# GPT-4

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-4. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-4.

OpenAI

Canonical URL: https://benchize.com/models/gpt-4
Last updated: Thu, 22 Oct 2026 08:20:15 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

OpenAI

## Benchmarks

| Benchmark | Score | ± | Rank | Source |  |
| --- | --- | --- | --- | --- | --- |
| [Korean](https://benchize.com/benchmarks/scale%3Akorean.md) | 51.39source score | CI 45.62–57.16 | 6 / 8 | [scale](https://labs.scale.com/leaderboard/korean) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 51.39 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4 sourceModelVersion gpt-4-0613 thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 45.62–57.16 contaminationWarning Not reported rank 13 reportedConfidenceHalfWidth 5.77 ### Source [Original source](https://labs.scale.com/leaderboard/korean) Source scale Original model label GPT-4 Observed 2026-10-22T03:30:16.357Z Evidence SHA-256 `c2863cb2cd550f38a25d3aaf6a6dc6919b3cf1472db1ad038a0cca36c5d0ec36` Source locator `/rows/12` |  |  |  |  |  |
| [Agentic Tool Use (Enterprise)](https://benchize.com/benchmarks/scale%3Atool_use_enterprise.md) | 51.39source score | CI 45.62–57.16 | 9 / 11 | [scale](https://labs.scale.com/leaderboard/tool_use_enterprise) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 51.39 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 45.62–57.16 contaminationWarning Not reported rank 26 reportedConfidenceHalfWidth 5.77 ### Source [Original source](https://labs.scale.com/leaderboard/tool_use_enterprise) Source scale Original model label GPT-4 Observed 2026-10-22T03:30:14.304Z Evidence SHA-256 `6a7b613a8a23135f5c03f151a64f6114024a94e1475b3ab65ad0a5c854562447` Source locator `/rows/25` |  |  |  |  |  |
| [Agentic Tool Use (Chat)](https://benchize.com/benchmarks/scale%3Atool_use_chat.md) | 37.88source score | CI 31.1–44.66 | 8 / 11 | [scale](https://labs.scale.com/leaderboard/tool_use_chat) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 37.88 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 31.1–44.66 contaminationWarning Not reported rank 30 reportedConfidenceHalfWidth 6.78 ### Source [Original source](https://labs.scale.com/leaderboard/tool_use_chat) Source scale Original model label GPT-4 Observed 2026-10-22T03:30:14.061Z Evidence SHA-256 `34269d5523ef290e5d0b50dfadc96d8208fd56ef4f906b53867da69826b98dfa` Source locator `/rows/29` |  |  |  |  |  |
| [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,283 | — | 164 / 191 | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1283 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_4 ### Reported statistics coverageCount 27 draws 0 judged 9 losses 9 rank 265 ratingDeviation 115 wins 0 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-4 Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/249` |  |  |  |  |  |

---
Cite as: GPT-4 — Benchize, https://benchize.com/models/gpt-4 (retrieved 2026-10-22)