OpenAI, proprietary

# GPT-4.5

> GPT-4.5 by OpenAI, released February 2025. Ranked #208 of 354 with a Noometry Index of 37.2. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/gpt-4-5
- Last updated: 2026-10-10
- Title: GPT-4.5 Benchmarks, Price & Rank (October 2026) | Noometry

GPT-4.5 by OpenAI ranks 208th of 354 ranked models on the Noometry Index as of October 2026, with a score of 37.2. Its strongest category is multimodal, where it ranks 71st.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #208 of 354
- **Index score:** 37.2
- **Evidence:** Confirmed 42 results
- **Provider:** [OpenAI](https://noometry.com/providers/openai)
- **Released:** February 27, 2025
- **Weights:** Proprietary
- **Reasoning:** Unknown
- **Context window:** —
- **Max output:** —
- **Input price:** Not listed
- **Output price:** Not listed
- **Blended price:** Not listed
- **Output speed:** Not measured
- **Value:** Not ranked
- **Knowledge cutoff:** Unknown

## Category scores

Each category score combines every public result we have in that category.

GPT-4.5 category scores

1.  Coding 42.2
2.  Agentic & Tool Use 27.9
3.  Reasoning 13.9
4.  Math 32.6
5.  Knowledge 32.5
6.  Multimodal 37.6
7.  Multilingual 52.5
8.  Instruction Following 72.6
9.  Long Context 40.4
10.  Writing & Preference 56.9
11.  020406080

GPT-4.5 category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 42.2 | #109 | 4 |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 27.9 | #97 | 1 |
| [Reasoning](https://noometry.com/best/reasoning) | 13.9 | #330 | 7 |
| [Math](https://noometry.com/best/math) | 32.6 | #211 | 4 |
| [Knowledge](https://noometry.com/best/knowledge) | 32.5 | #211 | 4 |
| [Multimodal](https://noometry.com/best/multimodal) | 37.6 | #71 | 2 |
| [Multilingual](https://noometry.com/best/multilingual) | 52.5 | #83 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 72.6 | #134 | 2 |
| [Long Context](https://noometry.com/best/long-context) | 40.4 | #155 | 2 |
| [Writing & Preference](https://noometry.com/best/writing) | 56.9 | #134 | 6 |

## Strengths and weaknesses

Categories where GPT-4.5 places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

GPT-4.5: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Multilingual](https://noometry.com/best/multilingual) | 52.5 | +5.1 | #83 of 297, top 28% |
| [Coding](https://noometry.com/best/coding) | 42.2 | +3.5 | #109 of 340, top 33% |
| [Writing & Preference](https://noometry.com/best/writing) | 56.9 | +3.1 | #134 of 312, top 43% |

### Weakest categories

GPT-4.5: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 13.9 | −9.7 | #330 of 350, top 95% |
| [Knowledge](https://noometry.com/best/knowledge) | 32.5 | −4.8 | #211 of 314, top 68% |
| [Math](https://noometry.com/best/math) | 32.6 | −3.9 | #211 of 327, top 65% |

## Closest competitors

The models ranked just above and below GPT-4.5. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to GPT-4.5
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [MiniMax-M2](https://noometry.com/models/minimax-m2) | #204 | 37.4 | $0.52 | 17 | [Compare](https://noometry.com/compare/gpt-4-5-vs-minimax-m2) |
| [Granite 4.1 8b](https://noometry.com/models/granite-4-1-8b) | #205 | 37.4 | — | — | [Compare](https://noometry.com/compare/gpt-4-5-vs-granite-4-1-8b) |
| [Gemma 3n E4b IT](https://noometry.com/models/gemma-3n-e4b-it) | #206 | 37.3 | — | 13 | [Compare](https://noometry.com/compare/gemma-3n-e4b-it-vs-gpt-4-5) |
| [Step 3.7 Flash](https://noometry.com/models/step-3-7-flash) | #207 | 37.3 | $0.42 | — | [Compare](https://noometry.com/compare/gpt-4-5-vs-step-3-7-flash) |
| [Yi-Lightning](https://noometry.com/models/yi-lightning) | #209 | 37.1 | — | — | [Compare](https://noometry.com/compare/gpt-4-5-vs-yi-lightning) |
| [Qwen Plus](https://noometry.com/models/qwen-plus) | #210 | 37.1 | $0.60 | 37 | [Compare](https://noometry.com/compare/gpt-4-5-vs-qwen-plus) |
| [Gemini 2.5 Flash-Lite](https://noometry.com/models/gemini-2-5-flash-lite) | #211 | 37.0 | $0.18 | 172 | [Compare](https://noometry.com/compare/gemini-2-5-flash-lite-vs-gpt-4-5) |
| [o3-mini](https://noometry.com/models/o3-mini) | #212 | 36.7 | $1.93 | — | [Compare](https://noometry.com/compare/gpt-4-5-vs-o3-mini) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## 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

GPT-4.5 Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 44.9% | #25 of 44, top 57% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 39.4% | #80 of 119, top 68% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench Coding](https://noometry.com/benchmarks/livebench-coding) | 75.2% | #3 of 39, top 8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1396 | #139 of 294, top 48% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Agentic & Tool Use

GPT-4.5 Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Cybench](https://noometry.com/benchmarks/cybench) | 17.5% | #13 of 21, top 62% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Reasoning

GPT-4.5 Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 0.8% | #72 of 83, top 87% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SimpleBench](https://noometry.com/benchmarks/simplebench) | 34.5% | #58 of 77, top 76% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 10.3% | #74 of 83, top 90% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [EnigmaEval](https://noometry.com/benchmarks/enigmaeval) | 3.2% | #26 of 38, top 69% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench Reasoning](https://noometry.com/benchmarks/livebench-reasoning) | 71.1% | #10 of 39, top 26% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1403 | #122 of 297, top 42% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LiveBench Data Analysis](https://noometry.com/benchmarks/livebench-data-analysis) | 64.3% | #12 of 39, top 31% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 136.74 | #120 of 213, top 57% |  | [Epoch AI](https://epoch.ai/eci) | 2025-02-27 |
| [ForecastBench](https://noometry.com/benchmarks/forecastbench) | 61.7 | #7 of 72, top 10% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench](https://noometry.com/benchmarks/livebench) | 69% | #8 of 39, top 21% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Math

GPT-4.5 Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 37.8% | #118 of 173, top 69% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-02-28 |
| [LiveBench Math](https://noometry.com/benchmarks/livebench-math) | 69.3% | #11 of 39, top 29% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1412 | #112 of 285, top 40% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 78.6% | #26 of 79, top 33% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-02-28 |

### Knowledge

GPT-4.5 Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 68.7% | #100 of 186, top 54% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-02-28 |
| [Humanity's Last Exam](https://noometry.com/benchmarks/hle) | 5.4% | #34 of 41, top 83% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Confabulations](https://noometry.com/benchmarks/confabulations) (lower is better) | 13.6% | #13 of 51, top 26% |  | [Lech Mazur benchmarks](https://github.com/lechmazur/confabulations) |  |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1394 | #130 of 273, top 48% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multimodal

GPT-4.5 Multimodal benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Vision](https://noometry.com/benchmarks/arena-vision) | 1195 | #81 of 122, top 67% |  | [LMArena](https://lmarena.ai/leaderboard/vision) | 2026-10-09 |
| [VPCT](https://noometry.com/benchmarks/vpct) | 45% | #10 of 24, top 42% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Multilingual

GPT-4.5 Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1413 | #83 of 297, top 28% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1421 | #127 of 285, top 45% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1418 | #101 of 223, top 46% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1457 | #38 of 231, top 17% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1416 | #44 of 211, top 21% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1392 | #65 of 213, top 31% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1419 | #82 of 283, top 29% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

GPT-4.5 Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LiveBench Instruction Following](https://noometry.com/benchmarks/livebench-if) | 72.3% | #16 of 39, top 42% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1404 | #100 of 298, top 34% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

GPT-4.5 Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Fiction.LiveBench](https://noometry.com/benchmarks/fiction-livebench) | 63.9% | #25 of 47, top 54% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1406 | #112 of 291, top 39% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

GPT-4.5 Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1417 | #99 of 297, top 34% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1394 | #89 of 295, top 31% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Short-Story Creative Writing](https://noometry.com/benchmarks/lech-mazur-writing) | 75.6% | #23 of 39, top 59% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) | 1258 | #82 of 115, top 72% |  | [EQ-Bench](https://eqbench.com/creative_writing.html) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1444 | #68 of 295, top 24% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LiveBench Language](https://noometry.com/benchmarks/livebench-language) | 61.5% | #4 of 39, top 11% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

## Compare GPT-4.5

-   [GPT-4.5 vs GPT-4o](https://noometry.com/compare/gpt-4-5-vs-gpt-4o)
-   [GPT-4.5 vs Step 3.7 Flash](https://noometry.com/compare/gpt-4-5-vs-step-3-7-flash)
-   [GPT-4.5 vs Yi-Lightning](https://noometry.com/compare/gpt-4-5-vs-yi-lightning)
-   [GPT-4.5 vs Gemma 3n E4b IT](https://noometry.com/compare/gemma-3n-e4b-it-vs-gpt-4-5)
-   [GPT-4.5 vs Qwen Plus](https://noometry.com/compare/gpt-4-5-vs-qwen-plus)
-   [GPT-4.5 vs Granite 4.1 8b](https://noometry.com/compare/gpt-4-5-vs-granite-4-1-8b)
-   [GPT-4.5 vs Gemini 2.5 Flash-Lite](https://noometry.com/compare/gemini-2-5-flash-lite-vs-gpt-4-5)
-   [GPT-4.5 vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-gpt-4-5)
-   [GPT-4.5 vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-gpt-4-5)
-   [GPT-4.5 vs Kimi K3](https://noometry.com/compare/gpt-4-5-vs-kimi-k3)
-   [GPT-4.5 vs Grok 4.6](https://noometry.com/compare/gpt-4-5-vs-grok-4-6)
-   [GPT-4.5 vs Qwen3.8 Max](https://noometry.com/compare/gpt-4-5-vs-qwen3-8-max)
-   [GPT-4.5 vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-gpt-4-5)
-   [GPT-4.5 vs Muse Spark 1.3](https://noometry.com/compare/gpt-4-5-vs-muse-spark-1-3)

## Other OpenAI models

-   [GPT-6 Astra](https://noometry.com/models/gpt-6-astra)70.8
-   [GPT-6.1 Sol](https://noometry.com/models/gpt-6-1-sol)65.6
-   [GPT-5.6 Sol](https://noometry.com/models/gpt-5-6-sol)65.0
-   [GPT-5.5 Pro](https://noometry.com/models/gpt-5-5-pro)64.3
-   [GPT-5.5](https://noometry.com/models/gpt-5-5)63.4
-   [GPT-6 Sol](https://noometry.com/models/gpt-6-sol)61.8
-   [GPT-5.4](https://noometry.com/models/gpt-5-4)59.4
-   [GPT-5.6 Terra](https://noometry.com/models/gpt-5-6-terra)59.2

## Frequently asked questions

### How good is GPT-4.5?

GPT-4.5 by OpenAI ranks 208th of 354 ranked models on the Noometry Index as of October 2026, with a score of 37.2. Its strongest category is multimodal, where it ranks 71st.

### Is GPT-4.5 open source?

No. GPT-4.5 is proprietary and available only through OpenAI's API and partner platforms.

### What are GPT-4.5's strengths and weaknesses?

Relative to other ranked models, GPT-4.5 places best in multilingual, coding, writing & preference and lowest in reasoning, knowledge, math.

### What is GPT-4.5 best at?

Its best category is multimodal, where it ranks 71st on Noometry.

### Cite this page

Noometry. (2026). GPT-4.5 benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/gpt-4-5

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/gpt-4-5.md).