Writing & Preference benchmark # EQ-Bench 4 leaderboard > EQ-Bench 4 results for 28 AI models, led by Claude Opus 5 at 1385. What the benchmark measures, who runs it, and a source for every score. - Canonical page: https://noometry.com/benchmarks/eqbench-4 - Last updated: 2026-10-10 - Title: EQ-Bench 4 Leaderboard (October 2026): Scores by Model As of October 2026, Claude Opus 5 has the highest published EQ-Bench 4 score on Noometry at 1385, out of 28 models with results. Last verified October 10, 2026 ## About EQ-Bench 4 Emotional intelligence in multi-turn role-play conversations, such as building rapport and handling conflict, rated by pairwise LLM-judged comparisons. - **Category:** [Writing & Preference](https://noometry.com/best/writing) - **Introduced:** 2026 - **Format:** Pairwise LLM-judged conversations - **Unit:** Arena rating (Bradley–Terry) - **Official site:** [eqbench.com](https://eqbench.com/) ## Top 15 models Top models on EQ-Bench 4 1. Claude Opus 5 1385 2. Claude Fable 5 1340 3. Kimi K3 1339 4. GPT-5.5 1315 5. Claude Opus 4.7 1311 6. Claude Opus 4.8 1281 7. GPT-5.4 1272 8. Muse Spark 1.1 1260 9. GPT-5.6 Sol 1250 10. Claude Sonnet 5 1236 11. GPT-5.6 Terra 1234 12. Inkling 1226 13. Claude Opus 4.6 1223 14. GLM-5.2 1222 15. MiMo-V2.5-Pro 1208 16. 115012001250130013501400 Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise) ## All results EQ-Bench 4 results by model | # | Model | Provider | Rating | Setting | Source | Date | | --- | --- | --- | --- | --- | --- | --- | | 1 | [Claude Opus 5](https://noometry.com/models/claude-opus-5) | [Anthropic](https://noometry.com/providers/anthropic) | 1385 | | [EQ-Bench](https://eqbench.com/) | | | 2 | [Claude Fable 5](https://noometry.com/models/claude-fable-5) | [Anthropic](https://noometry.com/providers/anthropic) | 1340 | | [EQ-Bench](https://eqbench.com/) | | | 3 | [Kimi K3](https://noometry.com/models/kimi-k3) | [Moonshot AI](https://noometry.com/providers/moonshot) | 1339 | | [EQ-Bench](https://eqbench.com/) | | | 4 | [GPT-5.5](https://noometry.com/models/gpt-5-5) | [OpenAI](https://noometry.com/providers/openai) | 1315 | | [EQ-Bench](https://eqbench.com/) | | | 5 | [Claude Opus 4.7](https://noometry.com/models/claude-opus-4-7) | [Anthropic](https://noometry.com/providers/anthropic) | 1311 | | [EQ-Bench](https://eqbench.com/) | | | 6 | [Claude Opus 4.8](https://noometry.com/models/claude-opus-4-8) | [Anthropic](https://noometry.com/providers/anthropic) | 1281 | | [EQ-Bench](https://eqbench.com/) | | | 7 | [GPT-5.4](https://noometry.com/models/gpt-5-4) | [OpenAI](https://noometry.com/providers/openai) | 1272 | | [EQ-Bench](https://eqbench.com/) | | | 8 | [Muse Spark 1.1](https://noometry.com/models/muse-spark-1-1) | [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 1260 | | [EQ-Bench](https://eqbench.com/) | | | 9 | [GPT-5.6 Sol](https://noometry.com/models/gpt-5-6-sol) | [OpenAI](https://noometry.com/providers/openai) | 1250 | | [EQ-Bench](https://eqbench.com/) | | | 10 | [Claude Sonnet 5](https://noometry.com/models/claude-sonnet-5) | [Anthropic](https://noometry.com/providers/anthropic) | 1236 | | [EQ-Bench](https://eqbench.com/) | | | 11 | [GPT-5.6 Terra](https://noometry.com/models/gpt-5-6-terra) | [OpenAI](https://noometry.com/providers/openai) | 1234 | | [EQ-Bench](https://eqbench.com/) | | | 12 | [Inkling](https://noometry.com/models/inkling) | [T Thinking Machines Lab](https://noometry.com/providers/thinking-machines) | 1226 | | [EQ-Bench](https://eqbench.com/) | | | 13 | [Claude Opus 4.6](https://noometry.com/models/claude-opus-4-6) | [Anthropic](https://noometry.com/providers/anthropic) | 1223 | | [EQ-Bench](https://eqbench.com/) | | | 14 | [GLM-5.2](https://noometry.com/models/glm-5-2) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 1222 | | [EQ-Bench](https://eqbench.com/) | | | 15 | [MiMo-V2.5-Pro](https://noometry.com/models/mimo-v2-5-pro) | [Xiaomi](https://noometry.com/providers/xiaomi) | 1208 | | [EQ-Bench](https://eqbench.com/) | | | 16 | [Claude Sonnet 4.6](https://noometry.com/models/claude-sonnet-4-6) | [Anthropic](https://noometry.com/providers/anthropic) | 1207 | | [EQ-Bench](https://eqbench.com/) | | | 17 | [Kimi K2.6](https://noometry.com/models/kimi-k2-6) | [Moonshot AI](https://noometry.com/providers/moonshot) | 1202 | | [EQ-Bench](https://eqbench.com/) | | | 18 | [DeepSeek V4 Pro](https://noometry.com/models/deepseek-v4-pro) | [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 1166 | | [EQ-Bench](https://eqbench.com/) | | | 19 | [GPT-5.6 Luna](https://noometry.com/models/gpt-5-6-luna) | [OpenAI](https://noometry.com/providers/openai) | 1156 | | [EQ-Bench](https://eqbench.com/) | | | 20 | [MiniMax-M3](https://noometry.com/models/minimax-m3) | [![](/logos/minimax.svg) MiniMax](https://noometry.com/providers/minimax) | 1150 | | [EQ-Bench](https://eqbench.com/) | | | 21 | [Gemini 3.1 Pro Preview](https://noometry.com/models/gemini-3-1-pro-preview) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 1142 | | [EQ-Bench](https://eqbench.com/) | | | 22 | [Gemma 4 31B IT](https://noometry.com/models/gemma-4-31b-it) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 1120 | | [EQ-Bench](https://eqbench.com/) | | | 23 | [Qwen3.7 Max](https://noometry.com/models/qwen3-7-max) | [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 1110 | | [EQ-Bench](https://eqbench.com/) | | | 24 | [Gemini 3.5 Flash](https://noometry.com/models/gemini-3-5-flash) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 1087 | | [EQ-Bench](https://eqbench.com/) | | | 25 | [Grok 4.3](https://noometry.com/models/grok-4-3) | [xAI](https://noometry.com/providers/xai) | 1075 | | [EQ-Bench](https://eqbench.com/) | | | 26 | [Claude Haiku 4.5](https://noometry.com/models/claude-haiku-4-5) | [Anthropic](https://noometry.com/providers/anthropic) | 1064 | | [EQ-Bench](https://eqbench.com/) | | | 27 | [Qwen3.6 27B](https://noometry.com/models/qwen3-6-27b) | [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 1026 | | [EQ-Bench](https://eqbench.com/) | | | 28 | [Mistral Medium 3.5](https://noometry.com/models/mistral-medium-3-5) | [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 993 | | [EQ-Bench](https://eqbench.com/) | | ## Compare the leaders - [Claude Opus 5 vs Claude Fable 5](https://noometry.com/compare/claude-fable-5-vs-claude-opus-5) - [Claude Opus 5 vs Kimi K3](https://noometry.com/compare/claude-opus-5-vs-kimi-k3) - [Claude Opus 5 vs GPT-5.5](https://noometry.com/compare/claude-opus-5-vs-gpt-5-5) - [Claude Opus 5 vs Claude Opus 4.7](https://noometry.com/compare/claude-opus-4-7-vs-claude-opus-5) - [Claude Fable 5 vs Kimi K3](https://noometry.com/compare/claude-fable-5-vs-kimi-k3) - [Claude Fable 5 vs GPT-5.5](https://noometry.com/compare/claude-fable-5-vs-gpt-5-5) ## Other writing & preference benchmarks - [LMArena Text](https://noometry.com/benchmarks/arena-text) - [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) - [Short-Story Creative Writing](https://noometry.com/benchmarks/lech-mazur-writing) - [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) - [WildBench](https://noometry.com/benchmarks/wildbench) - [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) - [LiveBench Language](https://noometry.com/benchmarks/livebench-language) ## Frequently asked questions ### What does EQ-Bench 4 measure? Emotional intelligence in multi-turn role-play conversations, such as building rapport and handling conflict, rated by pairwise LLM-judged comparisons. ### Which model has the highest EQ-Bench 4 score? As of October 2026, Claude Opus 5 has the highest published EQ-Bench 4 score on Noometry at 1385, out of 28 models with results. ### What is the best open-weight model on EQ-Bench 4? Kimi K3 has the highest EQ-Bench 4 rating among open-weight models at 1339, ranking 3 of 28 overall. ### Cite this page Noometry. (2026). EQ-Bench 4 leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/eqbench-4 Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/benchmarks/eqbench-4.md).