# BuzzBench > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/eq-bench%3Abuzzbench. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/eq-bench%3Abuzzbench. Humour analysis evaluated by EQ-Bench, measuring how well language models identify and explain comedic material. The published score and confidence interval are kept independently of response length. Canonical URL: https://benchize.com/benchmarks/eq-bench%3Abuzzbench 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. Humour analysis evaluated by EQ-Bench, measuring how well language models identify and explain comedic material. The published score and confidence interval are kept independently of response length. Writing & creativity · Models tested: 15 · Score publishers: [eq bench](https://eqbench.com/buzzbench.html) ## Model results | # | Model | Score | ± | | | --- | --- | --- | --- | --- | | 1 | [Gemini 2.5 Pro Preview 05-06](https://benchize.com/models/gemini-2-5-pro-preview-05-06.md) | 71.09% | CI 69.58–72.59% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 71.09 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion gemini-2.5-pro-preview-03-25 ### Reported statistics Uncertainty Confidence interval: 69.58–72.59% confidenceIntervalHigh 72.59 confidenceIntervalLow 69.58 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label gemini-2.5-pro-preview-03-25 Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/25` | | | | | | 2 | [GPT-4.1](https://benchize.com/models/gpt-4-1.md) | 67.1% | CI 66.35–67.86% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 67.1 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion gpt-4.1 ### Reported statistics Uncertainty Confidence interval: 66.35–67.86% confidenceIntervalHigh 67.86 confidenceIntervalLow 66.35 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label gpt-4.1 Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/24` | | | | | | 3 | [DeepSeek R1](https://benchize.com/models/deepseek-r1.md) | 62.73% | CI 62.15–63.32% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 62.73 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion deepseek-ai/deepseek-r1 ### Reported statistics Uncertainty Confidence interval: 62.15–63.32% confidenceIntervalHigh 63.32 confidenceIntervalLow 62.15 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label deepseek-ai/deepseek-r1 Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/18` | | | | | | 4 | [Claude 3.5 Sonnet](https://benchize.com/models/claude-3-5-sonnet.md) | 61.94% | CI 61.07–62.8% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 61.94 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion claude-3.5-sonnet ### Reported statistics Uncertainty Confidence interval: 61.07–62.8% confidenceIntervalHigh 62.8 confidenceIntervalLow 61.07 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label claude-3.5-sonnet Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/0` | | | | | | 5 | [O1](https://benchize.com/models/o1.md) | 59.28% | CI 58.18–60.38% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 59.28 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion o1 ### Reported statistics Uncertainty Confidence interval: 58.18–60.38% confidenceIntervalHigh 60.38 confidenceIntervalLow 58.18 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label o1 Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/7` | | | | | | 6 | [Gemini 2.0 Flash 001](https://benchize.com/models/gemini-2-0-flash-001.md) | 54.39% | CI 53.32–55.46% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 54.39 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion gemini-2.0-flash-001 ### Reported statistics Uncertainty Confidence interval: 53.32–55.46% confidenceIntervalHigh 55.46 confidenceIntervalLow 53.32 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label gemini-2.0-flash-001 Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/20` | | | | | | 7 | [DeepSeek V3](https://benchize.com/models/deepseek-chat.md) | 51.63% | CI 50.9–52.36% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 51.63 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion deepseek-ai/DeepSeek-V3 ### Reported statistics Uncertainty Confidence interval: 50.9–52.36% confidenceIntervalHigh 52.36 confidenceIntervalLow 50.9 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label deepseek-ai/DeepSeek-V3 Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/5` | | | | | | 8 | [O1 Mini](https://benchize.com/models/o1-mini.md) | 46.18% | CI 45.26–47.1% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 46.18 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion o1-mini ### Reported statistics Uncertainty Confidence interval: 45.26–47.1% confidenceIntervalHigh 47.1 confidenceIntervalLow 45.26 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label o1-mini Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/6` | | | | | | 9 | [Qwen2.5 72B Instruct](https://benchize.com/models/qwen-2-5-72b-instruct.md) | 45.89% | CI 45.08–46.7% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 45.89 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion Qwen/Qwen2.5-72B-Instruct ### Reported statistics Uncertainty Confidence interval: 45.08–46.7% confidenceIntervalHigh 46.7 confidenceIntervalLow 45.08 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label Qwen/Qwen2.5-72B-Instruct Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/16` | | | | | | 10 | [Llama 3.3 70B Instruct](https://benchize.com/models/llama-3-3-70b-instruct.md) | 45.7% | CI 44.75–46.65% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 45.7 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion meta-llama/llama-3.3-70b-instruct ### Reported statistics Uncertainty Confidence interval: 44.75–46.65% confidenceIntervalHigh 46.65 confidenceIntervalLow 44.75 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label meta-llama/llama-3.3-70b-instruct Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/8` | | | | | | 11 | [GPT-3.5 Turbo (older v0613)](https://benchize.com/models/gpt-3-5-turbo-0613.md) | 39% | CI 38.33–39.67% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 39.0 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion gpt-3.5-turbo-0613 ### Reported statistics Uncertainty Confidence interval: 38.33–39.67% confidenceIntervalHigh 39.67 confidenceIntervalLow 38.33 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label gpt-3.5-turbo-0613 Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/9` | | | | | | 12 | [Phi 4](https://benchize.com/models/phi-4.md) | 38.67% | CI 37.7–39.64% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 38.67 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion microsoft/phi-4 ### Reported statistics Uncertainty Confidence interval: 37.7–39.64% confidenceIntervalHigh 39.64 confidenceIntervalLow 37.7 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label microsoft/phi-4 Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/19` | | | | | | 13 | [Llama 3.1 8B Instruct](https://benchize.com/models/llama-3-1-8b-instruct.md) | 32.88% | CI 31.52–34.23% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 32.88 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion meta-llama/llama-3.1-8b-instruct ### Reported statistics Uncertainty Confidence interval: 31.52–34.23% confidenceIntervalHigh 34.23 confidenceIntervalLow 31.52 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label meta-llama/llama-3.1-8b-instruct Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/15` | | | | | | 14 | [Llama 3.2 3B Instruct](https://benchize.com/models/llama-3-2-3b-instruct.md) | 26.55% | CI 25.68–27.41% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 26.55 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion meta-llama/llama-3.2-3b-instruct ### Reported statistics Uncertainty Confidence interval: 25.68–27.41% confidenceIntervalHigh 27.41 confidenceIntervalLow 25.68 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label meta-llama/llama-3.2-3b-instruct Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/3` | | | | | | 15 | [Llama 3.2 1B Instruct](https://benchize.com/models/llama-3-2-1b-instruct.md) | 9.51% | CI 8.81–10.21% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 9.51 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion meta-llama/llama-3.2-1b-instruct ### Reported statistics Uncertainty Confidence interval: 8.81–10.21% confidenceIntervalHigh 10.21 confidenceIntervalLow 8.81 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label meta-llama/llama-3.2-1b-instruct Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/2` | | | | | --- Cite as: BuzzBench — Benchize, https://benchize.com/benchmarks/eq-bench%3Abuzzbench (retrieved 2026-10-21)