OpenAI, proprietary

# GPT-4o

> GPT-4o by OpenAI, released May 2024. Ranked #324 of 354 with a Noometry Index of 28.6. API: $2.50 in / $10 out per M tokens. 128K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/gpt-4o
- Last updated: 2026-10-10
- Title: GPT-4o Benchmarks, Price & Rank (October 2026) | Noometry

GPT-4o by OpenAI ranks 324th of 354 ranked models on the Noometry Index as of October 2026, with a score of 28.6. Its strongest category is multimodal, where it ranks 91st. API pricing starts at $2.50 per million input tokens and $10 per million output tokens, with a 128K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #324 of 354
- **Index score:** 28.6
- **Evidence:** Confirmed 72 results
- **Provider:** [OpenAI](https://noometry.com/providers/openai)
- **Released:** May 13, 2024
- **Weights:** Proprietary
- **Reasoning:** No
- **Context window:** 128K
- **Max output:** 16K
- **Input price:** $2.50 / M
- **Output price:** $10 / M
- **Blended price:** $4.38 / M
- **Output speed:** Not measured
- **Value:** #200 of 219
- **Knowledge cutoff:** September 2023
- **Input:** text, image

## Category scores

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

GPT-4o category scores

1.  Coding 24.8
2.  Agentic & Tool Use 21.0
3.  Reasoning 9.4
4.  Math 10.6
5.  Knowledge 28.8
6.  Multimodal 34.5
7.  Multilingual 43.2
8.  Instruction Following 66.6
9.  Long Context 39.4
10.  Writing & Preference 52.6
11.  020406080

GPT-4o category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 24.8 | #328 | 10 |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 21.0 | #141 | 4 |
| [Reasoning](https://noometry.com/best/reasoning) | 9.4 | #343 | 11 |
| [Math](https://noometry.com/best/math) | 10.6 | #312 | 6 |
| [Knowledge](https://noometry.com/best/knowledge) | 28.8 | #242 | 8 |
| [Multimodal](https://noometry.com/best/multimodal) | 34.5 | #91 | 4 |
| [Multilingual](https://noometry.com/best/multilingual) | 43.2 | #186 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 66.6 | #207 | 3 |
| [Long Context](https://noometry.com/best/long-context) | 39.4 | #179 | 2 |
| [Writing & Preference](https://noometry.com/best/writing) | 52.6 | #166 | 6 |

## Strengths and weaknesses

Categories where GPT-4o places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

GPT-4o: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Writing & Preference](https://noometry.com/best/writing) | 52.6 | −1.2 | #166 of 312, top 54% |
| [Long Context](https://noometry.com/best/long-context) | 39.4 | −1.5 | #179 of 296, top 61% |
| [Multilingual](https://noometry.com/best/multilingual) | 43.2 | −4.2 | #186 of 297, top 63% |

### Weakest categories

GPT-4o: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 9.4 | −14.2 | #343 of 350, top 98% |
| [Coding](https://noometry.com/best/coding) | 24.8 | −13.9 | #328 of 340, top 97% |
| [Math](https://noometry.com/best/math) | 10.6 | −25.9 | #312 of 327, top 96% |

## Closest competitors

The models ranked just above and below GPT-4o. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to GPT-4o
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Qwen2.5 7B Instruct](https://noometry.com/models/qwen2-5-7b-instruct) | #320 | 29.0 | $0.31 | — | [Compare](https://noometry.com/compare/gpt-4o-vs-qwen2-5-7b-instruct) |
| [Llama 3.2 3B](https://noometry.com/models/llama-3-2-3b) | #321 | 28.9 | $0.12 | — | [Compare](https://noometry.com/compare/gpt-4o-vs-llama-3-2-3b) |
| [Qwen1.5 4b Chat](https://noometry.com/models/qwen1-5-4b-chat) | #322 | 28.8 | — | — | [Compare](https://noometry.com/compare/gpt-4o-vs-qwen1-5-4b-chat) |
| [Llama 3-70B](https://noometry.com/models/llama-3-70b) | #323 | 28.8 | — | 104 | [Compare](https://noometry.com/compare/gpt-4o-vs-llama-3-70b) |
| [Ministral 8B](https://noometry.com/models/ministral-8b) | #325 | 28.2 | $0.15 | — | [Compare](https://noometry.com/compare/gpt-4o-vs-ministral-8b) |
| [Gemma 3 4B](https://noometry.com/models/gemma-3-4b) | #326 | 28.1 | $0.05 | 72 | [Compare](https://noometry.com/compare/gemma-3-4b-vs-gpt-4o) |
| [GPT-4.1 nano](https://noometry.com/models/gpt-4-1-nano) | #327 | 27.9 | $0.18 | 135 | [Compare](https://noometry.com/compare/gpt-4-1-nano-vs-gpt-4o) |
| [Phi 3 Mini 4k Instruct](https://noometry.com/models/phi-3-mini-4k-instruct) | #328 | 27.9 | — | — | [Compare](https://noometry.com/compare/gpt-4o-vs-phi-3-mini-4k-instruct) |

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-4o Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [SWE-bench Verified](https://noometry.com/benchmarks/swe-bench-verified) | 31% | #32 of 32, top 100% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-02-11 |
| [SWE-bench Verified (bash only)](https://noometry.com/benchmarks/swe-bench-bash-only) | 21.6% | #35 of 39, top 90% |  | [SWE-bench](https://www.swebench.com/) | 2025-07-20 |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 45.3% | #24 of 44, top 55% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 27.1% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 18.2% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 23.1% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [GSO](https://noometry.com/benchmarks/gso-bench) | 0% | #31 of 31, top 100% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 25.1% | #99 of 119, top 84% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [BigCodeBench Instruct](https://noometry.com/benchmarks/bigcodebench-instruct) | 51.1% | Best of 64 |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-05-13 |
| [BigCodeBench Instruct](https://noometry.com/benchmarks/bigcodebench-instruct) | 48% |  |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-11-20 |
| [LiveBench Coding](https://noometry.com/benchmarks/livebench-coding) | 51.4% | #16 of 39, top 42% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench Coding](https://noometry.com/benchmarks/livebench-coding) | 46.1% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1297 | #199 of 294, top 68% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1283 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [BigCodeBench Complete](https://noometry.com/benchmarks/bigcodebench-complete) | 58.9% |  |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-11-20 |
| [BigCodeBench Complete](https://noometry.com/benchmarks/bigcodebench-complete) | 61.1% | #3 of 66, top 5% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-05-13 |
| [CadEval](https://noometry.com/benchmarks/cadeval) | 26% | #12 of 14, top 86% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [HumanEval+](https://noometry.com/benchmarks/humaneval-plus) | 87.2% | #3 of 45, top 7% | aug 2024 | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |
| [MBPP+](https://noometry.com/benchmarks/mbpp-plus) | 72.2% | #11 of 38, top 29% | aug 2024 | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |

### Agentic & Tool Use

GPT-4o Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GDPval](https://noometry.com/benchmarks/gdpval) | 9.9% | #11 of 11, top 100% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [TheAgentCompany](https://noometry.com/benchmarks/the-agent-company) | 8.6% | #8 of 14, top 58% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Cybench](https://noometry.com/benchmarks/cybench) | 12.5% | #14 of 21, top 67% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [BALROG](https://noometry.com/benchmarks/balrog) | 32.3% | #16 of 35, top 46% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Search](https://noometry.com/benchmarks/arena-search) | 1006 | #32 of 32, top 100% |  | [LMArena](https://lmarena.ai/leaderboard/search) | 2026-08-24 |
| [METR Time Horizons](https://noometry.com/benchmarks/metr-time-horizons) | 40.8% | #26 of 32, top 82% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Reasoning

GPT-4o Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 0% | #77 of 83, top 93% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SimpleBench](https://noometry.com/benchmarks/simplebench) | 17.8% | #75 of 77, top 98% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 4.5% | #79 of 83, top 96% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 0% | #112 of 134, top 84% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 13% | #73 of 129, top 57% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-15 |
| [EnigmaEval](https://noometry.com/benchmarks/enigmaeval) | 0.8% | #35 of 38, top 93% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench Reasoning](https://noometry.com/benchmarks/livebench-reasoning) | 53.9% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench Reasoning](https://noometry.com/benchmarks/livebench-reasoning) | 55.8% | #15 of 39, top 39% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1281 | #199 of 297, top 68% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1264 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 64.5% | #103 of 151, top 69% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench Data Analysis](https://noometry.com/benchmarks/livebench-data-analysis) | 60.9% | #14 of 39, top 36% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench Data Analysis](https://noometry.com/benchmarks/livebench-data-analysis) | 56.1% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 16.6% | #102 of 125, top 82% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 128.97 | #143 of 213, top 68% |  | [Epoch AI](https://epoch.ai/eci) | 2024-05-13 |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 128.76 |  |  | [Epoch AI](https://epoch.ai/eci) | 2024-08-06 |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 128.81 |  |  | [Epoch AI](https://epoch.ai/eci) | 2024-11-20 |
| [ForecastBench](https://noometry.com/benchmarks/forecastbench) | 57.7 | #54 of 72, top 75% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench](https://noometry.com/benchmarks/livebench) | 52.2% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench](https://noometry.com/benchmarks/livebench) | 55.3% | #15 of 39, top 39% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Math

GPT-4o Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [FrontierMath (Tiers 1-3)](https://noometry.com/benchmarks/frontiermath) | 0.4% | #80 of 81, top 99% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 6.3% |  |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-02-25 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 6.3% |  |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-02-25 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 6.4% | #144 of 173, top 84% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-02-25 |
| [Omni-MATH](https://noometry.com/benchmarks/omni-math) | 29.3% | #40 of 57, top 71% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LiveBench Math](https://noometry.com/benchmarks/livebench-math) | 42.9% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench Math](https://noometry.com/benchmarks/livebench-math) | 49.5% | #20 of 39, top 52% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1284 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1285 | #189 of 285, top 67% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 49.8% |  |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-02-05 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 53.3% | #43 of 79, top 55% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 51% |  |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |
| [FrontierMath (Feb 2025 set)](https://noometry.com/benchmarks/frontiermath-2025-02) | 0.3% | #65 of 68, top 96% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-03-07 |
| [FrontierMath (Feb 2025 set)](https://noometry.com/benchmarks/frontiermath-2025-02) | 0.3% |  |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-03-06 |

### Knowledge

GPT-4o Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 48.9% |  |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 47.9% |  |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-02-05 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 49.2% | #128 of 186, top 69% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |
| [Humanity's Last Exam](https://noometry.com/benchmarks/hle) | 2.7% | #41 of 41, top 100% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SimpleQA Verified](https://noometry.com/benchmarks/simpleqa-verified) | 26% | #60 of 77, top 78% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-31 |
| [MMLU-Pro](https://noometry.com/benchmarks/mmlu-pro) | 71.3% | #35 of 58, top 61% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [Confabulations](https://noometry.com/benchmarks/confabulations) (lower is better) | 15.3% | #18 of 51, top 36% |  | [Lech Mazur benchmarks](https://github.com/lechmazur/confabulations) |  |
| [Confabulations](https://noometry.com/benchmarks/confabulations) (lower is better) | 17.2% |  |  | [Lech Mazur benchmarks](https://github.com/lechmazur/confabulations) |  |
| [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination) (lower is better) | 9.6% | #51 of 96, top 54% |  | [Vectara Hallucination Leaderboard](https://github.com/vectara/hallucination-leaderboard) |  |
| [GPQA (HELM)](https://noometry.com/benchmarks/helm-gpqa) | 52% | #31 of 57, top 55% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1241 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1250 | #196 of 273, top 72% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MMLU](https://noometry.com/benchmarks/mmlu) | 88.1% | Best of 81 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [MMLU](https://noometry.com/benchmarks/mmlu) | 84.2% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [MMLU](https://noometry.com/benchmarks/mmlu) | 84.3% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Multimodal

GPT-4o Multimodal benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Vision](https://noometry.com/benchmarks/arena-vision) | 1137 | #102 of 122, top 84% |  | [LMArena](https://lmarena.ai/leaderboard/vision) | 2026-10-09 |
| [LMArena Vision](https://noometry.com/benchmarks/arena-vision) | 1065 |  |  | [LMArena](https://lmarena.ai/leaderboard/vision) | 2026-10-09 |
| [Video-MME](https://noometry.com/benchmarks/video-mme) | 71.9% | #6 of 15, top 40% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Video-MME](https://noometry.com/benchmarks/video-mme) | 71.9% | #6 of 15, top 40% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [GeoBench](https://noometry.com/benchmarks/geobench) | 71% | #12 of 25, top 48% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [VPCT](https://noometry.com/benchmarks/vpct) | 40% | #13 of 24, top 55% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ScienceQA](https://noometry.com/benchmarks/scienceqa) | 88.5% | Best of 6 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Multilingual

GPT-4o Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1262 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1283 | #186 of 297, top 63% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1254 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1277 | #193 of 285, top 68% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1304 | #160 of 223, top 72% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1263 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1257 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1282 | #157 of 231, top 68% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1234 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1257 | #138 of 211, top 66% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1218 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1234 | #150 of 213, top 71% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1272 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1286 | #186 of 283, top 66% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1292 | #163 of 226, top 73% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1269 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

GPT-4o Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LiveBench Instruction Following](https://noometry.com/benchmarks/livebench-if) | 64.9% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench Instruction Following](https://noometry.com/benchmarks/livebench-if) | 68.6% | #20 of 39, top 52% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [IFEval](https://noometry.com/benchmarks/ifeval) | 81.7% | #35 of 57, top 62% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1278 | #190 of 298, top 64% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1267 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

GPT-4o Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Fiction.LiveBench](https://noometry.com/benchmarks/fiction-livebench) | 66.7% | #19 of 47, top 41% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1289 | #198 of 291, top 69% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1283 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

GPT-4o Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1300 | #190 of 297, top 64% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1283 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1275 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1292 | #173 of 295, top 59% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Short-Story Creative Writing](https://noometry.com/benchmarks/lech-mazur-writing) | 81.8% | #11 of 39, top 29% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WildBench](https://noometry.com/benchmarks/wildbench) | 82.8% | #19 of 57, top 34% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1279 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1302 | #186 of 295, top 64% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LiveBench Language](https://noometry.com/benchmarks/livebench-language) | 47.4% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LiveBench Language](https://noometry.com/benchmarks/livebench-language) | 47.6% | #14 of 39, top 36% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

## API pricing by provider

GPT-4o API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [azure](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models) | $2.50 | $10 | $1.25 | 2026-10-10 |
| [openai](https://platform.openai.com/docs/models) | $2.50 | $10 | $1.25 | 2026-10-10 |
| [openrouter](https://openrouter.ai/openai/gpt-4o) | $2.50 | $10 | $1.25 | 2026-10-10 |

[All OpenAI API prices →](https://noometry.com/llm-pricing/openai) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare GPT-4o

-   [GPT-4o vs GPT-4](https://noometry.com/compare/gpt-4-vs-gpt-4o)
-   [GPT-4o vs Llama 3-70B](https://noometry.com/compare/gpt-4o-vs-llama-3-70b)
-   [GPT-4o vs Ministral 8B](https://noometry.com/compare/gpt-4o-vs-ministral-8b)
-   [GPT-4o vs Qwen1.5 4b Chat](https://noometry.com/compare/gpt-4o-vs-qwen1-5-4b-chat)
-   [GPT-4o vs Gemma 3 4B](https://noometry.com/compare/gemma-3-4b-vs-gpt-4o)
-   [GPT-4o vs Llama 3.2 3B](https://noometry.com/compare/gpt-4o-vs-llama-3-2-3b)
-   [GPT-4o vs GPT-4.1 nano](https://noometry.com/compare/gpt-4-1-nano-vs-gpt-4o)
-   [GPT-4o vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-gpt-4o)
-   [GPT-4o vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-gpt-4o)
-   [GPT-4o vs Kimi K3](https://noometry.com/compare/gpt-4o-vs-kimi-k3)
-   [GPT-4o vs Grok 4.6](https://noometry.com/compare/gpt-4o-vs-grok-4-6)
-   [GPT-4o vs Qwen3.8 Max](https://noometry.com/compare/gpt-4o-vs-qwen3-8-max)
-   [GPT-4o vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-gpt-4o)
-   [GPT-4o vs Muse Spark 1.3](https://noometry.com/compare/gpt-4o-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-4o?

GPT-4o by OpenAI ranks 324th of 354 ranked models on the Noometry Index as of October 2026, with a score of 28.6. Its strongest category is multimodal, where it ranks 91st. API pricing starts at $2.50 per million input tokens and $10 per million output tokens, with a 128K-token context window.

### How much does GPT-4o cost?

GPT-4o costs $2.50 per million input tokens and $10 per million output tokens on OpenAI's own API, with cached input at $1.25.

### What is GPT-4o's context window?

GPT-4o accepts up to 128K tokens of input and can write up to 16K tokens in one response.

### Is GPT-4o open source?

No. GPT-4o is proprietary and available only through OpenAI's API and partner platforms.

### What are GPT-4o's strengths and weaknesses?

Relative to other ranked models, GPT-4o places best in writing & preference, long context, multilingual and lowest in reasoning, coding, math.

### What is GPT-4o best at?

Its best category is multimodal, where it ranks 91st on Noometry.

### Cite this page

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

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