Knowledge benchmark

# ARC (AI2) Challenge leaderboard

> ARC (AI2) Challenge results for 39 AI models, led by DeepSeek-V3 at 95.3%. What the benchmark measures, who runs it, and a source for every score.
- Canonical page: https://noometry.com/benchmarks/arc-challenge
- Last updated: 2026-10-10
- Title: ARC (AI2) Challenge Leaderboard (October 2026): Scores by Model

As of October 2026, DeepSeek-V3 has the highest published ARC (AI2) Challenge score on Noometry at 95.3%, out of 39 models with results.

Last verified October 10, 2026

## About ARC (AI2) Challenge

Grade-school science multiple-choice questions that retrieval alone cannot answer.

- **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/arc)

## Top 15 models

Top models on ARC (AI2) Challenge

1.  DeepSeek-V3 95.3%
2.  Llama 3.1-405B 95.3%
3.  Qwen2.5 72B Instruct 94.5%
4.  DeepSeek-V2 (MoE-236B, May 2024) 92.2%
5.  phi-3-medium 14B 91.6%
6.  Phi 3 Small 8k Instruct 90.7%
7.  GPT-3.5-turbo 87.4%
8.  Mixtral 8x7B 87.3%
9.  Claude Instant 86.3%
10.  Phi 3 Mini 4k Instruct 84.9%
11.  Qwen-14B 84.4%
12.  Llama 3-8B 82.8%
13.  Mistral 7B 78.6%
14.  Gemma 7B 78.3%
15.  Llama 2-70B 78.3%
16.  7580859095100

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## All results

ARC (AI2) Challenge results by model
| # | Model | Provider | Score | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- | --- |
| 1 | [DeepSeek-V3](https://noometry.com/models/deepseek-v3) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 95.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 2 | [Llama 3.1-405B](https://noometry.com/models/llama-3-1-405b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 95.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 3 | [Qwen2.5 72B Instruct](https://noometry.com/models/qwen2-5-72b-instruct) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 94.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 4 | [DeepSeek-V2 (MoE-236B, May 2024)](https://noometry.com/models/deepseek-v2) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 92.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 5 | [phi-3-medium 14B](https://noometry.com/models/phi-3-medium-14b) |  [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 91.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 6 | [Phi 3 Small 8k Instruct](https://noometry.com/models/phi-3-small-8k-instruct) |  [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 90.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 7 | [GPT-3.5-turbo](https://noometry.com/models/gpt-3-5-turbo) | [OpenAI](https://noometry.com/providers/openai) | 87.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 8 | [Mixtral 8x7B](https://noometry.com/models/mixtral-8x7b) |  [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 87.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 9 | [Claude Instant](https://noometry.com/models/claude-instant) | [Anthropic](https://noometry.com/providers/anthropic) | 86.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 10 | [Phi 3 Mini 4k Instruct](https://noometry.com/models/phi-3-mini-4k-instruct) |  [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 84.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 11 | [Qwen-14B](https://noometry.com/models/qwen-14b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 84.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 12 | [Llama 3-8B](https://noometry.com/models/llama-3-8b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 82.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 13 | [Mistral 7B](https://noometry.com/models/mistral-7b) |  [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 78.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 14 | [Gemma 7B](https://noometry.com/models/gemma-7b) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 78.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 15 | [Llama 2-70B](https://noometry.com/models/llama-2-70b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 78.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 16 | [Phi-2](https://noometry.com/models/phi-2) |  [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 75.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 17 | [Qwen-7B](https://noometry.com/models/qwen-7b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 75.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 18 | [Qwen2.5-Coder-32B](https://noometry.com/models/qwen2-5-coder-32b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 70.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 19 | [Falcon-180B](https://noometry.com/models/falcon-180b) |  [![](/logos/tii.svg) Technology Innovation Institute](https://noometry.com/providers/tii) | 67.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 20 | [Deepseek Coder v2](https://noometry.com/models/deepseek-coder-v2) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 64.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 21 | [Falcon-40B](https://noometry.com/models/falcon-40b) |  [![](/logos/tii.svg) Technology Innovation Institute](https://noometry.com/providers/tii) | 61.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 22 | [Qwen2.5-Coder (1.5B)](https://noometry.com/models/qwen2-5-coder) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 60.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 23 | [Llama 2-13B](https://noometry.com/models/llama-2-13b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 60.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 24 | [Nemotron-4 15B](https://noometry.com/models/nemotron-4-15b) |  [![](/logos/nvidia.svg) NVIDIA](https://noometry.com/providers/nvidia) | 55.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 25 | [INTELLECT-1](https://noometry.com/models/intellect-1) |  [![](/logos/huggingface.svg) Hugging Face](https://noometry.com/providers/huggingface) | 54.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 26 | [Llama 2-34B](https://noometry.com/models/llama-2-34b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 54.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 27 | [Llama 13b](https://noometry.com/models/llama-13b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 52.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 28 | [Yi 6B](https://noometry.com/models/yi-6b) | [01.AI](https://noometry.com/providers/01-ai) | 50.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 29 | [Falcon-7B](https://noometry.com/models/falcon-7b) |  [![](/logos/tii.svg) Technology Innovation Institute](https://noometry.com/providers/tii) | 47.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 30 | [StarCoder 2 15B](https://noometry.com/models/starcoder-2-15b) |  [![](/logos/nvidia.svg) NVIDIA](https://noometry.com/providers/nvidia) | 47.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 31 | [Llama 2-7B](https://noometry.com/models/llama-2-7b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 45.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 32 | [Phi-1.5](https://noometry.com/models/phi-1-5) |  [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 44.4% | 5 | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 33 | [DeepSeek Coder 33B](https://noometry.com/models/deepseek-coder-33b) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 42.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 34 | [Gemma 2B](https://noometry.com/models/gemma-2b) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 42.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 35 | [Dolly 2.0-12b](https://noometry.com/models/dolly-2-0-12b) |  [![](/logos/databricks.svg) Databricks](https://noometry.com/providers/databricks) | 39.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 36 | [StarCoder 2 7B](https://noometry.com/models/starcoder-2-7b) |  [![](/logos/nvidia.svg) NVIDIA](https://noometry.com/providers/nvidia) | 38.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 37 | [DeepSeek Coder 6.7B](https://noometry.com/models/deepseek-coder-6-7b) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 36.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 38 | [StarCoder 2 3B](https://noometry.com/models/starcoder-2-3b) |  [![](/logos/nvidia.svg) NVIDIA](https://noometry.com/providers/nvidia) | 34.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 39 | [DeepSeek Coder 1.3B](https://noometry.com/models/deepseek-coder-1-3b) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 25.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

## Compare the leaders

-   [DeepSeek-V3 vs Llama 3.1-405B](https://noometry.com/compare/deepseek-v3-vs-llama-3-1-405b)
-   [DeepSeek-V3 vs Qwen2.5 72B Instruct](https://noometry.com/compare/deepseek-v3-vs-qwen2-5-72b-instruct)
-   [DeepSeek-V3 vs DeepSeek-V2 (MoE-236B, May 2024)](https://noometry.com/compare/deepseek-v2-vs-deepseek-v3)
-   [DeepSeek-V3 vs phi-3-medium 14B](https://noometry.com/compare/deepseek-v3-vs-phi-3-medium-14b)
-   [Llama 3.1-405B vs Qwen2.5 72B Instruct](https://noometry.com/compare/llama-3-1-405b-vs-qwen2-5-72b-instruct)
-   [Llama 3.1-405B vs DeepSeek-V2 (MoE-236B, May 2024)](https://noometry.com/compare/deepseek-v2-vs-llama-3-1-405b)

## 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)
-   [BoolQ](https://noometry.com/benchmarks/boolq) (reference)
-   [MMLU](https://noometry.com/benchmarks/mmlu) (reference)
-   [OpenBookQA](https://noometry.com/benchmarks/openbookqa) (reference)
-   [TriviaQA](https://noometry.com/benchmarks/triviaqa) (reference)

## Frequently asked questions

### What does ARC (AI2) Challenge measure?

Grade-school science multiple-choice questions that retrieval alone cannot answer.

### Which model has the highest ARC (AI2) Challenge score?

As of October 2026, DeepSeek-V3 has the highest published ARC (AI2) Challenge score on Noometry at 95.3%, out of 39 models with results.

### What is the best open-weight model on ARC (AI2) Challenge?

DeepSeek-V3 has the highest ARC (AI2) Challenge accuracy among open-weight models at 95.3%, ranking 1 of 39 overall.

### Cite this page

Noometry. (2026). ARC (AI2) Challenge leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/arc-challenge

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/benchmarks/arc-challenge.md).