Reasoning benchmark # EBR-Bench leaderboard > EBR-Bench results for 24 AI models, led by GPT-6 Astra at 76.2%. What the benchmark measures, who runs it, and a source for every score. - Canonical page: https://noometry.com/benchmarks/ebr-bench - Last updated: 2026-10-10 - Title: EBR-Bench Leaderboard (October 2026): Scores by Model As of October 2026, GPT-6 Astra has the highest published EBR-Bench score on Noometry at 76.2%, out of 24 models with results. Last verified October 10, 2026 ## About EBR-Bench A description with primary sources is being prepared for this benchmark. - **Category:** [Reasoning](https://noometry.com/best/reasoning) - **Introduced:** 2026 - **Unit:** Percent (random guessing ≈ 0%) - **Official site:** [epoch.ai](https://epoch.ai/benchmarks) ## Top 15 models Top models on EBR-Bench 1. GPT-6 Astra 76.2% 2. Claude Opus 5.5 71.4% 3. Claude Fable 5.1 57.1% 4. GPT-6.1 Sol 54.3% 5. GPT-6 Sol 53.3% 6. Claude Opus 5 45.7% 7. GPT-5.6 Sol 44.8% 8. Claude Fable 5 39.5% 9. GPT-5.5 34.3% 10. Grok 4.6 30.5% 11. Claude Opus 4.8 28.6% 12. GPT-5.4 25.4% 13. GPT-5.2 23% 14. Claude Opus 4.7 19% 15. Claude Opus 4.5 14.3% 16. 020406080 Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise) ## All results EBR-Bench results by model | # | Model | Provider | Score | Setting | Source | Date | | --- | --- | --- | --- | --- | --- | --- | | 1 | [GPT-6 Astra](https://noometry.com/models/gpt-6-astra) | [OpenAI](https://noometry.com/providers/openai) | 76.2% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-30 | | 2 | [Claude Opus 5.5](https://noometry.com/models/claude-opus-5-5) | [Anthropic](https://noometry.com/providers/anthropic) | 71.4% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-09-22 | | 3 | [Claude Fable 5.1](https://noometry.com/models/claude-fable-5-1) | [Anthropic](https://noometry.com/providers/anthropic) | 57.1% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-09-08 | | 4 | [GPT-6.1 Sol](https://noometry.com/models/gpt-6-1-sol) | [OpenAI](https://noometry.com/providers/openai) | 54.3% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-09-29 | | 5 | [GPT-6 Sol](https://noometry.com/models/gpt-6-sol) | [OpenAI](https://noometry.com/providers/openai) | 53.3% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-09-22 | | 6 | [Claude Opus 5](https://noometry.com/models/claude-opus-5) | [Anthropic](https://noometry.com/providers/anthropic) | 45.7% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-09-05 | | 7 | [GPT-5.6 Sol](https://noometry.com/models/gpt-5-6-sol) | [OpenAI](https://noometry.com/providers/openai) | 44.8% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-09-04 | | 8 | [Claude Fable 5](https://noometry.com/models/claude-fable-5) | [Anthropic](https://noometry.com/providers/anthropic) | 39.5% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-17 | | 9 | [GPT-5.5](https://noometry.com/models/gpt-5-5) | [OpenAI](https://noometry.com/providers/openai) | 34.3% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-27 | | 10 | [Grok 4.6](https://noometry.com/models/grok-4-6) | [xAI](https://noometry.com/providers/xai) | 30.5% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-18 | | 11 | [Claude Opus 4.8](https://noometry.com/models/claude-opus-4-8) | [Anthropic](https://noometry.com/providers/anthropic) | 28.6% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-07 | | 12 | [GPT-5.4](https://noometry.com/models/gpt-5-4) | [OpenAI](https://noometry.com/providers/openai) | 25.4% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-25 | | 13 | [GPT-5.2](https://noometry.com/models/gpt-5-2) | [OpenAI](https://noometry.com/providers/openai) | 23% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-26 | | 14 | [Claude Opus 4.7](https://noometry.com/models/claude-opus-4-7) | [Anthropic](https://noometry.com/providers/anthropic) | 19% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-30 | | 15 | [Claude Opus 4.5](https://noometry.com/models/claude-opus-4-5) | [Anthropic](https://noometry.com/providers/anthropic) | 14.3% | 128K | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-25 | | 16 | [Gemini 3.1 Pro Preview](https://noometry.com/models/gemini-3-1-pro-preview) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 14.3% | | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-25 | | 17 | [Claude Opus 4.6](https://noometry.com/models/claude-opus-4-6) | [Anthropic](https://noometry.com/providers/anthropic) | 12.7% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-29 | | 18 | [GPT-5](https://noometry.com/models/gpt-5) | [OpenAI](https://noometry.com/providers/openai) | 12.7% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-29 | | 19 | [GLM-5.2](https://noometry.com/models/glm-5-2) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 9.5% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-29 | | 20 | [Qwen3.7 Max](https://noometry.com/models/qwen3-7-max) | [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 9.5% | | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-25 | | 21 | [Claude Opus 4.1](https://noometry.com/models/claude-opus-4-1) | [Anthropic](https://noometry.com/providers/anthropic) | 7.9% | | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-25 | | 22 | [Gemini 3.5 Flash](https://noometry.com/models/gemini-3-5-flash) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 4.8% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-25 | | 23 | [Claude Sonnet 4.5](https://noometry.com/models/claude-sonnet-4-5) | [Anthropic](https://noometry.com/providers/anthropic) | 2.4% | | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-25 | | 24 | [Kimi K2.6](https://noometry.com/models/kimi-k2-6) | [Moonshot AI](https://noometry.com/providers/moonshot) | 2.4% | | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-25 | ## Compare the leaders - [GPT-6 Astra vs Claude Opus 5.5](https://noometry.com/compare/claude-opus-5-5-vs-gpt-6-astra) - [GPT-6 Astra vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-gpt-6-astra) - [GPT-6 Astra vs GPT-6.1 Sol](https://noometry.com/compare/gpt-6-1-sol-vs-gpt-6-astra) - [GPT-6 Astra vs GPT-6 Sol](https://noometry.com/compare/gpt-6-astra-vs-gpt-6-sol) - [Claude Opus 5.5 vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-claude-opus-5-5) - [Claude Opus 5.5 vs GPT-6.1 Sol](https://noometry.com/compare/claude-opus-5-5-vs-gpt-6-1-sol) ## Other reasoning benchmarks - [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) - [SimpleBench](https://noometry.com/benchmarks/simplebench) - [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) - [NYT Connections (extended)](https://noometry.com/benchmarks/nyt-connections) - [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) - [CritPt](https://noometry.com/benchmarks/critpt) - [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) - [EnigmaEval](https://noometry.com/benchmarks/enigmaeval) - [Thematic Generalization](https://noometry.com/benchmarks/thematic-generalization) - [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) - [LiveBench Reasoning](https://noometry.com/benchmarks/livebench-reasoning) - [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) ## Frequently asked questions ### Which model has the highest EBR-Bench score? As of October 2026, GPT-6 Astra has the highest published EBR-Bench score on Noometry at 76.2%, out of 24 models with results. ### What is the best open-weight model on EBR-Bench? GLM-5.2 has the highest EBR-Bench accuracy among open-weight models at 9.5%, ranking 19 of 24 overall. ### Cite this page Noometry. (2026). EBR-Bench leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/ebr-bench Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/benchmarks/ebr-bench.md).