OpenAI, proprietary
GPT-5 Pro
GPT-5 Pro by OpenAI ranks 64th of 354 ranked models on the Noometry Index as of October 2026, with a score of 46.4. Its strongest category is knowledge, where it ranks 42nd. API pricing starts at $15 per million input tokens and $120 per million output tokens, with a 400K-token context window.
Last verified
Specifications
- Noometry rank
- #64 of 354
- Index score
- 46.4
- Evidence
- Confirmed 12 results
- Provider
- OpenAI
- Released
- October 6, 2025
- Weights
- Proprietary
- Reasoning
- Yes
- Context window
- 400K
- Max output
- 272K
- Input price
- $15 / M
- Output price
- $120 / M
- Blended price
- $41.25 / M
- Output speed
- 5 tokens/s Kagi
- Value
- #214 of 219
- Knowledge cutoff
- September 2024
- Input
- text, image
Category scores
Each category score combines every public result we have in that category.
- Coding 44.0
- Reasoning 38.9
- Math 48.5
- Knowledge 56.7
Strengths and weaknesses
Categories where GPT-5 Pro places highest and lowest among the models ranked in each, with its score against that category's median.
Closest competitors
The models ranked just above and below GPT-5 Pro. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Kimi K2.6 | #60 | 47.7 | $1.71 | — | Compare |
| o3 | #61 | 47.5 | $3.50 | 3 | Compare |
| Qwen3.6 Plus | #62 | 47.5 | $1.13 | — | Compare |
| Inkling-Small | #63 | 46.5 | $0.64 | — | Compare |
| Grok 4.20 Multi-Agent | #65 | 46.2 | $1.56 | — | Compare |
| GLM-5 | #66 | 46.1 | $1.55 | 23 | Compare |
| Qwen3.5 397B-A17B | #67 | 46.0 | $1.35 | 9 | Compare |
| Qwen3.8 27B | #68 | 46.0 | $1.11 | — | 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 |
|---|---|---|---|---|---|
| WeirdML | 60.4% | #31 of 119, top 27% | high | Epoch AI | |
| AlgoTune | 1.31 | #18 of 18, top 100% | medium | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| ARC-AGI-2 | 18.3% | #43 of 83, top 52% | Epoch AI | ||
| SimpleBench | 61.6% | #20 of 77, top 26% | Epoch AI | ||
| SimpleBench | 61.6% | high | Epoch AI | ||
| Kagi LLM Benchmark | 76.8% | #10 of 99, top 11% | Kagi LLM Benchmark | ||
| ARC-AGI-1 | 70.2% | Epoch AI | |||
| ARC-AGI-1 | 70.2% | #43 of 83, top 52% | high | Epoch AI | |
| EnigmaEval | 18.8% | #7 of 38, top 19% | Epoch AI | ||
| Epoch Capabilities Index | 150.28 | #50 of 213, top 24% | Epoch AI | 2025-10-07 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | #42 of 81, top 52% | high | Epoch AI | 2026-06-12 |
| FrontierMath Tier 4 | 19.5% | #43 of 63, top 69% | high | Epoch AI | 2026-06-12 |
| FrontierMath Tier 4 (v1) | 14.6% | #13 of 55, top 24% | high | Epoch AI | 2025-10-09 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Humanity's Last Exam | 31.6% | #11 of 41, top 27% | Epoch AI |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| azure | $15 | $120 | — | 2026-10-10 |
| openai | $15 | $120 | — | 2026-10-10 |
| openrouter | $15 | $120 | — | 2026-10-10 |
Compare GPT-5 Pro
- GPT-5 Pro vs Inkling-Small
- GPT-5 Pro vs Grok 4.20 Multi-Agent
- GPT-5 Pro vs Qwen3.6 Plus
- GPT-5 Pro vs GLM-5
- GPT-5 Pro vs o3
- GPT-5 Pro vs Qwen3.5 397B-A17B
- GPT-5 Pro vs Claude Fable 5.1
- GPT-5 Pro vs Gemini 3.8 Flash
- GPT-5 Pro vs Kimi K3
- GPT-5 Pro vs Grok 4.6
- GPT-5 Pro vs Qwen3.8 Max
- GPT-5 Pro vs GLM-5.3
- GPT-5 Pro vs Muse Spark 1.3
- GPT-5 Pro vs DeepSeek V4 Pro
Other OpenAI models
- GPT-6 Astra70.8
- GPT-6.1 Sol65.6
- 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
Frequently asked questions
How good is GPT-5 Pro?
GPT-5 Pro by OpenAI ranks 64th of 354 ranked models on the Noometry Index as of October 2026, with a score of 46.4. Its strongest category is knowledge, where it ranks 42nd. API pricing starts at $15 per million input tokens and $120 per million output tokens, with a 400K-token context window.
How much does GPT-5 Pro cost?
GPT-5 Pro costs $15 per million input tokens and $120 per million output tokens on OpenAI's own API.
What is GPT-5 Pro's context window?
GPT-5 Pro accepts up to 400K tokens of input and can write up to 272K tokens in one response.
Is GPT-5 Pro open source?
No. GPT-5 Pro is proprietary and available only through OpenAI's API and partner platforms.
How fast is GPT-5 Pro?
GPT-5 Pro generated about 5 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.
What are GPT-5 Pro's strengths and weaknesses?
Relative to other ranked models, GPT-5 Pro places best in knowledge, reasoning and lowest in coding, math.
What is GPT-5 Pro best at?
Its best category is knowledge, where it ranks 42nd on Noometry.