Claude Opus 5 vs GPT-6.1 Sol

Updated November 13, 2026. Rank says GPT-6.1 Sol is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Decision reading

GPT-6.1 Sol has the higher public score, 84.63 versus 76.07, and the 90% score intervals do not overlap. 17 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A

Claude Opus 5

Anthropic

76.07/100

Supported · Public rank #13

90% interval 73.4–78.7

Model B

GPT-6.1 Sol

OpenAI

84.63/100

Supported · Public rank #5

90% interval 80.4–88.9

API price per 1M tokens

Claude Opus 5: $5 input / $25 output

GPT-6.1 Sol: $2 input / $10 output

Context window

Claude Opus 5: 1M

GPT-6.1 Sol: 1.05M

Released

Claude Opus 5: July 24, 2026

GPT-6.1 Sol: September 29, 2026

Shared results: 17
Claude Opus 5 only: 68
GPT-6.1 Sol only: 12
Like-for-like categories: 4 / 8

Supported: Claude Opus 5 and GPT-6.1 SolHow the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

Coding work
Code generation, repair, and software-engineering tasks
GPT-6.1 Sol
GPT-6.1 Sol has the higher public coding point estimate, 73.4 to 66.8, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Claude Opus 5
Claude Opus 5 has the higher public agentic point estimate, 75.5 to 65.7, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Confidence: limited
Long documents
Prompts that approach the documented context limit
GPT-6.1 Sol
GPT-6.1 Sol has the larger documented context window.
Confidence: documented

Show secondary and unsupported calls

Chat turn cost
1K fresh input + 500 output tokens
GPT-6.1 Sol
GPT-6.1 Sol has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
GPT-6.1 Sol
GPT-6.1 Sol has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
GPT-6.1 Sol
GPT-6.1 Sol has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

Pick the job you would use them for

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

66.8Claude Opus 573.4GPT-6.1 Sol

Like-for-like · BenchAlign v5.8

GPT-6.1 Sol has the higher coding point estimate. Conditional score ranges do not establish rank confidence.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboard Shortlist models for this job

Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

What do you need a model for?

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

FrontierMath v2 (Tier 4)Math
Normalized gap 26.8
Claude Opus 5:73.171%
GPT-6.1 Sol:100.000%
Shared source
ARC-AGI-3Reasoning
Normalized gap 22.6
Claude Opus 5:30.2%
GPT-6.1 Sol:52.7%
Claude Opus 5 source GPT-6.1 Sol source
AutomationBenchAgentic
Normalized gap 10.1
Claude Opus 5:26.0%
GPT-6.1 Sol:36.1%
Claude Opus 5 source GPT-6.1 Sol source
FrontierMath v2 (Tiers 1-3)Math
Normalized gap 8.1
Claude Opus 5:85.614%
GPT-6.1 Sol:93.684%
Shared source
ARC-AGI-2Reasoning
Normalized gap 3.7
Claude Opus 5:90.4%
GPT-6.1 Sol:94.2%
Claude Opus 5 source GPT-6.1 Sol source

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, reasoning, multimodal, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Like-for-like

Claude Opus 5: 75.5; Supported · #5/135
GPT-6.1 Sol: 65.7; Supported · #17/135
Basis: BenchAlign v5.8 lane · 23 vs 7 public rows
Reading: Claude Opus 5 leads · intervals overlap

Coding

Like-for-like

Claude Opus 5: 66.8; Supported · #14/162
GPT-6.1 Sol: 73.4; Supported · #8/162
Basis: BenchAlign v5.8 lane · 21 vs 6 public rows
Reading: GPT-6.1 Sol leads · intervals overlap

Reasoning

Like-for-like

Claude Opus 5: 73.8; Supported · #12/160
GPT-6.1 Sol: 80.4; Supported · #5/160
Basis: BenchAlign v5.8 lane · 3 vs 6 public rows
Reading: GPT-6.1 Sol leads · intervals overlap

Knowledge

Like-for-like

Claude Opus 5: 79.0; Supported · #9/180
GPT-6.1 Sol: 85.6; Supported · #3/180
Basis: BenchAlign v5.8 lane · 19 vs 5 public rows
Reading: GPT-6.1 Sol leads · intervals overlap

Multimodal

Directional only

Claude Opus 5: 76.2; Estimated · #11/67
GPT-6.1 Sol: 78.9; Supported · #4/67
Basis: BenchAlign v5.8 lane · 8 vs 3 public rows
Reading: Directional only

Multilingual

Not comparable

Claude Opus 5: Not ranked
GPT-6.1 Sol: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Instruction following

Not comparable

Claude Opus 5: Not ranked
GPT-6.1 Sol: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Math

Not comparable

Claude Opus 5: 86.2; Unranked · 7 rankable rows
GPT-6.1 Sol: 93.8; Unranked · 2 rankable rows
Basis: Provisional lane · 2 vs 2 weighted rows
Reading: Not comparable

Category scores with the server-provided evidence basis for Claude Opus 5 and GPT-6.1 Sol
Category	Claude Opus 5	GPT-6.1 Sol	Basis	Reading
Agentic	75.5Supported · #5/135	65.7Supported · #17/135	Like-for-likeBenchAlign v5.8 lane · 23 vs 7 public rows	Claude Opus 5 leads · intervals overlap
Coding	66.8Supported · #14/162	73.4Supported · #8/162	Like-for-likeBenchAlign v5.8 lane · 21 vs 6 public rows	GPT-6.1 Sol leads · intervals overlap
Reasoning	73.8Supported · #12/160	80.4Supported · #5/160	Like-for-likeBenchAlign v5.8 lane · 3 vs 6 public rows	GPT-6.1 Sol leads · intervals overlap
Knowledge	79.0Supported · #9/180	85.6Supported · #3/180	Like-for-likeBenchAlign v5.8 lane · 19 vs 5 public rows	GPT-6.1 Sol leads · intervals overlap
Multimodal	76.2Estimated · #11/67	78.9Supported · #4/67	Directional onlyBenchAlign v5.8 lane · 8 vs 3 public rows	Directional only
Multilingual	Not ranked	Not ranked	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Instruction following	Not ranked	Not ranked	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Math	86.2Unranked · 7 rankable rows	93.8Unranked · 2 rankable rows	Not comparableProvisional lane · 2 vs 2 weighted rows	Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, reasoning, multimodal, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Claude Opus 5: $0.0175; Fits in one request
GPT-6.1 Sol: $0.007; Fits in one request

GPT-6.1 Sol has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Opus 5: $0.325; Fits in one request
GPT-6.1 Sol: $0.13; Fits in one request

GPT-6.1 Sol has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Claude Opus 5: $0.45; Fits in one request
GPT-6.1 Sol: $0.16; Fits in one request

GPT-6.1 Sol has the lower modeled cost

Costs use the listed standard API rates.

Your workload

Enter a month of tokens to price it at both models’ listed API rates.

Input, millionsOutput, millionsCached input, %

Claude Opus 5: $100.00; per month
GPT-6.1 Sol: $40.00; per month

Standard listed rates, no batch or volume discounts.

Cached input falls back to the list input rate only where a cached rate is unpublished

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

SpecificationClaude Opus 5GPT-6.1 Sol

Context window

Maximum documented context; output-token limits may be lower.

Claude Opus 5

Anthropic model overview

GPT-6.1 Sol

1.05M

OpenAI GPT-6.1 Sol model documentation

API model ID

Claude Opus 5

claude-opus-5

Anthropic model overview

GPT-6.1 Sol

gpt-6.1-sol

OpenAI GPT-6.1 Sol model documentation

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Claude Opus 5

$0.5 per 1M cached input tokens

Claude API pricing

GPT-6.1 Sol

$0.1 per 1M cached input tokens

OpenAI GPT-6.1 Sol model documentation

Documented inputs

Claude Opus 5

text, image

Anthropic model overview

GPT-6.1 Sol

text, image

OpenAI GPT-6.1 Sol model documentation

Documented outputs

Claude Opus 5

text

Anthropic model overview

GPT-6.1 Sol

text

OpenAI GPT-6.1 Sol model documentation

Provider availability

Claude Opus 5

Generally Available · Claude API

Anthropic model overview

GPT-6.1 Sol

Generally Available · OpenAI Responses API, OpenAI Chat Completions API

OpenAI GPT-6.1 Sol model documentation

Reasoning profile

Claude Opus 5

Reasoning

GPT-6.1 Sol

Reasoning

Weight access

Claude Opus 5

Proprietary

GPT-6.1 Sol

Proprietary

License

Claude Opus 5

Proprietary

GPT-6.1 Sol

Proprietary

Release date

Claude Opus 5

2026-07-24

GPT-6.1 Sol

2026-09-29

If you already use one of these models

Deployment change: The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal: GPT-6.1 Sol has the higher public score, 84.63 versus 76.07, and the 90% score intervals do not overlap.
Workload cost: Repository review: $0.325 vs $0.13. Cache-heavy agent loop: $0.45 vs $0.16.
Context tradeoff: GPT-6.1 Sol has the larger documented window (1.05M).

Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Claude Opus 5 or GPT-6.1 Sol?

GPT-6.1 Sol has the higher public score, 84.63 versus 76.07, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.

Which is better for coding, Claude Opus 5 or GPT-6.1 Sol?

GPT-6.1 Sol has the higher public coding point estimate, 73.4 to 66.8, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which is better for agentic tasks, Claude Opus 5 or GPT-6.1 Sol?

Claude Opus 5 has the higher public agentic tasks point estimate, 75.5 to 65.7, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which costs less, Claude Opus 5 or GPT-6.1 Sol?

For the stated presets, chat costs $0.0175 on Claude Opus 5 and $0.007 on GPT-6.1 Sol; repository review costs $0.325 and $0.13; the cache-heavy agent loop costs $0.45 and $0.16. Costs use the listed standard API rates.

Which has the larger context window, Claude Opus 5 or GPT-6.1 Sol?

GPT-6.1 Sol has the larger documented context window: 1.05M, compared with 1M.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence97 rows

Agentic

Terminal-Bench 4.1
Shared source
Claude Opus 553.30%
GPT-6.1 Sol60.90%
GPT-6.1 Sol leads this result
Terminal-Bench 3.0
Claude Opus 542.7%
Source
GPT-6.1 Sol—
Not directly comparable
BrowseComp
Claude Opus 590.8%
Source
GPT-6.1 Sol—
Not directly comparable
HLE w/ tools
Claude Opus 564.7%
Source
GPT-6.1 Sol—
Not directly comparable
DeepSearchQA
Claude Opus 595.0%
Source
GPT-6.1 Sol—
Not directly comparable
DRACO
Claude Opus 588.6%
Source
GPT-6.1 Sol—
Not directly comparable
BrowseComp (10-agent, prerelease)
Claude Opus 593.6%
Source
GPT-6.1 Sol—
Not directly comparable
OSWorld 2.0
Claude Opus 570.6%
Source
GPT-6.1 Sol—
Not directly comparable
MCP Atlas
Claude Opus 585.8%
Source
GPT-6.1 Sol—
Not directly comparable
MCP-Atlas claim coverage
Claude Opus 589.1%
Source
GPT-6.1 Sol—
Not directly comparable
LAB all-pass (Anthropic harness)
Claude Opus 523.58%
Source
GPT-6.1 Sol—
Not directly comparable
LAB criterion-pass (Anthropic harness)
Claude Opus 593.74%
Source
GPT-6.1 Sol—
Not directly comparable
LAB all-pass (Harvey held-out)
Claude Opus 511.7%
Source
GPT-6.1 Sol—
Not directly comparable
LAB criterion-pass (Harvey held-out)
Claude Opus 594.1%
Source
GPT-6.1 Sol—
Not directly comparable
Toolathlon-Verified
Claude Opus 580.6%
Source
GPT-6.1 Sol—
Not directly comparable
Toolathlon Verified Pass@3
Claude Opus 587.0%
Source
GPT-6.1 Sol—
Not directly comparable
Toolathlon Verified Pass³
Claude Opus 573.1%
Source
GPT-6.1 Sol—
Not directly comparable
Toolathlon Verified avg. turns
Claude Opus 523.5 turns
Source
GPT-6.1 Sol—
Not directly comparable
AutomationBench
Claude Opus 526.0%
Source
GPT-6.1 Sol36.1%
Source
GPT-6.1 Sol leads this result
Terminal-Bench 2.1 (Vals)
Claude Opus 584.6%
Source
GPT-6.1 Sol—
Not directly comparable
ApprenticeBench
Claude Opus 536%
Source
GPT-6.1 Sol—
Not directly comparable
MazeBench
Claude Opus 512%
Source
GPT-6.1 Sol17%
Source
GPT-6.1 Sol leads this result
OSWorld 2.1
Claude Opus 574.0%
Source
GPT-6.1 Sol—
Not directly comparable
Terminal-Bench-Science 0.1
Claude Opus 5—
GPT-6.1 Sol57.0%
Source
Not directly comparable
ExploitGym
Claude Opus 5—
GPT-6.1 Sol35.1%
Source
Not directly comparable
Hermes Index
Claude Opus 5—
GPT-6.1 Sol57.1%
Source
Not directly comparable
Hermes Bench
Claude Opus 5—
GPT-6.1 Sol73.9%
Source
Not directly comparable

Coding

ScarfBench
Shared source
Claude Opus 569.8%
GPT-6.1 Sol68.4%
Claude Opus 5 leads this result
Bug Hunt Bench
Shared source
Claude Opus 527.0 fixes
GPT-6.1 Sol44.3 fixes
GPT-6.1 Sol leads this result
SWE-bench Verified
Claude Opus 596%
Source
GPT-6.1 Sol—
Not directly comparable
SWE-bench Pro
Claude Opus 579.2%
Source
GPT-6.1 Sol—
Not directly comparable
SWE Multilingual
Claude Opus 589.5%
Source
GPT-6.1 Sol—
Not directly comparable
SWE Multimodal
Claude Opus 559.4%
Source
GPT-6.1 Sol—
Not directly comparable
DeepSWE
Claude Opus 568.8%
Source
GPT-6.1 Sol71.9%
Source
GPT-6.1 Sol leads this result
FrontierCode 1.1 Main
Claude Opus 553.4%
Source
GPT-6.1 Sol—
Not directly comparable
FrontierCode 1.1 Extended
Claude Opus 563.6%
Source
GPT-6.1 Sol—
Not directly comparable
FrontierSWE v2
Claude Opus 552.0%
Source
GPT-6.1 Sol—
Not directly comparable
ProgramBench (episode 1)
Claude Opus 583.0%
Source
GPT-6.1 Sol—
Not directly comparable
ProgramBench
Claude Opus 593.0%
Source
GPT-6.1 Sol—
Not directly comparable
CursorBench 3.2
Claude Opus 570.0%
Source
GPT-6.1 Sol—
Not directly comparable
VulcanBench v3
Claude Opus 587.0%
Source
GPT-6.1 Sol—
Not directly comparable
VulcanBench CII v1
Claude Opus 596.4%
Source
GPT-6.1 Sol—
Not directly comparable
LiveCodeBench (Vals)
Claude Opus 589.0%
Source
GPT-6.1 Sol—
Not directly comparable
SWE-bench (Vals)
Claude Opus 597.0%
Source
GPT-6.1 Sol—
Not directly comparable
CursorBench 4.0
Claude Opus 546.6%
Source
GPT-6.1 Sol—
Not directly comparable
PostTrainBench v1.1
Claude Opus 535.0%
Source
GPT-6.1 Sol—
Not directly comparable
FrontierCode 2.0
Shared source
Claude Opus 526.7%
GPT-6.1 Sol39.0%
GPT-6.1 Sol leads this result
PostTrainBench
Shared source
Claude Opus 535.7%
GPT-6.1 Sol38.8%
GPT-6.1 Sol leads this result
VulcanBench Frontier v4
Claude Opus 5—
GPT-6.1 Sol88.8%
Source
Not directly comparable

Reasoning

ARC-AGI-1
Claude Opus 597.50%
Source
GPT-6.1 Sol96.50%
Source
Claude Opus 5 leads this result
ARC-AGI-2
Claude Opus 590.4%
Source
GPT-6.1 Sol94.2%
Source
GPT-6.1 Sol leads this result
ARC-AGI-3
Claude Opus 530.2%
Source
GPT-6.1 Sol52.7%
Source
GPT-6.1 Sol leads this result
BioBasicsBench
Claude Opus 5—
GPT-6.1 Sol62.6%
Source
Not directly comparable
STEMBench
Claude Opus 5—
GPT-6.1 Sol2.76
Source
Not directly comparable
ARC-AGI-3 Provider Adapter
Claude Opus 5—
GPT-6.1 Sol96.18%
Source
Not directly comparable

Multimodal

Chartography (no tools)
Claude Opus 529.6%
Source
GPT-6.1 Sol—
Not directly comparable
Chartography (tools)
Claude Opus 583.0%
Source
GPT-6.1 Sol—
Not directly comparable
BenchCAD Vision2Code (no tools)
Claude Opus 50.366
Source
GPT-6.1 Sol—
Not directly comparable
BenchCAD Vision2Code (tools)
Claude Opus 50.821
Source
GPT-6.1 Sol—
Not directly comparable
GDP.pdf (no tools)
Claude Opus 583.4%
Source
GPT-6.1 Sol—
Not directly comparable
GDP.pdf (tools)
Claude Opus 585.5%
Source
GPT-6.1 Sol—
Not directly comparable
OfficeQA
Claude Opus 578.1%
Source
GPT-6.1 Sol—
Not directly comparable
OfficeQA Pro
Claude Opus 566.9%
Source
GPT-6.1 Sol—
Not directly comparable
ExtractBench (LlamaIndex)
Claude Opus 5—
GPT-6.1 Sol95.31%
Source
Not directly comparable
ExtractBench Pro
Claude Opus 5—
GPT-6.1 Sol12%
Source
Not directly comparable
ParseBench
Claude Opus 5—
GPT-6.1 Sol69.63%
Source
Not directly comparable

Knowledge

HLE
Claude Opus 564.7%
Source
GPT-6.1 Sol—
Not directly comparable
HLE w/o tools
Claude Opus 556.3%
Source
GPT-6.1 Sol—
Not directly comparable
HLE-Verified
Claude Opus 554.4%
Source
GPT-6.1 Sol—
Not directly comparable
LABBench2
Claude Opus 584.2%
Source
GPT-6.1 Sol—
Not directly comparable
HealthBench (raw)
Claude Opus 567.1%
Source
GPT-6.1 Sol56.7%
Source
Claude Opus 5 leads this result
HealthBench (length-adjusted)
Claude Opus 557.8%
Source
GPT-6.1 Sol58.5%
Source
GPT-6.1 Sol leads this result
HealthBench Professional
Claude Opus 559.8%
Source
GPT-6.1 Sol64.2%
Source
GPT-6.1 Sol leads this result
HealthBench Professional (raw)
Claude Opus 573.4%
Source
GPT-6.1 Sol67.2%
Source
Claude Opus 5 leads this result
BioMysteryBench (human-solvable)
Claude Opus 590.1%
Source
GPT-6.1 Sol—
Not directly comparable
BioMysteryBench (human-difficult)
Claude Opus 549.4%
Source
GPT-6.1 Sol—
Not directly comparable
SpatialBench Verified
Claude Opus 572.5%
Source
GPT-6.1 Sol—
Not directly comparable
SingleCellBench
Claude Opus 560.6%
Source
GPT-6.1 Sol—
Not directly comparable
ProteinGym Hard
Claude Opus 547.7%
Source
GPT-6.1 Sol—
Not directly comparable
Protein Design
Claude Opus 542.5%
Source
GPT-6.1 Sol—
Not directly comparable
Organic chemistry V2
Claude Opus 561.6%
Source
GPT-6.1 Sol—
Not directly comparable
Protocols (troubleshooting)
Claude Opus 561.1%
Source
GPT-6.1 Sol—
Not directly comparable
Protocols (understanding)
Claude Opus 578.4%
Source
GPT-6.1 Sol—
Not directly comparable
GPQA Diamond (Vals)
Claude Opus 593.4%
Source
GPT-6.1 Sol—
Not directly comparable
MMLU-Pro (Vals)
Claude Opus 591.6%
Source
GPT-6.1 Sol—
Not directly comparable
HealthBench Hard
Claude Opus 5—
GPT-6.1 Sol36.2%
Source
Not directly comparable

Multilingual

GMMLU
Claude Opus 592.5%
Source
GPT-6.1 Sol—
Not directly comparable
MILU
Claude Opus 592.1%
Source
GPT-6.1 Sol—
Not directly comparable
INCLUDE
Claude Opus 589.8%
Source
GPT-6.1 Sol—
Not directly comparable

Instruction following

Gray Swan IPI (15 attempts)
Claude Opus 54.6%
Source
GPT-6.1 Sol—
Not directly comparable

Math

IMO 2026
Claude Opus 542/42
Source
GPT-6.1 Sol—
Not directly comparable
RiemannBench (no tools)
Claude Opus 560.0%
Source
GPT-6.1 Sol—
Not directly comparable
RiemannBench (tools)
Claude Opus 579.0%
Source
GPT-6.1 Sol—
Not directly comparable
ArXivMath Jun. 2026 (no tools)
Claude Opus 590.8%
Source
GPT-6.1 Sol—
Not directly comparable
ArXivMath Jun. 2026 (tools)
Claude Opus 591.3%
Source
GPT-6.1 Sol—
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Shared source
Claude Opus 585.614%
GPT-6.1 Sol93.684%
GPT-6.1 Sol leads this result
FrontierMath v2 (Tier 4)
Shared source
Claude Opus 573.171%
GPT-6.1 Sol100.000%
GPT-6.1 Sol leads this result

97 public results · 17 shared

Related comparisons

Compare API pricing Read the methodology Open the model selector

Watch Claude Opus 5 vs GPT-6.1 Sol

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 7,000+ subscribers.

Last updated November 13, 2026

Claude Opus 5 vs GPT-6.1 Sol

Decision reading

Which one for your work

Coding work

Agentic work

Long documents

Chat turn cost

Cache-heavy agent loop cost

Repository review cost

Which one for a specific job

Or describe your own job

What is actually comparable

Shape of the matched evidence

Category results, on a stated basis

Agentic

Coding

Reasoning

Knowledge

Multimodal

Multilingual

Instruction following

Math

What each workload costs

Chat turn

Repository review

Cache-heavy agent loop

Your workload

Specification differences

Context window

API model ID

Cached-input rate

Documented inputs

Documented outputs

Provider availability

Reasoning profile

Weight access

License

Release date

If you already use one of these models

Questions

Which is better, Claude Opus 5 or GPT-6.1 Sol?

Which is better for coding, Claude Opus 5 or GPT-6.1 Sol?

Which is better for agentic tasks, Claude Opus 5 or GPT-6.1 Sol?

Which costs less, Claude Opus 5 or GPT-6.1 Sol?

Which has the larger context window, Claude Opus 5 or GPT-6.1 Sol?

Benchmark evidence

Agentic

Coding

Reasoning

Multimodal

Knowledge

Multilingual

Instruction following

Math

Related comparisons

Watch Claude Opus 5 vs GPT-6.1 Sol