Knowledge benchmark # OpenBookQA leaderboard > OpenBookQA results for 19 AI models, led by Phi 3 Mini 4k Instruct at 88%. What the benchmark measures, who runs it, and a source for every score. - Canonical page: https://noometry.com/benchmarks/openbookqa - Last updated: 2026-10-10 - Title: OpenBookQA Leaderboard (October 2026): Scores by Model As of October 2026, Phi 3 Mini 4k Instruct has the highest published OpenBookQA score on Noometry at 88%, out of 19 models with results. Last verified October 10, 2026 ## About OpenBookQA Elementary science questions that require combining a given fact with common knowledge. - **Category:** [Knowledge](https://noometry.com/best/knowledge) - **Introduced:** 2018 - **Format:** Multiple choice - **Unit:** Percent (random guessing ≈ 25%) - **Official site:** [allenai.org](https://allenai.org/data/open-book-qa) ## Top 15 models Top models on OpenBookQA 1. Phi 3 Mini 4k Instruct 88% 2. Phi 3 Small 8k Instruct 88% 3. phi-3-medium 14B 87.4% 4. GPT-3.5-turbo 86% 5. Mixtral 8x7B 85.8% 6. Llama 3-8B 82.6% 7. Mistral 7B 79.8% 8. Gemma 7B 78.6% 9. Phi-2 73.6% 10. Falcon-180B 64.2% 11. Llama 2-70B 60.2% 12. Llama 2-7B 58.6% 13. Llama 2-34B 58.2% 14. Llama 2-13B 57% 15. Falcon-40B 56.6% 16. 5060708090 Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise) ## All results OpenBookQA results by model | # | Model | Provider | Score | Setting | Source | Date | | --- | --- | --- | --- | --- | --- | --- | | 1 | [Phi 3 Mini 4k Instruct](https://noometry.com/models/phi-3-mini-4k-instruct) | [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 88% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 2 | [Phi 3 Small 8k Instruct](https://noometry.com/models/phi-3-small-8k-instruct) | [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 88% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 3 | [phi-3-medium 14B](https://noometry.com/models/phi-3-medium-14b) | [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 87.4% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 4 | [GPT-3.5-turbo](https://noometry.com/models/gpt-3-5-turbo) | [OpenAI](https://noometry.com/providers/openai) | 86% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 5 | [Mixtral 8x7B](https://noometry.com/models/mixtral-8x7b) | [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 85.8% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 6 | [Llama 3-8B](https://noometry.com/models/llama-3-8b) | [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 82.6% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 7 | [Mistral 7B](https://noometry.com/models/mistral-7b) | [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 79.8% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 8 | [Gemma 7B](https://noometry.com/models/gemma-7b) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 78.6% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 9 | [Phi-2](https://noometry.com/models/phi-2) | [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 73.6% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 10 | [Falcon-180B](https://noometry.com/models/falcon-180b) | [![](/logos/tii.svg) Technology Innovation Institute](https://noometry.com/providers/tii) | 64.2% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 11 | [Llama 2-70B](https://noometry.com/models/llama-2-70b) | [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 60.2% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 12 | [Llama 2-7B](https://noometry.com/models/llama-2-7b) | [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 58.6% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 13 | [Llama 2-34B](https://noometry.com/models/llama-2-34b) | [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 58.2% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 14 | [Llama 2-13B](https://noometry.com/models/llama-2-13b) | [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 57% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 15 | [Falcon-40B](https://noometry.com/models/falcon-40b) | [![](/logos/tii.svg) Technology Innovation Institute](https://noometry.com/providers/tii) | 56.6% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 16 | [Llama 13b](https://noometry.com/models/llama-13b) | [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 56.4% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 17 | [Falcon-7B](https://noometry.com/models/falcon-7b) | [![](/logos/tii.svg) Technology Innovation Institute](https://noometry.com/providers/tii) | 51.6% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 18 | [Dolly 2.0-12b](https://noometry.com/models/dolly-2-0-12b) | [![](/logos/databricks.svg) Databricks](https://noometry.com/providers/databricks) | 39.2% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 19 | [Phi-1.5](https://noometry.com/models/phi-1-5) | [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 37.2% | 5 | [Epoch AI](https://epoch.ai/benchmarks) | | ## Compare the leaders - [Phi 3 Mini 4k Instruct vs Phi 3 Small 8k Instruct](https://noometry.com/compare/phi-3-mini-4k-instruct-vs-phi-3-small-8k-instruct) - [Phi 3 Mini 4k Instruct vs phi-3-medium 14B](https://noometry.com/compare/phi-3-medium-14b-vs-phi-3-mini-4k-instruct) - [Phi 3 Mini 4k Instruct vs GPT-3.5-turbo](https://noometry.com/compare/gpt-3-5-turbo-vs-phi-3-mini-4k-instruct) - [Phi 3 Mini 4k Instruct vs Mixtral 8x7B](https://noometry.com/compare/mixtral-8x7b-vs-phi-3-mini-4k-instruct) - [Phi 3 Small 8k Instruct vs phi-3-medium 14B](https://noometry.com/compare/phi-3-medium-14b-vs-phi-3-small-8k-instruct) - [Phi 3 Small 8k Instruct vs GPT-3.5-turbo](https://noometry.com/compare/gpt-3-5-turbo-vs-phi-3-small-8k-instruct) ## Other knowledge benchmarks - [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) - [Humanity's Last Exam](https://noometry.com/benchmarks/hle) - [SimpleQA Verified](https://noometry.com/benchmarks/simpleqa-verified) - [MMLU-Pro](https://noometry.com/benchmarks/mmlu-pro) - [Confabulations](https://noometry.com/benchmarks/confabulations) - [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination) - [LMArena Expert](https://noometry.com/benchmarks/arena-expert) - [GPQA (HELM)](https://noometry.com/benchmarks/helm-gpqa) - [ARC (AI2) Challenge](https://noometry.com/benchmarks/arc-challenge) (reference) - [BoolQ](https://noometry.com/benchmarks/boolq) (reference) - [MMLU](https://noometry.com/benchmarks/mmlu) (reference) - [TriviaQA](https://noometry.com/benchmarks/triviaqa) (reference) ## Frequently asked questions ### What does OpenBookQA measure? Elementary science questions that require combining a given fact with common knowledge. ### Which model has the highest OpenBookQA score? As of October 2026, Phi 3 Mini 4k Instruct has the highest published OpenBookQA score on Noometry at 88%, out of 19 models with results. ### What is the best open-weight model on OpenBookQA? Phi 3 Mini 4k Instruct has the highest OpenBookQA accuracy among open-weight models at 88%, ranking 1 of 19 overall. ### Cite this page Noometry. (2026). OpenBookQA leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/openbookqa Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/benchmarks/openbookqa.md).