Long Context benchmark # CL-bench leaderboard > CL-bench results for 19 AI models, led by GPT-5.4 at 27.9%. What the benchmark measures, who runs it, and a source for every score. - Canonical page: https://noometry.com/benchmarks/cl-bench - Last updated: 2026-10-10 - Title: CL-bench Leaderboard (October 2026): Scores by Model As of October 2026, GPT-5.4 has the highest published CL-bench score on Noometry at 27.9%, out of 19 models with results. Last verified October 10, 2026 ## About CL-bench A description with primary sources is being prepared for this benchmark. - **Category:** [Long Context](https://noometry.com/best/long-context) - **Introduced:** 2026 - **Unit:** Percent (random guessing ≈ 0%) - **Official site:** [epoch.ai](https://epoch.ai/benchmarks) ## Top 15 models Top models on CL-bench 1. GPT-5.4 27.9% 2. GPT-5.1 23.7% 3. Grok 4.20 (Non-Reasoning) 22.2% 4. Claude Opus 4.5 21.1% 5. Gemini 3.1 Pro Preview 20.8% 6. Claude Opus 4.6 20.7% 7. Qwen3.6 Plus 20.3% 8. Qwen3.5 Plus 19.8% 9. Kimi K2.5 19.3% 10. GLM-5 18.7% 11. GPT-5.2 18.2% 12. o3 17.8% 13. Kimi K2 (Jul 2025) 17.6% 14. GLM-4.7 15.9% 15. Gemini 3 Pro 15.8% 16. 1015202530 Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise) ## All results CL-bench results by model | # | Model | Provider | Score | Setting | Source | Date | | --- | --- | --- | --- | --- | --- | --- | | 1 | [GPT-5.4](https://noometry.com/models/gpt-5-4) | [OpenAI](https://noometry.com/providers/openai) | 27.9% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | | | 2 | [GPT-5.1](https://noometry.com/models/gpt-5-1) | [OpenAI](https://noometry.com/providers/openai) | 23.7% | high | [Epoch AI](https://epoch.ai/benchmarks) | | | 3 | [Grok 4.20 (Non-Reasoning)](https://noometry.com/models/grok-4-20) | [xAI](https://noometry.com/providers/xai) | 22.2% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 4 | [Claude Opus 4.5](https://noometry.com/models/claude-opus-4-5) | [Anthropic](https://noometry.com/providers/anthropic) | 21.1% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 5 | [Gemini 3.1 Pro Preview](https://noometry.com/models/gemini-3-1-pro-preview) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 20.8% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 6 | [Claude Opus 4.6](https://noometry.com/models/claude-opus-4-6) | [Anthropic](https://noometry.com/providers/anthropic) | 20.7% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 7 | [Qwen3.6 Plus](https://noometry.com/models/qwen3-6-plus) | [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 20.3% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 8 | [Qwen3.5 Plus](https://noometry.com/models/qwen3-5-plus) | [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 19.8% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 9 | [Kimi K2.5](https://noometry.com/models/kimi-k2-5) | [Moonshot AI](https://noometry.com/providers/moonshot) | 19.3% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 10 | [GLM-5](https://noometry.com/models/glm-5) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 18.7% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 11 | [GPT-5.2](https://noometry.com/models/gpt-5-2) | [OpenAI](https://noometry.com/providers/openai) | 18.2% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 12 | [o3](https://noometry.com/models/o3) | [OpenAI](https://noometry.com/providers/openai) | 17.8% | high | [Epoch AI](https://epoch.ai/benchmarks) | | | 13 | [Kimi K2 (Jul 2025)](https://noometry.com/models/kimi-k2) | [Moonshot AI](https://noometry.com/providers/moonshot) | 17.6% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 14 | [GLM-4.7](https://noometry.com/models/glm-4-7) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 15.9% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 15 | [Gemini 3 Pro](https://noometry.com/models/gemini-3-pro) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 15.8% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 16 | [MiMo-V2-Pro](https://noometry.com/models/mimo-v2-pro) | [Xiaomi](https://noometry.com/providers/xiaomi) | 15.7% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 17 | [Qwen3 Max](https://noometry.com/models/qwen3-max) | [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 14.5% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 18 | [DeepSeek-V3.2-Exp](https://noometry.com/models/deepseek-v3-2-exp) | [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 13.2% | thinking | [Epoch AI](https://epoch.ai/benchmarks) | | | 19 | [MiniMax-M2.5](https://noometry.com/models/minimax-m2-5) | [![](/logos/minimax.svg) MiniMax](https://noometry.com/providers/minimax) | 11.4% | | [Epoch AI](https://epoch.ai/benchmarks) | | ## Compare the leaders - [GPT-5.4 vs GPT-5.1](https://noometry.com/compare/gpt-5-1-vs-gpt-5-4) - [GPT-5.4 vs Grok 4.20 (Non-Reasoning)](https://noometry.com/compare/gpt-5-4-vs-grok-4-20) - [GPT-5.4 vs Claude Opus 4.5](https://noometry.com/compare/claude-opus-4-5-vs-gpt-5-4) - [GPT-5.4 vs Gemini 3.1 Pro Preview](https://noometry.com/compare/gemini-3-1-pro-preview-vs-gpt-5-4) - [GPT-5.1 vs Grok 4.20 (Non-Reasoning)](https://noometry.com/compare/gpt-5-1-vs-grok-4-20) - [GPT-5.1 vs Claude Opus 4.5](https://noometry.com/compare/claude-opus-4-5-vs-gpt-5-1) ## Other long context benchmarks - [Fiction.LiveBench](https://noometry.com/benchmarks/fiction-livebench) - [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) - [CL-bench Life](https://noometry.com/benchmarks/cl-bench-life) ## Frequently asked questions ### Which model has the highest CL-bench score? As of October 2026, GPT-5.4 has the highest published CL-bench score on Noometry at 27.9%, out of 19 models with results. ### What is the best open-weight model on CL-bench? Kimi K2.5 has the highest CL-bench accuracy among open-weight models at 19.3%, ranking 9 of 19 overall. ### Cite this page Noometry. (2026). CL-bench leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/cl-bench Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/benchmarks/cl-bench.md).