arena: game dev13891313GPT-6.1 Sol
Design Arena: data viz12781269GPT-6.1 Sol
Design Arena: 3D14611322GPT-6.1 Sol
Design Arena: all code categories13451301GPT-6.1 Sol
Design Arena: SVGNot measured1318Only GPT-6 Sol measured
Design Arena: ASCII artNot measured1226Only GPT-6 Sol measured
LiveBench design82.1%82.2%GPT-6 Sol
GeneralLike-for-likePublic boards, shown as published, kept out of the index241
General benchmarks for GPT-6.1 Sol and GPT-6 Sol
BenchmarkGPT-6.1 SolGPT-6 SolLeader
Vals Index63.9%Not measuredOnly GPT-6.1 Sol measured
LiveBench data analysis82.7%81.2%GPT-6.1 Sol
Public Benefits Bench (Vals AI)59.3%56.6%GPT-6.1 Sol
SAGE (Vals AI)46.5%44.8%GPT-6.1 Sol
MedScribe (Vals AI)86.5%82.0%GPT-6.1 Sol
Long context reasoning (AA-LCR)84.0%83.7%GPT-6.1 Sol
DTBench96.5%97.3%GPT-6 Sol
LMCA62.8%59.1%GPT-6.1 Sol
Furniture assembly80.0%58.3%GPT-6.1 Sol
LMArena Text14431398GPT-6.1 Sol
LMArena Text: instruction following14661413GPT-6.1 Sol
LMArena Text: creative writing14251378GPT-6.1 Sol
LMArena Vision12881240GPT-6.1 Sol
LMArena Text: English14501396GPT-6.1 Sol
LMArena Text: non-English14331388GPT-6.1 Sol
LMArena Text: Chinese14871412GPT-6.1 Sol
LMArena Text: GermanNot measured1379Only GPT-6 Sol measured
LMArena Text: JapaneseNot measured1377Only GPT-6 Sol measured
LMArena Text: KoreanNot measured1336Only GPT-6 Sol measured
LMArena Text: French14601399GPT-6.1 Sol
LMArena Text: Spanish14391387GPT-6.1 Sol
LMArena Text: Russian14571402GPT-6.1 Sol
LMArena Text: PolishNot measured1372Only GPT-6 Sol measured
LMArena Text: multi-turn14421414GPT-6.1 Sol
LMArena Text: longer queries14581416GPT-6.1 Sol
LMArena Text: writing and language14441389GPT-6.1 Sol
LMArena Text: entertainment and media14261373GPT-6.1 Sol
LMArena Vision: English12741229GPT-6.1 Sol
LMArena Vision: reading text12891258GPT-6.1 Sol
LMArena Vision: creative writing13011219GPT-6.1 Sol
Neither model has a result on the other 16 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-6.1 Sol and GPT-6 Sol
BenchmarkGPT-6.1 SolGPT-6 SolLeader
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 Sol$0.0070Fits in one request
GPT-6 Sol$0.0070Fits in one request

Same cost

Repository review

50K input + 3K output tokens

GPT-6.1 Sol$0.130Fits in one request
GPT-6 Sol$0.130Fits in one request

Same cost

Agent loop

200K input + 10K output tokens

GPT-6.1 Sol$0.500Fits in one request
GPT-6 Sol$0.500Fits in one request

Same cost

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 Sol and GPT-6 Sol
SpecificationOpenAI GPT-6.1 SolOpenAI GPT-6 Sol
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 29, 2026September 22, 2026
Context window1.05M1.05M
Input $/Mtok$2.00$2.00
Output $/Mtok$10.00$10.00
Coding index88.782.8
Independent measurements behind it22
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-6.1 Sol better than GPT-6 Sol for coding?

Pick GPT-6.1 Sol for coding: it scores 88.7 on the Vibe Coding Index against 82.8 for GPT-6 Sol. Pick GPT-6 Sol when what matters is CyberBench (Vals AI) or SciCode, where it leads.

Which is cheaper, GPT-6.1 Sol or GPT-6 Sol?

GPT-6.1 Sol costs $2.00 per million input tokens and $10.00 per million output tokens; GPT-6 Sol costs $2.00 and $10.00. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-6.1 Sol or GPT-6 Sol?

Neither: both take 1.05M tokens.

How many benchmarks is the GPT-6.1 Sol vs GPT-6 Sol comparison based on?

90 benchmarks have a result for both models as of October 21, 2026. GPT-6.1 Sol's coding index rests on 2 independent benchmarks and GPT-6 Sol's on 2. 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-sol-vs-gpt-6-sol" title="GPT-6.1 Sol vs GPT-6 Sol, 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-sol-vs-gpt-6-sol">LLMBenchmark.ai, GPT-6.1 Sol vs GPT-6 Sol</a></p>