# GPT-4 Turbo Preview

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

OpenAI

Canonical URL: https://benchize.com/models/gpt-4-turbo-preview
Last updated: Wed, 21 Oct 2026 18:52:20 GMT

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

OpenAI

## Benchmarks

| Benchmark | Score | ± | Rank |  |
| --- | --- | --- | --- | --- |
| [Agentic Tool Use (Chat)](https://benchize.com/benchmarks/scale%3Atool_use_chat.md) | 53.03source score | CI 46.08–59.98 | 4 / 11 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 53.03 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4 Turbo Preview sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 46.08–59.98 contaminationWarning Not reported rank 18 reportedConfidenceHalfWidth 6.95 ### Source [Original source](https://labs.scale.com/leaderboard/tool_use_chat) Source scale Original model label GPT-4 Turbo Preview Observed 2026-10-21T16:35:40.196Z Evidence SHA-256 `53ee3ef4e3efd7d807b9d93d3755560597812d218b9beb4b3ca98b8752d70590` Source locator `/rows/17` |  |  |  |  |
| [Coding](https://benchize.com/benchmarks/scale%3Acoding.md) | 1,034source score | CI 1,012–1,056 | 4 / 8 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 1034 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4 Turbo Preview sourceModelVersion gpt-4-0125-preview thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 1,012–1,056 contaminationWarning Not reported rank 13 reportedConfidenceHalfWidth 22 ### Source [Original source](https://labs.scale.com/leaderboard/coding) Source scale Original model label GPT-4 Turbo Preview Observed 2026-10-21T16:35:43.120Z Evidence SHA-256 `0c9ec6a10c453ad3d004b54cea41d9957b4739308340858336bbff82141ff309` Source locator `/rows/12` |  |  |  |  |
| [Math](https://benchize.com/benchmarks/scale%3Amath.md) | 95.1source score | CI 93.88–96.32 | 2 / 5 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 95.1 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4 Turbo Preview sourceModelVersion gpt-4-0125-preview thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 93.88–96.32 contaminationWarning Not reported rank 5 reportedConfidenceHalfWidth 1.22 ### Source [Original source](https://labs.scale.com/leaderboard/math) Source scale Original model label GPT-4 Turbo Preview Observed 2026-10-21T16:35:44.522Z Evidence SHA-256 `9733a9f093382f55ad8f743d72cbdefe7c68699b651a4c4344e87489642a779d` Source locator `/rows/4` |  |  |  |  |
| [Spanish](https://benchize.com/benchmarks/scale%3Aspanish.md) | 1,020source score | CI 998–1,042 | 2 / 5 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 1020 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4 Turbo Preview sourceModelVersion gpt-4-0125-preview thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 998–1,042 contaminationWarning Not reported rank 14 reportedConfidenceHalfWidth 22 ### Source [Original source](https://labs.scale.com/leaderboard/spanish) Source scale Original model label GPT-4 Turbo Preview Observed 2026-10-21T16:35:44.884Z Evidence SHA-256 `20dbd29f5dee622033d82f3adac6f1fd3067ca0737ea686c945855c6ce1c38ac` Source locator `/rows/13` |  |  |  |  |
| [Adversarial Robustness](https://benchize.com/benchmarks/scale%3Aadversarial_robustness.md) | 20source score | CI 9–31 | 2 / 4 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 20 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4 Turbo Preview sourceModelVersion gpt-4-0125-preview thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 9–31 contaminationWarning Not reported rank 6 reportedConfidenceHalfWidth 11 ### Source [Original source](https://labs.scale.com/leaderboard/adversarial_robustness) Source scale Original model label GPT-4 Turbo Preview Observed 2026-10-21T16:35:39.820Z Evidence SHA-256 `9ad617f4026dbd8729d7a28d03eca7818e4f0f6e7e03675760b4a0d2f1ab8f47` Source locator `/rows/5` |  |  |  |  |
| [Instruction Following](https://benchize.com/benchmarks/scale%3Ainstruction_following.md) | 83.19source score | CI 81.88–84.5 | 2 / 4 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 83.19 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4 Turbo Preview sourceModelVersion gpt-4-0125-preview thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 81.88–84.5 contaminationWarning Not reported rank 9 reportedConfidenceHalfWidth 1.31 ### Source [Original source](https://labs.scale.com/leaderboard/instruction_following) Source scale Original model label GPT-4 Turbo Preview Observed 2026-10-21T16:35:41.991Z Evidence SHA-256 `2c7dbe83fd053bd9116743dda0283e16adc2d63e4ae4b62d23fc991f6772ff2f` Source locator `/rows/8` |  |  |  |  |
| [Korean](https://benchize.com/benchmarks/scale%3Akorean.md) | 60.76source score | CI 55.12–66.4 | 1 / 8 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 60.76 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4 Turbo Preview sourceModelVersion gpt-4-0125-preview thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 55.12–66.4 contaminationWarning Not reported rank 5 reportedConfidenceHalfWidth 5.64 ### Source [Original source](https://labs.scale.com/leaderboard/korean) Source scale Original model label GPT-4 Turbo Preview Observed 2026-10-21T16:35:44.172Z Evidence SHA-256 `e1846e496288a3d1d0a49f645276e266d451f5bb5704de0e8e1a771e011f803b` Source locator `/rows/4` |  |  |  |  |
| [Agentic Tool Use (Enterprise)](https://benchize.com/benchmarks/scale%3Atool_use_enterprise.md) | 60.76source score | CI 55.12–66.4 | 4 / 11 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 60.76 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4 Turbo Preview sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 55.12–66.4 contaminationWarning Not reported rank 16 reportedConfidenceHalfWidth 5.64 ### Source [Original source](https://labs.scale.com/leaderboard/tool_use_enterprise) Source scale Original model label GPT-4 Turbo Preview Observed 2026-10-21T16:35:40.753Z Evidence SHA-256 `fbc7110acd9299aeb97bd56cddab6949bfbd09b2f3e01ee6edfa7f7df8cee3a8` Source locator `/rows/15` |  |  |  |  |

---
Cite as: GPT-4 Turbo Preview — Benchize, https://benchize.com/models/gpt-4-turbo-preview (retrieved 2026-10-21)