# Creative Writing v3 > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3. Short-form creative writing evaluated by LLM judges using pairwise Elo comparisons and writing-quality rubrics. Reported scores are preserved before optional interactive vocabulary or repetition adjustments. Canonical URL: https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3 Last updated: Wed, 21 Oct 2026 18:05:10 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Short-form creative writing evaluated by LLM judges using pairwise Elo comparisons and writing-quality rubrics. Reported scores are preserved before optional interactive vocabulary or repetition adjustments. Writing & creativity · Models tested: 90 · Score publishers: [eq bench](https://eqbench.com/creative_writing.html) ## Model results | # | Model | Score | | | --- | --- | --- | --- | | 1 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra.md) | 2,173.3elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 2173.3 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.80 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-6-astra ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-6-astra Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/0` | | | | | 2 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1.md) | 2,162elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 2162.0 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.95 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion claude-fable-5-1 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label claude-fable-5-1 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/1` | | | | | 3 | [Claude Opus 5](https://benchize.com/models/claude-opus-5.md) | 2,132.6elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 2132.6 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 17.07 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion claude-opus-5 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label claude-opus-5 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/2` | | | | | 4 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol.md) | 2,124.7elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 2124.7 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.51 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-6-sol ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-6-sol Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/3` | | | | | 5 | [Kimi K3](https://benchize.com/models/kimi-k3.md) | 2,082.3elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 2082.3 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.85 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion kimi-k3 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label kimi-k3 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/4` | | | | | 6 | [GLM 5.3](https://benchize.com/models/glm-5-3.md) | 2,075elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 2075.0 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 17.04 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion GLM-5.3 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label GLM-5.3 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/5` | | | | | 7 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5.md) | 2,050.1elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 2050.1 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.79 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion claude-opus-5-5 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label claude-opus-5-5 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/6` | | | | | 8 | [Grok 4.7](https://benchize.com/models/grok-4-7.md) | 2,006.7elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 2006.7 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 17.16 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion grok-4.7 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label grok-4.7 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/7` | | | | | 9 | [Ox Alpha](https://benchize.com/models/ox-alpha.md) | 1,971.7elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1971.7 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.89 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion ox-alpha ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label ox-alpha Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/8` | | | | | 10 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol.md) | 1,971.6elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1971.6 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.78 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-5.6-sol ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-5.6-sol Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/9` | | | | | 11 | [Claude Fable 5](https://benchize.com/models/claude-fable-5.md) | 1,943.1elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1943.1 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.81 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion claude-fable-5 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label claude-fable-5 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/10` | | | | | 12 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1.md) | 1,927.1elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1927.1 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.54 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion muse-spark-1.1 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label muse-spark-1.1 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/12` | | | | | 13 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7.md) | 1,914.3elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1914.3 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.57 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion claude-opus-4-7 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label claude-opus-4-7 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/13` | | | | | 14 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3.md) | 1,905.9elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1905.9 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.70 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion muse-spark-1.3 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label muse-spark-1.3 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/15` | | | | | 15 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra.md) | 1,854.9elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1854.9 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.56 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-5.6-terra ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-5.6-terra Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/16` | | | | | 16 | [GPT-5.5](https://benchize.com/models/gpt-5-5.md) | 1,843.9elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1843.9 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 17.01 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-5.5 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-5.5 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/17` | | | | | 17 | [Qwen3.8 2.4T A95B](https://benchize.com/models/qwen3-8-2-4t-a95b.md) | 1,842.5elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1842.5 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.72 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion Qwen/Qwen3.8-2.4T-A95B ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label Qwen/Qwen3.8-2.4T-A95B Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/18` | | | | | 18 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2.md) | 1,840.4elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1840.4 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.44 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion muse-spark-1.2 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label muse-spark-1.2 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/19` | | | | | 19 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8.md) | 1,839.8elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1839.8 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.66 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion claude-opus-4-8 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label claude-opus-4-8 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/20` | | | | | 20 | [GPT-5.4](https://benchize.com/models/gpt-5-4.md) | 1,839.7elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1839.7 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.89 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-5.4 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-5.4 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/21` | | | | | 21 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna.md) | 1,828.7elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1828.7 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.58 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-5.6-luna ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-5.6-luna Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/22` | | | | | 22 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6.md) | 1,810.4elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1810.4 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.50 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion claude-sonnet-4-6 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label claude-sonnet-4-6 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/23` | | | | | 23 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6.md) | 1,809.1elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1809.1 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.53 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion claude-opus-4-6 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label claude-opus-4-6 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/24` | | | | | 24 | [Muse Glimmer 30B](https://benchize.com/models/muse-glimmer-30b.md) | 1,798.3elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1798.3 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.26 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion meta-models/Muse-Glimmer-30B ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label meta-models/Muse-Glimmer-30B Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/25` | | | | | 25 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5.md) | 1,794elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1794.0 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.47 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion claude-sonnet-5 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label claude-sonnet-5 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/26` | | | | | 26 | [Space Bunny Alpha](https://benchize.com/models/space-bunny-alpha.md) | 1,784.3elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1784.3 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.30 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion space-bunny-alpha ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label space-bunny-alpha Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/27` | | | | | 27 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash.md) | 1,747.9elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1747.9 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.54 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gemini-3.8-flash ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gemini-3.8-flash Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/29` | | | | | 28 | [Kimi K2.6](https://benchize.com/models/kimi-k2-6.md) | 1,724.5elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1724.5 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.67 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion moonshotai/Kimi-K2.6 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label moonshotai/Kimi-K2.6 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/30` | | | | | 29 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash.md) | 1,723.2elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1723.2 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.27 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gemini-3.7-flash ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gemini-3.7-flash Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/31` | | | | | 30 | [GPT-5.2](https://benchize.com/models/gpt-5-2.md) | 1,702.9elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1702.9 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.66 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-5.2 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-5.2 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/32` | | | | | 31 | [GPT-5.3 Chat](https://benchize.com/models/gpt-5-3-chat.md) | 1,689.9elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1689.9 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.21 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-5.3-chat ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-5.3-chat Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/34` | | | | | 32 | [Claude Sonnet 4.5](https://benchize.com/models/claude-sonnet-4-5.md) | 1,677.6elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1677.6 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.14 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion claude-sonnet-4.5 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label claude-sonnet-4.5 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/36` | | | | | 33 | [O3](https://benchize.com/models/o3.md) | 1,675.6elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1675.6 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.28 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion o3 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label o3 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/37` | | | | | 34 | [Qwen3.8 27B](https://benchize.com/models/qwen3-8-27b.md) | 1,671.3elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1671.3 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.50 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion Qwen/Qwen3.8-27B ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label Qwen/Qwen3.8-27B Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/38` | | | | | 35 | [Kimi K2](https://benchize.com/models/kimi-k2.md) | 1,665.7elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1665.7 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.40 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion moonshotai/Kimi-K2-Instruct ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label moonshotai/Kimi-K2-Instruct Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/39` | | | | | 36 | [GPT-5.4 Mini](https://benchize.com/models/gpt-5-4-mini.md) | 1,665elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1665.0 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.51 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-5.4-mini ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-5.4-mini Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/40` | | | | | 37 | [Kimi K2 Thinking](https://benchize.com/models/kimi-k2-thinking.md) | 1,630.9elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1630.9 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.47 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion moonshotai/Kimi-K2-Thinking ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label moonshotai/Kimi-K2-Thinking Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/41` | | | | | 38 | [Inkling](https://benchize.com/models/inkling.md) | 1,610.8elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1610.8 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.38 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion thinkingmachines/Inkling ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label thinkingmachines/Inkling Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/46` | | | | | 39 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash.md) | 1,603.5elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1603.5 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.22 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gemini-3.6-flash ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gemini-3.6-flash Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/47` | | | | | 40 | [GLM-5](https://benchize.com/models/glm-5.md) | 1,600.6elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1600.6 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.09 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion zai-org/GLM-5 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label zai-org/GLM-5 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/48` | | | | | 41 | [Claude Opus 4](https://benchize.com/models/claude-opus-4.md) | 1,579.7elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1579.7 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.05 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion claude-opus-4 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label claude-opus-4 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/50` | | | | | 42 | [Grok 4.5](https://benchize.com/models/grok-4-5.md) | 1,578.8elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1578.8 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.25 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion grok-4.5 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label grok-4.5 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/51` | | | | | 43 | [Kimi K2.5](https://benchize.com/models/kimi-k2-5.md) | 1,578.6elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1578.6 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.94 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion moonshotai/Kimi-K2.5 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label moonshotai/Kimi-K2.5 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/52` | | | | | 44 | [DeepSeek V4 Flash](https://benchize.com/models/deepseek-v4-flash.md) | 1,559.1elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1559.1 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.29 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion deepseek-ai/DeepSeek-V4-Flash ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label deepseek-ai/DeepSeek-V4-Flash Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/54` | | | | | 44 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite.md) | 1,559.1elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1559.1 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.15 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gemini-3.5-flash-lite ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gemini-3.5-flash-lite Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/55` | | | | | 46 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro.md) | 1,553.2elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1553.2 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.45 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion deepseek-ai/DeepSeek-V4-Pro ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label deepseek-ai/DeepSeek-V4-Pro Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/56` | | | | | 47 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash.md) | 1,540.1elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1540.1 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.08 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion deepseek-v4.1-flash ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label deepseek-v4.1-flash Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/57` | | | | | 48 | [DeepSeek V3.2](https://benchize.com/models/deepseek-v3-2.md) | 1,515elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1515.0 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.28 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion deepseek-ai/DeepSeek-V3.2 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label deepseek-ai/DeepSeek-V3.2 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/59` | | | | | 49 | [DeepSeek R1](https://benchize.com/models/deepseek-r1.md) | 1,500elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1500.0 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.68 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion deepseek-ai/DeepSeek-R1 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label deepseek-ai/DeepSeek-R1 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/61` | | | | | 50 | [MiMo-V2.5-Pro](https://benchize.com/models/mimo-v2-5-pro.md) | 1,493.4elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1493.4 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.06 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion XiaomiMiMo/MiMo-V2.5-Pro ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label XiaomiMiMo/MiMo-V2.5-Pro Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/62` | | | | | 51 | [Inkling Small](https://benchize.com/models/inkling-small.md) | 1,491.4elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1491.4 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.53 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion thinkingmachines/Inkling-Small ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label thinkingmachines/Inkling-Small Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/63` | | | | | 52 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview.md) | 1,491.3elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1491.3 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.04 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gemini-3.1-pro-preview ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gemini-3.1-pro-preview Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/64` | | | | | 53 | [Claude Sonnet 4](https://benchize.com/models/claude-sonnet-4.md) | 1,482.8elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1482.8 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.77 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion claude-sonnet-4 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label claude-sonnet-4 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/66` | | | | | 54 | [Qwen3.5 397B A17B](https://benchize.com/models/qwen3-5-397b-a17b.md) | 1,478.2elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1478.2 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.00 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion Qwen/Qwen3.5-397B-A17B ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label Qwen/Qwen3.5-397B-A17B Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/67` | | | | | 55 | [Mistral Medium 3.1](https://benchize.com/models/mistral-medium-3-1.md) | 1,475.7elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1475.7 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.96 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion mistral-medium-3.1 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label mistral-medium-3.1 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/68` | | | | | 56 | [DeepSeek V4 Flash 0731](https://benchize.com/models/deepseek-v4-flash-0731.md) | 1,441.1elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1441.1 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.98 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion deepseek-ai/DeepSeek-V4-Flash-0731 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label deepseek-ai/DeepSeek-V4-Flash-0731 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/71` | | | | | 57 | [DeepSeek Chat V3.1](https://benchize.com/models/deepseek-chat-v3-1.md) | 1,435.9elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1435.9 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.10 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion deepseek-ai/DeepSeek-V3.1 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label deepseek-ai/DeepSeek-V3.1 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/72` | | | | | 58 | [Gemini 2.5 Pro Preview 06-05](https://benchize.com/models/gemini-2-5-pro-preview.md) | 1,421.2elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1421.2 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.16 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gemini-2.5-pro-preview-06-05 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gemini-2.5-pro-preview-06-05 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/73` | | | | | 59 | [R1 0528](https://benchize.com/models/deepseek-r1-0528.md) | 1,421.1elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1421.1 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.88 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion deepseek-ai/DeepSeek-R1-0528 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label deepseek-ai/DeepSeek-R1-0528 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/74` | | | | | 60 | [Hermes 4 405B](https://benchize.com/models/hermes-4-405b.md) | 1,420.8elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1420.8 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.15 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion NousResearch/Hermes-4-405B ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label NousResearch/Hermes-4-405B Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/75` | | | | | 61 | [GPT-4.1](https://benchize.com/models/gpt-4-1.md) | 1,419.7elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1419.7 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.80 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-4.1 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-4.1 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/76` | | | | | 62 | [GLM-4.7](https://benchize.com/models/glm-4-7.md) | 1,413.3elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1413.3 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.97 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion zai-org/GLM-4.7 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label zai-org/GLM-4.7 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/78` | | | | | 63 | [GLM-4.6](https://benchize.com/models/glm-4-6.md) | 1,411.1elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1411.1 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.10 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion zai-org/GLM-4.6 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label zai-org/GLM-4.6 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/81` | | | | | 64 | [Gemma 4 31B](https://benchize.com/models/gemma-4-31b-it.md) | 1,368.2elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1368.2 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.01 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion google/gemma-4-31B-it ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label google/gemma-4-31B-it Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/84` | | | | | 65 | [MiniMax M2.5](https://benchize.com/models/minimax-m2-5.md) | 1,361elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1361.0 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.18 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion minimax/minimax-m2.5 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label minimax/minimax-m2.5 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/86` | | | | | 66 | [GLM-4.5](https://benchize.com/models/glm-4-5.md) | 1,343.3elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1343.3 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.83 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion zai-org/GLM-4.5 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label zai-org/GLM-4.5 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/89` | | | | | 67 | [Gemma 4 26B A4B](https://benchize.com/models/gemma-4-26b-a4b-it.md) | 1,304.6elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1304.6 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.03 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion google/gemma-4-26B-A4B-it ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label google/gemma-4-26B-A4B-it Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/93` | | | | | 68 | [Gemma 3 27B](https://benchize.com/models/gemma-3-27b-it.md) | 1,265.7elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1265.7 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.33 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion google/gemma-3-27b-it ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label google/gemma-3-27b-it Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/97` | | | | | 69 | [Mistral Small 3.2 24B](https://benchize.com/models/mistral-small-3-2-24b-instruct.md) | 1,255.4elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1255.4 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 14.31 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion mistralai/Mistral-Small-3.2-24B-Instruct-2506 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label mistralai/Mistral-Small-3.2-24B-Instruct-2506 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/100` | | | | | 70 | [Reka Flash 3](https://benchize.com/models/reka-flash-3.md) | 1,227.8elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1227.8 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 13.63 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion RekaAI/reka-flash-3 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label RekaAI/reka-flash-3 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/101` | | | | | 71 | [GPT-4.1 Mini](https://benchize.com/models/gpt-4-1-mini.md) | 1,147elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1147.0 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 13.67 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-4.1-mini ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-4.1-mini Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/103` | | | | | 72 | [Gemini 2.0 Flash 001](https://benchize.com/models/gemini-2-0-flash-001.md) | 1,127.5elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1127.5 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 14.24 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gemini-2.0-flash-001 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gemini-2.0-flash-001 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/107` | | | | | 73 | [Gemma 3 12B](https://benchize.com/models/gemma-3-12b-it.md) | 1,125.5elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1125.5 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 14.63 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion google/gemma-3-12b-it ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label google/gemma-3-12b-it Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/108` | | | | | 74 | [GLM-4.7 Flash](https://benchize.com/models/glm-4-7-flash.md) | 1,124.7elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1124.7 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 13.68 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion zai-org/GLM-4.7-Flash ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label zai-org/GLM-4.7-Flash Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/109` | | | | | 75 | [Gemma 3 4B](https://benchize.com/models/gemma-3-4b-it.md) | 1,068elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1068.0 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 13.91 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion google/gemma-3-4b-it ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label google/gemma-3-4b-it Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/113` | | | | | 76 | [gpt-oss-120b](https://benchize.com/models/gpt-oss-120b.md) | 961elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 961.0 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 10.74 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion openai/gpt-oss-120b ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label openai/gpt-oss-120b Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/117` | | | | | 77 | [GPT-4.1 Nano](https://benchize.com/models/gpt-4-1-nano.md) | 945.8elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 945.8 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 11.03 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-4.1-nano ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-4.1-nano Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/118` | | | | | 78 | [Mistral Nemo](https://benchize.com/models/mistral-nemo.md) | 880.9elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 880.9 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 9.51 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion mistralai/Mistral-Nemo-Instruct-2407 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label mistralai/Mistral-Nemo-Instruct-2407 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/120` | | | | | 79 | [GPT-4o Mini](https://benchize.com/models/gpt-4o-mini.md) | 872.8elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 872.8 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 11.67 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-4o-mini ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-4o-mini Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/121` | | | | | 80 | [Llama 4 Maverick](https://benchize.com/models/llama-4-maverick.md) | 860.1elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 860.1 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 10.50 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion meta-llama/Llama-4-Maverick-17B-128E-Instruct ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label meta-llama/Llama-4-Maverick-17B-128E-Instruct Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/123` | | | | | 81 | [Llama 3.1 70B Instruct](https://benchize.com/models/llama-3-1-70b-instruct.md) | 783.6elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 783.6 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 10.18 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion meta-llama/llama-3.1-70b-instruct ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label meta-llama/llama-3.1-70b-instruct Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/126` | | | | | 82 | [Llama 4 Scout](https://benchize.com/models/llama-4-scout.md) | 783.1elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 783.1 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 9.12 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion meta-llama/Llama-4-Scout-17B-16E-Instruct ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label meta-llama/Llama-4-Scout-17B-16E-Instruct Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/127` | | | | | 83 | [Mistral Small 3.1 24B](https://benchize.com/models/mistral-small-3-1-24b-instruct.md) | 760.9elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 760.9 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 8.46 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion mistralai/mistral-small-3.1-24b-instruct-2503 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label mistralai/mistral-small-3.1-24b-instruct-2503 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/129` | | | | | 84 | [Claude 3 Haiku](https://benchize.com/models/claude-3-haiku.md) | 717.3elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 717.3 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 9.91 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion anthropic/claude-3-haiku ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label anthropic/claude-3-haiku Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/132` | | | | | 85 | [Llama 3.1 8B Instruct](https://benchize.com/models/llama-3-1-8b-instruct.md) | 713elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 713.0 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 8.89 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion meta-llama/llama-3.1-8b-instruct ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label meta-llama/llama-3.1-8b-instruct Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/133` | | | | | 86 | [Mistral Small 3](https://benchize.com/models/mistral-small-24b-instruct-2501.md) | 706.5elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 706.5 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 8.17 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion mistralai/Mistral-Small-24B-Instruct-2501 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label mistralai/Mistral-Small-24B-Instruct-2501 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/134` | | | | | 87 | [gpt-oss-20b](https://benchize.com/models/gpt-oss-20b.md) | 665.6elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 665.6 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 7.87 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion openai/gpt-oss-20b ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label openai/gpt-oss-20b Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/136` | | | | | 88 | [Llama 3.2 3B Instruct](https://benchize.com/models/llama-3-2-3b-instruct.md) | 595.3elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 595.3 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 8.18 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion meta-llama/llama-3.2-3b-instruct ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label meta-llama/llama-3.2-3b-instruct Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/137` | | | | | 89 | [GPT-3.5 Turbo (older v0613)](https://benchize.com/models/gpt-3-5-turbo-0613.md) | 450.9elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 450.9 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 8.22 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion openai/gpt-3.5-turbo-0613 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label openai/gpt-3.5-turbo-0613 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/138` | | | | | 90 | [Llama 3.2 1B Instruct](https://benchize.com/models/llama-3-2-1b-instruct.md) | 200elo | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 200.0 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 6.49 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion meta-llama/llama-3.2-1b-instruct ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label meta-llama/llama-3.2-1b-instruct Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/139` | | | | --- Cite as: Creative Writing v3 — Benchize, https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3 (retrieved 2026-10-21)