# GPT-6 Sol

GPT-6 Sol is an AI model released by OpenAI on Sep 22 2026. It has a 1.05M context window. Tracked results include 59% on BullshitBench v2, 89.58% on ARC-AGI-2 and 68.8% on DeepSWE 1.1.

## Facts

| Field | Value |
| --- | --- |
| Model | GPT-6 Sol |
| Developer | OpenAI |
| Release date | Tuesday, Sep 22 2026 |
| Licensing | Closed |
| Context window | 1.05M |

## API pricing

All rates in USD per 1,000,000 tokens, pay-as-you-go.

| Tier | Input | Cached input | Cache write | Output |
| --- | --- | --- | --- | --- |
| Up to 272K input tokens | $2.00 | $0.20 | $2.50 | $10.00 |
| Over 272K input tokens | $4.00 | $0.40 | $5.00 | $15.00 |

OpenAI also publishes a Fast mode for this model at exactly twice the standard rate in every column — $4.00 per million input tokens and $20.00 per million output at short context.
Verified October 19, 2026 against the first-party source: https://developers.openai.com/api/docs/models/gpt-6-sol

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| CheatBench | 71.9% | [CheatBench](https://cheatbench.ai/), retrieved 2026-09-25 | Measures how often AI agents try to cheat on difficult assignments, such as reading hidden answers, copying work or manipulating grading. The overall score gives equal weight to ten categories; the sycophancy category measures how far an agent shifts its beliefs toward a user's stated views. Scores describe each model in its tested agent setup, and task success is measured separately. Lower is better. |
| BullshitBench v2 | 59% | [BullshitBench](https://github.com/petergpt/bullshit-benchmark) | Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. |
| DeepSWE 1.1 | 68.8% | Lab | Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. |
| Next.js Evals | 100% | [Next.js Evals](https://nextjs.org/evals) | Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. |
| Supabase Evals (with skills) | 78.3% | [Supabase Evals](https://supabase.com/evals) | Supabase's own open benchmark: a coding agent is dropped into a real Supabase project and asked to do real work — set up a schema, fix a broken security policy, debug an Edge Function — and every run is checked against a live Supabase stack. This is the headline number, where the agent has Supabase's own skills loaded, as most people building on Supabase would. The score is the share of scenarios it got right. Higher is better. |
| Supabase Evals (no skills) | 78.3% | [Supabase Evals](https://supabase.com/evals) | The same Supabase scenarios, but with none of Supabase's skills loaded — so it measures what the model already knows about building on Supabase, rather than how well it follows Supabase's supplied instructions. Higher is better. |
| Terminal-Bench 4.0 | 49.39% | [Terminal-Bench](https://github.com/harbor-framework/terminal-bench), retrieved 2026-10-12 | Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better. |
| ARC-AGI-2 | 89.58% | [BenchLM](https://benchlm.ai), retrieved 2026-10-12 | Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. |
| OSWorld 2.0 | 60.5% | Lab | Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.0 is a harder, refreshed task set. Higher is better. |
| Agent's Last Exam (pass@1) | 56.4% | Lab | A hard set of desktop and operating-system tasks an AI agent has to finish by looking at the screen and working the machine itself. The score is the share it passes outright — partial credit does not count. Higher is better. |
| AutomationBench | 33.2% | Lab | Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. |
| threejseval | 1622 | [threejseval](https://threejseval.com/ranking) | Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better. |

## About GPT-6 Sol

GPT-6 Sol was introduced in September 2026 alongside GPT-6 Luna as a lower-cost option within the family opened by Astra. OpenAI positioned Sol for coding, professional tasks and agent workflows, while reserving Astra for more demanding work. The initial product announcement offered the pair through ChatGPT Work, Codex and the API, with access dependent on the plan and interface.

The API model documented a 1,050,000-token context window, text and image inputs, and configurable reasoning effort. These controls allowed developers to adjust the computation used for different requests. Sol's launch emphasized efficiency, but comparisons with other models still depended on reasoning settings, tools and task selection. GPT-6.1 Sol followed as a separate update later that month.

## Questions and answers

### When was GPT-6 Sol released?

GPT-6 Sol was released by OpenAI on Tuesday, Sep 22 2026.

### Who made GPT-6 Sol?

GPT-6 Sol was built by OpenAI. Creators of ChatGPT and the GPT series of models. Pioneered large-scale language model research.

### How much does GPT-6 Sol cost?

GPT-6 Sol costs $2.00 per million input tokens and $10.00 per million output tokens through the OpenAI API. Cached input is $0.20 per million tokens. Those are the rates for the “Up to 272K input tokens” tier; 1 other pricing tier is published for this model. Rates are pay-as-you-go API prices verified against OpenAI's published pricing on October 19, 2026.

### What benchmark scores did GPT-6 Sol get?

GPT-6 Sol reports 12 tracked benchmark scores — CheatBench: 71.9%; BullshitBench v2: 59%; DeepSWE 1.1: 68.8%; Next.js Evals: 100%; Supabase Evals (with skills): 78.3%; Supabase Evals (no skills): 78.3%; Terminal-Bench 4.0: 49.39%; ARC-AGI-2: 89.58%; OSWorld 2.0: 60.5%; Agent's Last Exam (pass@1): 56.4%; AutomationBench: 33.2%; threejseval: 1622. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of GPT-6 Sol?

GPT-6 Sol has a context window of 1.05M. Providers may specify separate input and output token limits.

### Is GPT-6 Sol open source?

No. GPT-6 Sol is a closed model. The weights are not published — it is available only through the provider's own API, apps, or partner platforms.

### What came before and after GPT-6 Sol?

OpenAI's previous tracked release was GPT-6 Astra on Sep 3 2026, 19 days earlier. It was followed by GPT-6 Luna on Sep 22 2026.


---

Canonical page: https://aireleasetracker.com/model/openai/gpt-6-sol
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.