OpenAI, proprietary

# GPT-4

> GPT-4 by OpenAI, released March 2023. Ranked #316 of 354 with a Noometry Index of 29.1. API: $30 in / $60 out per M tokens. 8K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/gpt-4
- Last updated: 2026-10-10
- Title: GPT-4 Benchmarks, Price & Rank (October 2026) | Noometry

GPT-4 by OpenAI ranks 316th of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.1. Its strongest category is long context, where it ranks 212th. API pricing starts at $30 per million input tokens and $60 per million output tokens, with a 8K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #316 of 354
- **Index score:** 29.1
- **Evidence:** Confirmed 38 results
- **Provider:** [OpenAI](https://noometry.com/providers/openai)
- **Released:** March 14, 2023
- **Weights:** Proprietary
- **Reasoning:** No
- **Context window:** 8K
- **Max output:** 8K
- **Input price:** $30 / M
- **Output price:** $60 / M
- **Blended price:** $37.50 / M
- **Output speed:** Not measured
- **Value:** #218 of 219
- **Knowledge cutoff:** November 2023
- **Input:** text

## Category scores

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

GPT-4 category scores

1.  Coding 31.6
2.  Reasoning 17.8
3.  Math 10.8
4.  Knowledge 18.4
5.  Multilingual 40.6
6.  Instruction Following 65.3
7.  Long Context 37.7
8.  Writing & Preference 34.9
9.  020406080

GPT-4 category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 31.6 | #283 | 4 |
| [Reasoning](https://noometry.com/best/reasoning) | 17.8 | #289 | 5 |
| [Math](https://noometry.com/best/math) | 10.8 | #309 | 3 |
| [Knowledge](https://noometry.com/best/knowledge) | 18.4 | #282 | 2 |
| [Multilingual](https://noometry.com/best/multilingual) | 40.6 | #215 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 65.3 | #222 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 37.7 | #212 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 34.9 | #268 | 4 |

## Strengths and weaknesses

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

### Strongest categories

GPT-4: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Long Context](https://noometry.com/best/long-context) | 37.7 | −3.2 | #212 of 296, top 72% |
| [Multilingual](https://noometry.com/best/multilingual) | 40.6 | −6.8 | #215 of 297, top 73% |
| [Instruction Following](https://noometry.com/best/instruction-following) | 65.3 | −6.0 | #222 of 305, top 73% |

### Weakest categories

GPT-4: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Math](https://noometry.com/best/math) | 10.8 | −25.8 | #309 of 327, top 95% |
| [Knowledge](https://noometry.com/best/knowledge) | 18.4 | −18.9 | #282 of 314, top 90% |
| [Writing & Preference](https://noometry.com/best/writing) | 34.9 | −18.9 | #268 of 312, top 86% |

## Closest competitors

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

Models ranked closest to GPT-4
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Gemma 2 27B](https://noometry.com/models/gemma-2-27b) | #312 | 29.4 | $0.65 | — | [Compare](https://noometry.com/compare/gemma-2-27b-vs-gpt-4) |
| [Gemma 1.1 2b IT](https://noometry.com/models/gemma-1-1-2b-it) | #313 | 29.3 | — | — | [Compare](https://noometry.com/compare/gemma-1-1-2b-it-vs-gpt-4) |
| [Phi 3 Small 8k Instruct](https://noometry.com/models/phi-3-small-8k-instruct) | #314 | 29.3 | — | — | [Compare](https://noometry.com/compare/gpt-4-vs-phi-3-small-8k-instruct) |
| [Claude 3.5 Haiku](https://noometry.com/models/claude-3-5-haiku) | #315 | 29.2 | — | — | [Compare](https://noometry.com/compare/claude-3-5-haiku-vs-gpt-4) |
| [Llama 2-7B](https://noometry.com/models/llama-2-7b) | #317 | 29.1 | — | — | [Compare](https://noometry.com/compare/gpt-4-vs-llama-2-7b) |
| [Granite 4.0 Micro](https://noometry.com/models/granite-4-0-micro) | #318 | 29.0 | $0.0408 | — | [Compare](https://noometry.com/compare/gpt-4-vs-granite-4-0-micro) |
| [Claude 3 Sonnet](https://noometry.com/models/claude-3-sonnet) | #319 | 29.0 | — | — | [Compare](https://noometry.com/compare/claude-3-sonnet-vs-gpt-4) |
| [Qwen2.5 7B Instruct](https://noometry.com/models/qwen2-5-7b-instruct) | #320 | 29.0 | $0.31 | — | [Compare](https://noometry.com/compare/gpt-4-vs-qwen2-5-7b-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-4 Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 12.4% | #110 of 119, top 93% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [BigCodeBench Instruct](https://noometry.com/benchmarks/bigcodebench-instruct) | 46% | #15 of 64, top 24% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-06-13 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1249 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1187 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1254 | #224 of 294, top 77% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1209 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [BigCodeBench Complete](https://noometry.com/benchmarks/bigcodebench-complete) | 57.2% | #15 of 66, top 23% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-06-13 |
| [HumanEval+](https://noometry.com/benchmarks/humaneval-plus) | 79.3% | #12 of 45, top 27% | may 2023 | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |

### Agentic & Tool Use

GPT-4 Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [METR Time Horizons](https://noometry.com/benchmarks/metr-time-horizons) | 36.1% | #28 of 32, top 88% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Reasoning

GPT-4 Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 4% | #97 of 129, top 76% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-07 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1241 | #225 of 297, top 76% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1174 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1200 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1239 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 12% | #56 of 74, top 76% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-28 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 62.7% | #108 of 151, top 72% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 17.1% | #99 of 125, top 80% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [BIG-Bench Hard](https://noometry.com/benchmarks/bbh) | 75.1% | #8 of 27, top 30% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 125.89 | #155 of 213, top 73% |  | [Epoch AI](https://epoch.ai/eci) | 2023-03-14 |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 123.12 |  |  | [Epoch AI](https://epoch.ai/eci) | 2023-06-13 |
| [ForecastBench](https://noometry.com/benchmarks/forecastbench) | 57.8 | #53 of 72, top 74% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [HellaSwag](https://noometry.com/benchmarks/hellaswag) | 95.3% | Best of 29 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [HellaSwag](https://noometry.com/benchmarks/hellaswag) | 95.3% | Best of 29 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WinoGrande](https://noometry.com/benchmarks/winogrande) | 87.5% | #3 of 43, top 7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WinoGrande](https://noometry.com/benchmarks/winogrande) | 87.5% | #3 of 43, top 7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Math

GPT-4 Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 0.6% |  |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-10-22 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 1.1% | #168 of 173, top 98% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-10-23 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1230 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1217 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1268 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1269 | #202 of 285, top 71% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 23% | #60 of 79, top 76% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |
| [GSM8K](https://noometry.com/benchmarks/gsm8k) | 92% | #3 of 38, top 8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [GSM8K](https://noometry.com/benchmarks/gsm8k) | 90% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Knowledge

GPT-4 Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 30.7% |  |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 35.7% | #157 of 186, top 85% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-10-23 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1128 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1149 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1205 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1211 | #216 of 273, top 80% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MMLU](https://noometry.com/benchmarks/mmlu) | 86.4% | #5 of 81, top 7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [MMLU](https://noometry.com/benchmarks/mmlu) | 82.4% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [TriviaQA](https://noometry.com/benchmarks/triviaqa) | 84.8% | #5 of 25, top 20% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Multilingual

GPT-4 Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1241 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1194 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1160 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1246 | #215 of 297, top 73% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1238 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1184 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1136 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1242 | #211 of 285, top 75% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1281 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1170 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1219 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1283 | #168 of 223, top 76% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1198 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1251 | #178 of 231, top 78% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1162 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1246 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1209 | #152 of 211, top 73% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1195 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1114 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1137 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1184 | #170 of 213, top 80% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1174 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1087 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1060 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1251 | #213 of 283, top 76% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1173 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1241 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1195 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1168 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1261 | #177 of 226, top 79% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1197 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1248 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

GPT-4 Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1235 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1201 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1189 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1241 | #221 of 298, top 75% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

GPT-4 Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1190 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1188 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1244 | #224 of 291, top 77% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1236 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

GPT-4 Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1206 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1262 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1186 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1263 | #219 of 297, top 74% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1232 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1190 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1244 | #210 of 295, top 72% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1192 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) | 752 | #107 of 115, top 94% |  | [EQ-Bench](https://eqbench.com/creative_writing.html) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1257 | #218 of 295, top 74% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1185 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1206 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1250 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

GPT-4 API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [openai](https://platform.openai.com/docs/models) | $30 | $60 | — | 2026-10-10 |
| [openrouter](https://openrouter.ai/openai/gpt-4) | $30 | $60 | — | 2026-10-10 |

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

## Compare GPT-4

-   [GPT-4 vs Claude 3.5 Haiku](https://noometry.com/compare/claude-3-5-haiku-vs-gpt-4)
-   [GPT-4 vs Llama 2-7B](https://noometry.com/compare/gpt-4-vs-llama-2-7b)
-   [GPT-4 vs Phi 3 Small 8k Instruct](https://noometry.com/compare/gpt-4-vs-phi-3-small-8k-instruct)
-   [GPT-4 vs Granite 4.0 Micro](https://noometry.com/compare/gpt-4-vs-granite-4-0-micro)
-   [GPT-4 vs Gemma 1.1 2b IT](https://noometry.com/compare/gemma-1-1-2b-it-vs-gpt-4)
-   [GPT-4 vs Claude 3 Sonnet](https://noometry.com/compare/claude-3-sonnet-vs-gpt-4)
-   [GPT-4 vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-gpt-4)
-   [GPT-4 vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-gpt-4)
-   [GPT-4 vs Kimi K3](https://noometry.com/compare/gpt-4-vs-kimi-k3)
-   [GPT-4 vs Grok 4.6](https://noometry.com/compare/gpt-4-vs-grok-4-6)
-   [GPT-4 vs Qwen3.8 Max](https://noometry.com/compare/gpt-4-vs-qwen3-8-max)
-   [GPT-4 vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-gpt-4)
-   [GPT-4 vs Muse Spark 1.3](https://noometry.com/compare/gpt-4-vs-muse-spark-1-3)
-   [GPT-4 vs DeepSeek V4 Pro](https://noometry.com/compare/deepseek-v4-pro-vs-gpt-4)

## 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?

GPT-4 by OpenAI ranks 316th of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.1. Its strongest category is long context, where it ranks 212th. API pricing starts at $30 per million input tokens and $60 per million output tokens, with a 8K-token context window.

### How much does GPT-4 cost?

GPT-4 costs $30 per million input tokens and $60 per million output tokens on OpenAI's own API.

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

GPT-4 accepts up to 8K tokens of input and can write up to 8K tokens in one response.

### Is GPT-4 open source?

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

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

Relative to other ranked models, GPT-4 places best in long context, multilingual, instruction following and lowest in math, knowledge, writing & preference.

### What is GPT-4 best at?

Its best category is long context, where it ranks 212th on Noometry.

### Cite this page

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

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