OpenAI, proprietary
GPT-6.1 Sol
GPT-6.1 Sol by OpenAI ranks 6th of 354 ranked models on the Noometry Index as of October 2026, with a score of 65.6. Its strongest category is math, where it ranks 1st. API pricing starts at $2 per million input tokens and $10 per million output tokens, with a 1.05M-token context window.
Last verified
Specifications
- Noometry rank
- #6 of 354
- Index score
- 65.6
- Evidence
- Confirmed 34 results
- Provider
- OpenAI
- Released
- September 29, 2026
- Weights
- Proprietary
- Reasoning
- Yes
- Context window
- 1.05M
- Max output
- 128K
- Input price
- $2 / M
- Output price
- $10 / M
- Blended price
- $4 / M
- Output speed
- Not measured
- Value
- #160 of 219
- Knowledge cutoff
- April 2026
- Input
- text, image, pdf
Category scores
Each category score combines every public result we have in that category.
- Coding 63.2
- Agentic & Tool Use 39.6
- Reasoning 81.9
- Math 93.7
- Knowledge 71.8
- Multimodal 52.7
- Multilingual 54.3
- Instruction Following 77.0
- Long Context 44.9
- Writing & Preference 63.6
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 63.2 | #8 | 5 |
| Agentic & Tool Use | 39.6 | #26 | 2 |
| Reasoning | 81.9 | #2 | 8 |
| Math | 93.7 | #1 | 5 |
| Knowledge | 71.8 | #4 | 3 |
| Multimodal | 52.7 | #5 | 2 |
| Multilingual | 54.3 | #46 | 1 |
| Instruction Following | 77.0 | #29 | 1 |
| Long Context | 44.9 | #54 | 1 |
| Writing & Preference | 63.6 | #63 | 3 |
Strengths and weaknesses
Categories where GPT-6.1 Sol places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Writing & Preference | 63.6 | +9.8 | #63 of 312, top 21% |
| Long Context | 44.9 | +3.9 | #54 of 296, top 19% |
| Agentic & Tool Use | 39.6 | +9.3 | #26 of 154, top 17% |
Closest competitors
The models ranked just above and below GPT-6.1 Sol. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Claude Fable 5.1 | #2 | 69.0 | $20 | — | Compare |
| Claude Opus 5.5 | #3 | 68.6 | $8 | — | Compare |
| Claude Opus 5 | #4 | 67.8 | $10 | — | Compare |
| Claude Fable 5 | #5 | 66.8 | $20 | 25 | Compare |
| GPT-5.6 Sol | #7 | 65.0 | $8 | 10 | Compare |
| GPT-5.5 Pro | #8 | 64.3 | $67.50 | — | Compare |
| GPT-5.5 | #9 | 63.4 | $11.25 | 25 | Compare |
| Claude Sonnet 5.5 | #10 | 61.9 | $4 | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| DeepSWE | 75.2% | Best of 29 | high | Model card (self-reported) | 2026-09-29 |
| DeepSWE | 64.4% | low | Model card (self-reported) | 2026-09-29 | |
| DeepSWE | 71.9% | max | Model card (self-reported) | 2026-09-29 | |
| DeepSWE | 73% | medium | Model card (self-reported) | 2026-09-29 | |
| DeepSWE | 71.9% | xhigh | Model card (self-reported) | 2026-09-29 | |
| FrontierCode | 50.2% | #7 of 37, top 19% | medium | Epoch AI | |
| LMArena WebDev | 1755 | #4 of 113, top 4% | LMArena | 2026-10-08 | |
| SciCode | 55.8% | #24 of 121, top 20% | high | Epoch AI | |
| SciCode | 53.2% | low | Epoch AI | ||
| SciCode | 54.2% | max | Epoch AI | ||
| SciCode | 53.2% | medium | Epoch AI | ||
| SciCode | 55.7% | xhigh | Epoch AI | ||
| LMArena Coding | 1487 | #36 of 294, top 13% | LMArena | 2026-10-08 |
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| APEX-Agents | 60% | #12 of 49, top 25% | max | Epoch AI | |
| GDP.pdf | 32% | #2 of 36, top 6% | high | Model card (self-reported) | 2026-09-29 |
| GDP.pdf | 27% | low | Model card (self-reported) | 2026-09-29 | |
| GDP.pdf | 31% | max | Model card (self-reported) | 2026-09-29 | |
| GDP.pdf | 30% | medium | Model card (self-reported) | 2026-09-29 | |
| GDP.pdf | 31.8% | xhigh | Model card (self-reported) | 2026-09-29 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| ARC-AGI-2 | 91.7% | high | Epoch AI | ||
| ARC-AGI-2 | 76.7% | low | Epoch AI | ||
| ARC-AGI-2 | 94.2% | #2 of 83, top 3% | max | Epoch AI | |
| ARC-AGI-2 | 86.7% | medium | Epoch AI | ||
| ARC-AGI-2 | 91.7% | xhigh | Epoch AI | ||
| NYT Connections (extended) | 95.5% | #5 of 91, top 6% | high reasoning | Lech Mazur benchmarks | |
| ARC-AGI-1 | 98.5% | #4 of 83, top 5% | high | Epoch AI | |
| ARC-AGI-1 | 93.5% | low | Epoch AI | ||
| ARC-AGI-1 | 96.5% | max | Epoch AI | ||
| ARC-AGI-1 | 95.5% | medium | Epoch AI | ||
| ARC-AGI-1 | 98.5% | xhigh | Epoch AI | ||
| CritPt | 30% | high | Epoch AI | ||
| CritPt | 24.9% | low | Epoch AI | ||
| CritPt | 31.7% | #3 of 134, top 3% | max | Epoch AI | |
| CritPt | 27.7% | medium | Epoch AI | ||
| CritPt | 31.7% | xhigh | Epoch AI | ||
| Chess Puzzles | 61% | #5 of 129, top 4% | max | Epoch AI | 2026-09-29 |
| EBR-Bench | 54.3% | #4 of 24, top 17% | max | Epoch AI | 2026-09-29 |
| LMArena Hard Prompts | 1466 | #40 of 297, top 14% | LMArena | 2026-10-08 | |
| Mystery Game Puzzles | 80% | #2 of 74, top 3% | max | Epoch AI | 2026-09-29 |
| Epoch Capabilities Index | 166.09 | #3 of 213, top 2% | Epoch AI | 2026-09-29 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| FrontierMath (Tiers 1-3) | 93.7% | Best of 81 | max | Epoch AI | 2026-09-29 |
| FrontierMath Tier 4 | 100% | Best of 63 | max | Epoch AI | 2026-09-29 |
| OTIS Mock AIME 2024-2025 | 100% | #8 of 173, top 5% | max | Epoch AI | 2026-09-29 |
| ProofBench | 99% | #6 of 77, top 8% | Epoch AI | ||
| LMArena Math | 1464 | #49 of 285, top 18% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 95.4% | #4 of 186, top 3% | max | Epoch AI | 2026-09-29 |
| SimpleQA Verified | 73.9% | #2 of 77, top 3% | max | Epoch AI | 2026-09-29 |
| LMArena Expert | 1502 | #24 of 273, top 9% | LMArena | 2026-10-08 |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Vision | 1288 | #23 of 122, top 19% | LMArena | 2026-10-09 | |
| Furniture Assembly | 80% | #2 of 31, top 7% | max | Epoch AI | 2026-09-29 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1438 | #46 of 297, top 16% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1477 | #68 of 285, top 24% | LMArena | 2026-10-08 | |
| LMArena Russian | 1455 | #38 of 283, top 14% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1468 | #25 of 298, top 9% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1465 | #36 of 291, top 13% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1447 | #50 of 297, top 17% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1432 | #48 of 295, top 17% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1449 | #56 of 295, top 19% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| azure | $2 | $10 | $0.10 | 2026-10-10 |
| bedrock | $2 | $10 | $0.10 | 2026-10-10 |
| openai | $2 | $10 | $0.10 | 2026-10-10 |
| openrouter | $2 | $10 | $0.10 | 2026-10-10 |
Compare GPT-6.1 Sol
- GPT-6.1 Sol vs GPT-6 Sol
- GPT-6.1 Sol vs Claude Fable 5
- GPT-6.1 Sol vs GPT-5.6 Sol
- GPT-6.1 Sol vs Claude Opus 5
- GPT-6.1 Sol vs GPT-5.5 Pro
- GPT-6.1 Sol vs Claude Opus 5.5
- GPT-6.1 Sol vs GPT-5.5
- GPT-6.1 Sol vs Claude Fable 5.1
- GPT-6.1 Sol vs Gemini 3.8 Flash
- GPT-6.1 Sol vs Kimi K3
- GPT-6.1 Sol vs Grok 4.6
- GPT-6.1 Sol vs Qwen3.8 Max
- GPT-6.1 Sol vs GLM-5.3
- GPT-6.1 Sol vs Muse Spark 1.3
Other OpenAI models
- GPT-6 Astra70.8
- GPT-5.6 Sol65.0
- GPT-5.5 Pro64.3
- GPT-5.563.4
- GPT-6 Sol61.8
- GPT-5.459.4
- GPT-5.6 Terra59.2
- GPT-5.4 Pro58.9
Frequently asked questions
How good is GPT-6.1 Sol?
GPT-6.1 Sol by OpenAI ranks 6th of 354 ranked models on the Noometry Index as of October 2026, with a score of 65.6. Its strongest category is math, where it ranks 1st. API pricing starts at $2 per million input tokens and $10 per million output tokens, with a 1.05M-token context window.
How much does GPT-6.1 Sol cost?
GPT-6.1 Sol costs $2 per million input tokens and $10 per million output tokens on OpenAI's own API, with cached input at $0.10.
What is GPT-6.1 Sol's context window?
GPT-6.1 Sol accepts up to 1.05M tokens of input and can write up to 128K tokens in one response.
Is GPT-6.1 Sol open source?
No. GPT-6.1 Sol is proprietary and available only through OpenAI's API and partner platforms.
What are GPT-6.1 Sol's strengths and weaknesses?
Relative to other ranked models, GPT-6.1 Sol places best in math, reasoning, knowledge and lowest in writing & preference, long context, agentic & tool use.
What is GPT-6.1 Sol best at?
Its best category is math, where it ranks 1st on Noometry.