OpenAI, proprietary
GPT-5.4 Pro
GPT-5.4 Pro by OpenAI ranks 18th of 354 ranked models on the Noometry Index as of October 2026, with a score of 58.9. Its strongest category is knowledge, where it ranks 7th. API pricing starts at $30 per million input tokens and $180 per million output tokens, with a 1.05M-token context window.
Last verified
Specifications
- Noometry rank
- #18 of 354
- Index score
- 58.9
- Evidence
- Confirmed 16 results
- Provider
- OpenAI
- Released
- March 5, 2026
- Weights
- Proprietary
- Reasoning
- Yes
- Context window
- 1.05M
- Max output
- 128K
- Input price
- $30 / M
- Output price
- $180 / M
- Blended price
- $67.50 / M
- Output speed
- Not measured
- Value
- #217 of 219
- Knowledge cutoff
- August 2025
- Input
- text, image
Category scores
Each category score combines every public result we have in that category.
- Coding 43.2
- Reasoning 70.7
- Math 72.4
- Knowledge 68.3
Strengths and weaknesses
Categories where GPT-5.4 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-5.4 Pro. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Gemini 3.7 Flash | #14 | 59.8 | $1.50 | — | Compare |
| Kimi K3 | #15 | 59.5 | $6 | — | Compare |
| GPT-5.4 | #16 | 59.4 | $5.63 | 12 | Compare |
| GPT-5.6 Terra | #17 | 59.2 | $4.50 | 11 | Compare |
| Claude Opus 4.7 | #19 | 58.3 | $10 | 33 | Compare |
| Claude Opus 4.6 | #20 | 58.2 | $10 | 19 | Compare |
| Grok 4.6 | #21 | 56.9 | $3 | — | Compare |
| Qwen3.8 Max | #22 | 56.8 | $3 | — | 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 | 57.4% | #35 of 119, top 30% | none | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| ARC-AGI-2 | 83.3% | #15 of 83, top 19% | xhigh | Epoch AI | |
| SimpleBench | 74.1% | #9 of 77, top 12% | Epoch AI | ||
| ARC-AGI-1 | 94.5% | #16 of 83, top 20% | xhigh | Epoch AI | |
| CritPt | 30% | #9 of 134, top 7% | xhigh | Epoch AI | |
| Chess Puzzles | 58.6% | #6 of 129, top 5% | xhigh | Epoch AI | 2026-03-19 |
| EnigmaEval | 23.8% | #5 of 38, top 14% | Epoch AI | ||
| Epoch Capabilities Index | 158.93 | #13 of 213, top 7% | Epoch AI | 2026-03-05 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | #13 of 81, top 17% | xhigh | Epoch AI | 2026-06-13 |
| FrontierMath Tier 4 | 58.5% | #15 of 63, top 24% | xhigh | Epoch AI | 2026-06-13 |
| FrontierMath (Feb 2025 set) | 50% | #3 of 68, top 5% | xhigh | Epoch AI | 2026-03-06 |
| FrontierMath Tier 4 (v1) | 37.5% | #3 of 55, top 6% | Epoch AI | 2026-03-06 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 94.6% | #6 of 186, top 4% | xhigh | Epoch AI | 2026-03-20 |
| Humanity's Last Exam | 44.3% | #5 of 41, top 13% | Epoch AI | ||
| SimpleQA Verified | 46.3% | #34 of 77, top 45% | xhigh | Epoch AI | 2026-08-27 |
| Vectara Hallucination Rate (lower is better) | 8.3% | #38 of 96, top 40% | Vectara Hallucination Leaderboard |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| azure | $30 | $180 | — | 2026-10-10 |
| openai | $30 | $180 | — | 2026-10-10 |
| openrouter | $30 | $180 | — | 2026-10-10 |
Compare GPT-5.4 Pro
- GPT-5.4 Pro vs GPT-5.2 Pro
- GPT-5.4 Pro vs GPT-5.6 Terra
- GPT-5.4 Pro vs Claude Opus 4.7
- GPT-5.4 Pro vs GPT-5.4
- GPT-5.4 Pro vs Claude Opus 4.6
- GPT-5.4 Pro vs Kimi K3
- GPT-5.4 Pro vs Grok 4.6
- GPT-5.4 Pro vs Claude Fable 5.1
- GPT-5.4 Pro vs Gemini 3.8 Flash
- GPT-5.4 Pro vs Qwen3.8 Max
- GPT-5.4 Pro vs GLM-5.3
- GPT-5.4 Pro vs Muse Spark 1.3
- GPT-5.4 Pro vs DeepSeek V4 Pro
- GPT-5.4 Pro vs MiMo-V2.6-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-5.4 Pro?
GPT-5.4 Pro by OpenAI ranks 18th of 354 ranked models on the Noometry Index as of October 2026, with a score of 58.9. Its strongest category is knowledge, where it ranks 7th. API pricing starts at $30 per million input tokens and $180 per million output tokens, with a 1.05M-token context window.
How much does GPT-5.4 Pro cost?
GPT-5.4 Pro costs $30 per million input tokens and $180 per million output tokens on OpenAI's own API.
What is GPT-5.4 Pro's context window?
GPT-5.4 Pro accepts up to 1.05M tokens of input and can write up to 128K tokens in one response.
Is GPT-5.4 Pro open source?
No. GPT-5.4 Pro is proprietary and available only through OpenAI's API and partner platforms.
What are GPT-5.4 Pro's strengths and weaknesses?
Relative to other ranked models, GPT-5.4 Pro places best in knowledge, reasoning and lowest in coding, math.
What is GPT-5.4 Pro best at?
Its best category is knowledge, where it ranks 7th on Noometry.