GPT-6 Sol and GPT-6 Luna released
OpenAI · Model release
Source confirmed
Data as of October 6, 2026 · How the score is built
Superseded.OpenAI has newer models in this line:GPT-6.1 Sol
SupersededProprietaryReasoning
Released Sep 22, 20261.05M contextOpenAI GPT-6 Sol model documentation
GPT-6 Sol
Decision readingGPT-6 Sol scores 75.2 out of 100 and ranks #10 of 214. This profile shows 16 source-displayable benchmark rows; its strongest eligible category is Coding at #10. API pricing is $2 input and $10 output per million tokens, with cached input at $0.2.
Released Sep 22, 2026 — see all recent releases
GPT-6 Sol will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
75.2/100
field median 52#10 of 214 ranked models
Public
#10of 214
Verified #8 of 83
Price
$2input / $10 output
input median $0.95cached $0.20 · blended $6
Speed
Not measured
field median 98 tok/sTime to first token not measured
Context
1.05Mtokens
field median 256,000Maximum output length is tracked separately
Strongest published evidence
Coding ranks #10. Particularly well-suited for software development and code generation tasks.
Validate before choosing
16 published rows leave some tracked benchmark slots empty. Independent runtime speed has not been measured.
Source-linked · 16 displayable benchmark rows
Follow model changesCheck the published record for the model and serving route you use.
Check this modelCategory score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| Agentic8.9 points below GPT-5.6 SolRank #26 of 120Percentile 79thWeight 22%5 benchmarksVerified | 59.0 | 5 benchmarks | Verified | |||
| Coding2.7 points below GPT-5.6 SolRank #10 of 144Percentile 94thWeight 20%1 benchmarkVerified | 66.7 | 1 benchmark | Verified | |||
| ReasoningRank #16 of 27Percentile 42ndWeight 17%3 benchmarksVerified | 69.5 | 3 benchmarks | Verified | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeRank #10 of 173Percentile 95thWeight 12%5 benchmarksVerified | 76.8 | 5 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%1 benchmarkVerified | Score pending | 1 benchmark | Verified | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
An earlier release can outscore a newer one in a single category. The note under that category names the release and the gap.
16 of 655 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic5/5 verified
- Coding1/1 verified
- Reasoning3/3 verified
- MultimodalNot measured
- Knowledge5/5 verified
- MultilingualNot measured
- Inst. Following1/1 verified
- MathNot measured
Verified sourceProvisionalNot measured
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
GPT-6 Sol category percentile values
- Agentic79th percentile
- Coding94th percentile
- Reasoning42nd percentile
- MultimodalNot eligible
- Knowledge95th percentile
- MultilingualNot eligible
- Instruction followingNot eligible
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#26/120
- Coding#10/144
- Reasoning#16/27
- MultimodalNot ranked
- Knowledge#10/173
- MultilingualNot ranked
- Inst. FollowingNot ranked
- MathNot ranked
Top decileTop quartileMid-fieldNot eligible
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| DeepSWE | Score68.8% | Versus best verified row Best verified: Gemini 4 Argon · 77.9% | Gap9.1 behind | Weight15% ref. weight | Provider exact |
Agentic5 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| OSWorld 2.0 | Score60.5% | Versus best verified row Best verified: GPT-6 Astra · 72.6% | Gap12.1 behind | Weight10% ref. weight | Provider exact |
| AutomationBench | Score33.2% | Versus best verified row Best verified: DeepSeek V4.1 Flash · 54.8% | Gap21.6 behind | Weight5% ref. weight | Provider exact |
| Agents' Last Exam | Score56.4% | Versus best verified row Best verified: GPT-6 Astra · 59.3% | Gap2.9 behind | Weight3% ref. weight | Provider exact |
| ExploitGym | Score22.1% | Versus best verified row Best verified: GPT-6 Astra · 42.4% | Gap20.3 behind | WeightDisplay only | Provider exact |
| CWE-bench v1 | Score52.0% | Versus best verified row Best verified: GPT-6 Astra · 68.0% | Gap16 behind | WeightDisplay only | Benchmark exact |
Reasoning3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| ARC-AGI-2Abstraction and Reasoning Corpus for AGI v2 | Score89.6% | Versus best verified row Best verified: GPT-6 Astra · 95% | Gap5.4 behind | WeightWeighted 25% | Benchmark exact |
| ARC-AGI-3Abstraction and Reasoning Corpus for AGI v3 | Score4.6% | Versus best verified row Best verified: GPT-6 Astra · 62.7% | Gap58.1 behind | WeightWeighted 15% | Benchmark exact |
| ARC-AGI-1ARC-AGI-1 Semi-Private Evaluation | Score95.50% | Versus best verified row Best verified: GPT-6 Astra · 98.50% | Gap3 behind | WeightDisplay only | Benchmark exact |
Knowledge5 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HealthBench (raw)HealthBench raw score | Score47.1% | Versus best verified row Best verified: Claude Sonnet 5.5 · 69.4% | Gap22.3 behind | WeightDisplay only | Provider exact |
| HealthBench (length-adjusted)HealthBench length-adjusted score | Score53.2% | Versus best verified row Best verified: Claude Sonnet 5.5 · 65.4% | Gap12.2 behind | WeightDisplay only | Provider exact |
| HealthBench Professional | Score60.8% | Versus best verified row Best verified: Claude Sonnet 5.5 · 69.2% | Gap8.4 behind | WeightDisplay only | Provider exact |
| HealthBench Professional (raw)HealthBench Professional raw score | Score59.5% | Versus best verified row Best verified: Claude Sonnet 5.5 · 77.1% | Gap17.6 behind | WeightDisplay only | Provider exact |
| HealthBench Hard | Score30.1% | Versus best verified row Best verified: Muse Spark · 42.8% | Gap12.7 behind | WeightDisplay only | Provider exact |
Inst. Following1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Gray Swan IPI (15 attempts)Gray Swan Indirect Prompt Injection, attack success at 15 attempts | Score10.1% | Versus best verified row Best verified: Gemini 4 Argon · 0.7% | Gap9.4 behind | WeightDisplay only | Provider exact |
External signals1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| SEC-Bench Pro | Score66.3% | Versus best verified row Best verified: GPT-6 Astra · 85.4% | Gap19.1 behind | WeightDisplay only | Provider exact |
What it costs to get this score
Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.
Current modelExplore all models
GPT-6 Sol · 75.2 score · $6 blended per million tokens
The chart opens on the current model. Scroll horizontally to inspect the full price axis.
Horizontal: blended price per million tokens, log scale · Vertical: public score
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Radar
Full release historyGPT-6 Sol release history
Radar confirmed these at the source. Use GPT-6 Sol in your work? Explore Radar to follow supported changes and choose your alerts.
Radar
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- gpt-6-solOpenAI GPT-6 Sol model documentation
- Context window
- 1.05MOpenAI GPT-6 Sol model documentation
- Maximum output
- 128,000 tokensOpenAI GPT-6 Sol model documentation
- Knowledge cutoff
- April 20, 2026OpenAI GPT-6 Sol model documentation
- Input modalities
- text, imageOpenAI GPT-6 Sol model documentation
- Output modalities
- textOpenAI GPT-6 Sol model documentation
- Parameters
- Not disclosed by the provider
- Availability
- OpenAI Responses API · OpenAI Chat Completions API · ChatGPT Work · CodexOpenAI GPT-6 Sol and Luna launch
Chat Completions supports function calling with GPT-6 Sol only when reasoning_effort is none. Use the Responses API for built-in tools or for function calling with reasoning on. OpenAI GPT-6 Sol model documentation, read Sep 25, 2026
- Cloud regions
- Not tracked yet
- Lifecycle
- activeOpenAI GPT-6 Sol model documentation
- API capabilities
- Streaming · function calling · structured outputs · web/file search · image generation · code interpreter · hosted shell · apply patch · skills · computer use · MCP · tool searchOpenAI GPT-6 Sol model documentation
- Prompt caching
- Published at $0.20 per million cached input tokensOpenAI GPT-6 Sol model documentation
- Self-host
- Weights are not published
- Rate limits
- Tier 1: 500 RPM / 500K TPM; Tier 5: 15K RPM / 40M TPM; Free unsupportedOpenAI GPT-6 Sol model documentation
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
GPT-6 Sol ranks #10 of 214 on the public leaderboard with a score of 75.19/100. Its source-verified position is #8 of 83.
GPT-6 Sol is a proprietary model with a 1.05M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Released September 22, 2026 in ChatGPT Work and Codex for Plus, Pro, Business, Enterprise, and Edu users, and in the OpenAI API as gpt-6-sol. OpenAI documents Responses API support for built-in tools and function calling; Chat Completions supports function calling when reasoning_effort is set to none.
OpenAI documents GPT-6 Sol as a distinct API model for complex coding and agentic workflows, with configurable reasoning, text and image input, text output, and a 1,050,000-token context window. OpenAI publishes provider-run measurements, and ARC Prize provides verified ARC-AGI results.
GPT-6 Sol sits in the GPT-6 family with GPT-6 Astra, GPT-6.1 Sol, GPT-6 Luna. Its explicit predecessor is GPT-5.6 Sol. 16 of 655 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Coding at #10, while its lowest eligible position is Agentic at #26. particularly well-suited for software development and code generation tasks.
Last updated October 6, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does GPT-6 Sol perform overall in AI benchmarks?
GPT-6 Sol ranks #10 out of 214 models on the public BenchAlign leaderboard, with a score of 75.19/100. Its evidence status is Supported, and this profile shows 16 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is GPT-6 Sol good for knowledge and understanding?
GPT-6 Sol ranks #10 out of 173 eligible models for knowledge and understanding, with a public category score of 76.8/100. That places it in the current top ten for this category. Check the underlying rows before treating the aggregate as a workload guarantee.
Is GPT-6 Sol good for coding and programming?
GPT-6 Sol ranks #10 out of 144 eligible models for coding and programming, with a public category score of 66.7/100. That places it in the current top ten for this category. Check the underlying rows before treating the aggregate as a workload guarantee.
Is GPT-6 Sol good for reasoning and logic?
GPT-6 Sol ranks #16 out of 27 eligible models for reasoning and logic, with a public category score of 69.5/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is GPT-6 Sol good for agentic tool use and computer tasks?
GPT-6 Sol ranks #26 out of 120 eligible models for agentic tool use and computer tasks, with a public category score of 59/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is GPT-6 Sol good for instruction following?
GPT-6 Sol has source-displayable benchmark coverage for instruction following, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Which sibling models are related to GPT-6 Sol?
GPT-6 Sol belongs to the GPT-6 family. Related tracked variants include GPT-6 Astra, GPT-6.1 Sol, GPT-6 Luna. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does GPT-6 Sol have full benchmark coverage on BenchLM?
No. GPT-6 Sol currently has 33 source-displayable rows across 655 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of GPT-6 Sol?
GPT-6 Sol has a documented context window of 1.05M. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.