Reasoning benchmark

# LiveBench Reasoning leaderboard

> LiveBench Reasoning results for 39 AI models, led by GPT-5.1 at 95.8%. What the benchmark measures, who runs it, and a source for every score.
- Canonical page: https://noometry.com/benchmarks/livebench-reasoning
- Last updated: 2026-10-10
- Title: LiveBench Reasoning Leaderboard (October 2026): Scores by Model

As of October 2026, GPT-5.1 has the highest published LiveBench Reasoning score on Noometry at 95.8%, out of 39 models with results.

Last verified October 10, 2026

## About LiveBench Reasoning

LiveBench reasoning tasks such as logic puzzles, refreshed to limit contamination.

- **Category:** [Reasoning](https://noometry.com/best/reasoning)
- **Introduced:** 2024
- **Unit:** Percent (random guessing ≈ 0%)
- **Official site:** [livebench.ai](https://livebench.ai)

## Top 15 models

Top models on LiveBench Reasoning

1.  GPT-5.1 95.8%
2.  o1 91.6%
3.  Gemini 2.5 Pro 89.8%
4.  o3-mini 89.6%
5.  Claude 3.7 Sonnet 87.8%
6.  QwQ-32B 83.5%
7.  DeepSeek-R1 83.2%
8.  Gemini 2.0 Flash (Feb 2025) 78.2%
9.  o1-mini 72.3%
10.  GPT-4.5 71.1%
11.  DeepSeek-R1-Distill-Llama-70B 67.6%
12.  DeepSeek-V3 65.8%
13.  Gemini 2.0 Pro 60.1%
14.  Claude 3.5 Sonnet 56.7%
15.  GPT-4o 55.8%
16.  405060708090100

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

## All results

LiveBench Reasoning results by model
| # | Model | Provider | Score | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- | --- |
| 1 | [GPT-5.1](https://noometry.com/models/gpt-5-1) | [OpenAI](https://noometry.com/providers/openai) | 95.8% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 2 | [o1](https://noometry.com/models/o1) | [OpenAI](https://noometry.com/providers/openai) | 91.6% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 3 | [Gemini 2.5 Pro](https://noometry.com/models/gemini-2-5-pro) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 89.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 4 | [o3-mini](https://noometry.com/models/o3-mini) | [OpenAI](https://noometry.com/providers/openai) | 89.6% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 5 | [Claude 3.7 Sonnet](https://noometry.com/models/claude-3-7-sonnet) | [Anthropic](https://noometry.com/providers/anthropic) | 87.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 6 | [QwQ-32B](https://noometry.com/models/qwq-32b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 83.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 7 | [DeepSeek-R1](https://noometry.com/models/deepseek-r1) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 83.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 8 | [Gemini 2.0 Flash (Feb 2025)](https://noometry.com/models/gemini-2-0-flash) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 78.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 9 | [o1-mini](https://noometry.com/models/o1-mini) | [OpenAI](https://noometry.com/providers/openai) | 72.3% | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 10 | [GPT-4.5](https://noometry.com/models/gpt-4-5) | [OpenAI](https://noometry.com/providers/openai) | 71.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 11 | [DeepSeek-R1-Distill-Llama-70B](https://noometry.com/models/deepseek-r1-distill-llama-70b) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 67.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 12 | [DeepSeek-V3](https://noometry.com/models/deepseek-v3) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 65.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 13 | [Gemini 2.0 Pro](https://noometry.com/models/gemini-2-0-pro) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 60.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 14 | [Claude 3.5 Sonnet](https://noometry.com/models/claude-3-5-sonnet) | [Anthropic](https://noometry.com/providers/anthropic) | 56.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 15 | [GPT-4o](https://noometry.com/models/gpt-4o) | [OpenAI](https://noometry.com/providers/openai) | 55.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 16 | [Grok-2 (Dec 2024)](https://noometry.com/models/grok-2) | [xAI](https://noometry.com/providers/xai) | 54.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 17 | [DeepSeek-R1-Distill-Qwen-32B](https://noometry.com/models/deepseek-r1-distill-qwen-32b) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 52.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 18 | [Qwen2.5-Max](https://noometry.com/models/qwen2-5-max) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 51.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 19 | [Llama-3.3-70B-Instruct](https://noometry.com/models/llama-3-3-70b-instruct) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 50.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 20 | [Gemini 2.0 Flash-Lite](https://noometry.com/models/gemini-2-0-flash-lite) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 50.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 21 | [Phi-4](https://noometry.com/models/phi-4) |  [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 47.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 22 | [Sonar](https://noometry.com/models/sonar) |  [![](/logos/perplexity.svg) Perplexity](https://noometry.com/providers/perplexity) | 46.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 23 | [Mistral Small](https://noometry.com/models/mistral-small) |  [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 44.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 24 | [Gemma 3 27B](https://noometry.com/models/gemma-3-27b) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 43.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 25 | [Mistral Large](https://noometry.com/models/mistral-large) |  [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 43.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 26 | [Qwen2.5-Coder-32B](https://noometry.com/models/qwen2-5-coder-32b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 42.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 27 | [Claude 3 Opus](https://noometry.com/models/claude-3-opus) | [Anthropic](https://noometry.com/providers/anthropic) | 40.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 28 | [Amazon Nova Lite](https://noometry.com/models/amazon-nova-lite) | [Amazon](https://noometry.com/providers/amazon) | 36.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 29 | [GPT-4o mini](https://noometry.com/models/gpt-4o-mini) | [OpenAI](https://noometry.com/providers/openai) | 32.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 30 | [Amazon Nova Pro](https://noometry.com/models/amazon-nova-pro) | [Amazon](https://noometry.com/providers/amazon) | 32.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 31 | [Claude 3.5 Haiku](https://noometry.com/models/claude-3-5-haiku) | [Anthropic](https://noometry.com/providers/anthropic) | 28.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 32 | [Gemma 2 27B](https://noometry.com/models/gemma-2-27b) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 28.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 33 | [Phi 3 Mini 4k Instruct](https://noometry.com/models/phi-3-mini-4k-instruct) |  [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 26.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 34 | [Amazon Nova Micro](https://noometry.com/models/amazon-nova-micro) | [Amazon](https://noometry.com/providers/amazon) | 25.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 35 | [Command R+](https://noometry.com/models/command-r-plus) |  [![](/logos/cohere.svg) Cohere](https://noometry.com/providers/cohere) | 24.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 36 | [Command R](https://noometry.com/models/command-r) |  [![](/logos/cohere.svg) Cohere](https://noometry.com/providers/cohere) | 21.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 37 | [OLMo 2 Furious 13B](https://noometry.com/models/olmo-2-furious-13b) |  [![](/logos/ai2.svg) Allen Institute for AI (Ai2)](https://noometry.com/providers/ai2) | 16.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 38 | [Phi 3 Small 8k Instruct](https://noometry.com/models/phi-3-small-8k-instruct) |  [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 15.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 39 | [Gemma 2 9B](https://noometry.com/models/gemma-2-9b) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 15.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

## Compare the leaders

-   [GPT-5.1 vs o1](https://noometry.com/compare/gpt-5-1-vs-o1)
-   [GPT-5.1 vs Gemini 2.5 Pro](https://noometry.com/compare/gemini-2-5-pro-vs-gpt-5-1)
-   [GPT-5.1 vs o3-mini](https://noometry.com/compare/gpt-5-1-vs-o3-mini)
-   [GPT-5.1 vs Claude 3.7 Sonnet](https://noometry.com/compare/claude-3-7-sonnet-vs-gpt-5-1)
-   [o1 vs Gemini 2.5 Pro](https://noometry.com/compare/gemini-2-5-pro-vs-o1)
-   [o1 vs o3-mini](https://noometry.com/compare/o1-vs-o3-mini)

## 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)
-   [EBR-Bench](https://noometry.com/benchmarks/ebr-bench)
-   [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles)

## Frequently asked questions

### What does LiveBench Reasoning measure?

LiveBench reasoning tasks such as logic puzzles, refreshed to limit contamination.

### Which model has the highest LiveBench Reasoning score?

As of October 2026, GPT-5.1 has the highest published LiveBench Reasoning score on Noometry at 95.8%, out of 39 models with results.

### What is the best open-weight model on LiveBench Reasoning?

QwQ-32B has the highest LiveBench Reasoning accuracy among open-weight models at 83.5%, ranking 6 of 39 overall.

### Cite this page

Noometry. (2026). LiveBench Reasoning leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/livebench-reasoning

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