Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models838Deals30d267Policy30d80, 15 pendingSources1,184

GPT-6.1 Sol

OpenAIReleased Sep 29, 2026Current

Score basis

GPT-6.1 Sol is at the frontier in math and factuality, strong in reasoning and long context, capable in multimodal tasks and instruction following, and behind the leaders in agentic tasks and coding. Too few results yet to rate safety or multilingual tasks.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Frontier2 capabilities
  1. MathLeads5 of 5
  2. Factuality−0.9%3 of 4
Strong2 capabilities
  1. Reasoning−6.0%5 of 6
  2. Long Context−9.2%1 of 3
Capable2 capabilities
  1. Multimodal−21.5%1 of 6
  2. Instruction Following−21.7%2 of 3
Limited2 capabilities
  1. Agentic−25.4%3 of 7
  2. Coding−28.7%4 of 10
Not rated2 capabilities

Too few results yet to rate Safety or Multilingual.

Price

$2.00input$10.00outputper million tokens

From Artificial Analysis · 3 providers tracked · All prices

Costs more than 82% of 331 priced models · 3:1 input-to-output blend, log scale

Evidence

138results on50benchmarks

  • 42 independently verified
  • 74 aggregator
  • 17 vendor-reported
  • 5 cross-referenced

From 21 sources · latest Nov 13, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Research

28 papers reference GPT-6.1 Sol

GPT-6.1 Sol benchmark results

138 results on 50 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Math

FrontierFull math ranking

Leads the field5 of 5 ranked benchmarks measured

Show 2 more math resultsHide 2 math results

Factuality

FrontierFull factuality ranking

0.9% behind the leader3 of 4 ranked benchmarks measured

Show 9 more factuality resultsHide 9 factuality results

Reasoning

StrongFull reasoning ranking

6.0% behind the leader5 of 6 ranked benchmarks measured

Show 21 more reasoning resultsHide 21 reasoning results

Long Context

StrongFull long context ranking

9.2% behind the leader1 of 3 ranked benchmarks measured

Show 4 more long context resultsHide 4 long context results

Multimodal

CapableFull multimodal ranking

21.5% behind the leader1 of 6 ranked benchmarks measured

Show 6 more multimodal resultsHide 6 multimodal results

Instruction Following

CapableFull instruction following ranking

21.7% behind the leader2 of 3 ranked benchmarks measured

Show 1 more instruction following resultHide 1 instruction following result

Agentic

LimitedFull agentic ranking

25.4% behind the leader3 of 7 ranked benchmarks measured

Show 9 more agentic resultsHide 9 agentic results

Coding

LimitedFull coding ranking

28.7% behind the leader4 of 10 ranked benchmarks measured

Show 5 more coding resultsHide 5 coding results

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 54 more resultsHide 54 results

GPT-6.1 Sol: common questions

Who makes GPT-6.1 Sol?

GPT-6.1 Sol is made by OpenAI.

When was GPT-6.1 Sol released?

GPT-6.1 Sol was released on Sep 29, 2026, according to Artificial Analysis.

What is GPT-6.1 Sol good at?

GPT-6.1 Sol is at the frontier in math and factuality, strong in reasoning and long context, capable in multimodal tasks and instruction following, and behind the leaders in agentic tasks and coding. Too few results yet to rate safety or multilingual tasks.

How much does GPT-6.1 Sol cost?

GPT-6.1 Sol costs $2.00 per million input tokens and $10.00 per million output tokens, according to Artificial Analysis. We track its price at 3 providers. At a mix of three input tokens to one output token, it costs more than 82% of the 331 priced models we track.

How many benchmarks has GPT-6.1 Sol been tested on?

We track 138 results for GPT-6.1 Sol on 50 benchmarks from 21 sources, 42 of them independently verified. The latest was recorded on Nov 13, 2026.

Which API features does GPT-6.1 Sol support?

OpenRouter lists tool calling, structured outputs, and reasoning for GPT-6.1 Sol.

About this record

Where GPT-6.1 Sol's numbers come from, and every name it appears under.

Tracked since
Sep 29, 2026
Newest source mention
Oct 29, 2026

Where the results come from

Verification: 138 scores · 42 independently verified · 74 aggregator-attributed · 5 vendor cross-reference · 17 vendor-reported. How these tiers are assigned

From 21 sources on 11 sites. Artificial Analysis supplies 75 of them; the 42 independently verified results come from 8 sites. Bars are coloured by trust tier.

  • artificialanalysis.ai75
  • arcprize.org18
  • livebench.ai14
  • api.llm-stats.com11
  • deploymentsafety.openai.com6
  • assets.claude.com5
  • epoch.ai3
  • datasets-server.huggingface.co2
  • labs.scale.com2
  • lmarena.ai1
  • simple-bench.com1

Also known as

How our sources name GPT-6.1 Sol at each reasoning setting.

SettingShort formAPI id
lowgpt-6.1 sol (low)gpt-6-1-sol-low
mediumgpt-6.1 sol (medium)gpt-6-1-sol-medium
highgpt-6.1 sol (high) gpt-6.1 sol high gpt-6.1 sol extra highgpt-6-1-sol-high
xhighgpt-6.1 sol (xhigh)gpt-6-1-sol-xhigh
maxgpt-6.1 sol (max)gpt-6.1-sol-max
Also listed asgpt-6-1-solgpt-6.1-sol:batchopenai gpt 6.1 solchatgpt 6.1openai: gpt-6.1 sol