OpenAI · Frontier
GPT 6 Sol Pro
GPT-6 Sol Pro uses the same underlying model as GPT-6 Sol with Pro reasoning mode enabled for higher-quality responses on complex tasks.
- Reasoning
- Tools
- Vision
- Structured output
- PDF input
- Input
- Text, Images
- Output
- Text
- Reasoning effort
- low · medium · high · xhigh · max
- Discovery tier
- Frontier
Pricing
USD per 1M tokens- Input
- $2.00
- Output
- $10.00
- Cache read
- $0.20
- Cache write
- $2.50
Reference prices as published by the model provider. API example
Specifications
- Context window
- 1.1M
- Max output
- 128K
- Average output (7 days)
- 135 tokens
- Longer than 13% of 473 models
Side by side
GPT 6 Sol Pro compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| GPT 6 Sol ProOpenAIThis model | Claude Sonnet 5.5AnthropicRemove | |
|---|---|---|
| Provider | OpenAI | Anthropic |
| Discovery tier | Frontier | Frontier |
| Added | Sep 22, 2026 | Sep 28, 2026 |
| Limits | ||
| Context window | 1.05MBest | 1M |
| Max output | 128K | 128K |
| Average output | 135 tokens | 523 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $2.00 | $2.00 |
| Output | $10.00 | $10.00 |
| Cache read | $0.20 | $0.10Best |
| Cache write | $2.50 | $2.50 |
| Performance | ||
| Throughput | — | 269.5 tok/s |
| Time to first token | — | 4.9 s |
| Request success (24h) | — | 99.8% |
| Benchmark indexes | ||
| Intelligence Index | — | 46.8 |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Vision | Yes | Yes |
| Structured output | Yes | Yes |
| PDF input | Yes | Yes |
| Reasoning effort | low, medium, high, xhigh, max | low, medium, high |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- GPT 6 Sol Pro
- Claude Sonnet 5.5
Intelligence Index
- GPT 6 Sol Pro—
- Claude Sonnet 5.546.8
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- GPT 6 Sol Pro: —
- Claude Sonnet 5.5: 59.4%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- GPT 6 Sol Pro: —
- Claude Sonnet 5.5: 29.4%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- GPT 6 Sol Pro: —
- Claude Sonnet 5.5: 1,635 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- GPT 6 Sol Pro: —
- Claude Sonnet 5.5: 1,548 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- GPT 6 Sol Pro: —
- Claude Sonnet 5.5: 25.2%
AA-LCRv1.1
Reasoning across long documents
- GPT 6 Sol Pro: —
- Claude Sonnet 5.5: 78.0%
MLCR-AA
Long-context reasoning over medical records
- GPT 6 Sol Pro: —
- Claude Sonnet 5.5: 18.9%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- GPT 6 Sol Pro: —
- Claude Sonnet 5.5: 45.8%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- GPT 6 Sol Pro: —
- Claude Sonnet 5.5: 43.9%
SciCode
Scientific computing in Python
- GPT 6 Sol Pro: —
- Claude Sonnet 5.5: 53.7%
Legacy evaluations
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- GPT 6 Sol Pro: —
- Claude Sonnet 5.5: 78.0%
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
- GPT 6 Sol Pro
- Claude Sonnet 5.5
| Leaderboard | GPT 6 Sol Pro | Claude Sonnet 5.5 |
|---|---|---|
| Combined | Not in top 20 | #7 · 21.7% |
Ranks among Noumen catalog models on Combined leaderboards. Only top-20 placements are listed.
- GPT 6 Sol Pro
- Claude Sonnet 5.5
| Leaderboard | GPT 6 Sol Pro | Claude Sonnet 5.5 |
|---|---|---|
| FrontierCode Main | Not in top 20 | #5 · 52.1% |
| FrontierCode Extended | Not in top 20 | #4 · 64.4% |
Ranks among Noumen catalog models on FrontierCode leaderboards. Only top-20 placements are listed.FrontierCode
- GPT 6 Sol Pro
- Claude Sonnet 5.5
| Leaderboard | GPT 6 Sol Pro | Claude Sonnet 5.5 |
|---|---|---|
| Epoch Capabilities Index | Not in top 20 | #6 · 166.2 |
Ranks among Noumen catalog models on Epoch AI leaderboards. Only top-20 placements are listed.Epoch AI
- GPT 6 Sol Pro
- Claude Sonnet 5.5
| Leaderboard | GPT 6 Sol Pro | Claude Sonnet 5.5 |
|---|---|---|
| ARC-AGI-1 | Not in top 20 | #11 · 96.5% |
Ranks among Noumen catalog models on ARC Prize leaderboards. Only top-20 placements are listed.ARC Prize
- GPT 6 Sol Pro
- Claude Sonnet 5.5
| Leaderboard | GPT 6 Sol Pro | Claude Sonnet 5.5 |
|---|---|---|
| Game Development | Not in top 20 | #3 · 1415 |
| Website | Not in top 20 | #7 · 1322 |
| UI Component | Not in top 20 | #5 · 1372 |
| Data Visualization | Not in top 20 | #2 · 1387 |
| 3D | Not in top 20 | #6 · 1399 |
| Web Apps | Not in top 20 | #5 · 1305 |
| Mobile Apps | Not in top 20 | #3 · 1280 |
Ranks among Noumen catalog models on Design Arena leaderboards. Only top-20 placements are listed.Design Arena
- GPT 6 Sol Pro
- Claude Sonnet 5.5
| Leaderboard | GPT 6 Sol Pro | Claude Sonnet 5.5 |
|---|---|---|
| Usage Share | Not in top 20 | #10 · 2.1% |
Ranks among Noumen catalog models on Usage leaderboards. Only top-20 placements are listed.
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-6-sol-pro",
"reasoning_effort": "medium",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="openai/gpt-6-sol-pro",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)OpenAI
Related models
Other OpenAI models, starting with the same family.