Agentic & Tool Use benchmark

# Vending-Bench 2 leaderboard

> Vending-Bench 2 results for 60 AI models, led by GPT-6 Astra at 15,515. What the benchmark measures, who runs it, and a source for every score.
- Canonical page: https://noometry.com/benchmarks/vending-bench-2
- Last updated: 2026-10-10
- Title: Vending-Bench 2 Leaderboard (October 2026): Scores by Model

As of October 2026, GPT-6 Astra has the highest published Vending-Bench 2 score on Noometry at 15,515, out of 60 models with results.

Last verified October 10, 2026

## About Vending-Bench 2

Running a simulated vending-machine business over a long horizon. The score is the final bank balance.

- **Category:** [Agentic & Tool Use](https://noometry.com/best/agentic)
- **Introduced:** 2025
- **Format:** Long-horizon simulation
- **Unit:** Raw score
- **Official site:** [andonlabs.com](https://andonlabs.com/evals/vending-bench)

## Top 15 models

Top models on Vending-Bench 2

1.  GPT-6 Astra 15,515
2.  GPT-6 Sol 14,428
3.  Gemini 4 Argon 13,718
4.  Claude Opus 5 11,182
5.  Claude Opus 4.7 10,937
6.  Grok 4.7 10,537
7.  GPT-5.6 Sol 9,619
8.  Claude Opus 5.5 9,235
9.  Grok 4.6 9,047
10.  GLM-5.2 8,314
11.  GLM-5.3 8,164
12.  Claude Opus 4.6 8,018
13.  GPT-5.5 7,524
14.  GPT-5.6 Terra 7,343
15.  Claude Sonnet 4.6 7,204
16.  05000100001500020000

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

## All results

Vending-Bench 2 results by model
| # | Model | Provider | Rating | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- | --- |
| 1 | [GPT-6 Astra](https://noometry.com/models/gpt-6-astra) | [OpenAI](https://noometry.com/providers/openai) | 15,515 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 2 | [GPT-6 Sol](https://noometry.com/models/gpt-6-sol) | [OpenAI](https://noometry.com/providers/openai) | 14,428 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 3 | [Gemini 4 Argon](https://noometry.com/models/gemini-4-argon) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 13,718 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 4 | [Claude Opus 5](https://noometry.com/models/claude-opus-5) | [Anthropic](https://noometry.com/providers/anthropic) | 11,182 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 5 | [Claude Opus 4.7](https://noometry.com/models/claude-opus-4-7) | [Anthropic](https://noometry.com/providers/anthropic) | 10,937 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 6 | [Grok 4.7](https://noometry.com/models/grok-4-7) | [xAI](https://noometry.com/providers/xai) | 10,537 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 7 | [GPT-5.6 Sol](https://noometry.com/models/gpt-5-6-sol) | [OpenAI](https://noometry.com/providers/openai) | 9,619 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 8 | [Claude Opus 5.5](https://noometry.com/models/claude-opus-5-5) | [Anthropic](https://noometry.com/providers/anthropic) | 9,235 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 9 | [Grok 4.6](https://noometry.com/models/grok-4-6) | [xAI](https://noometry.com/providers/xai) | 9,047 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 10 | [GLM-5.2](https://noometry.com/models/glm-5-2) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 8,314 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 11 | [GLM-5.3](https://noometry.com/models/glm-5-3) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 8,164 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 12 | [Claude Opus 4.6](https://noometry.com/models/claude-opus-4-6) | [Anthropic](https://noometry.com/providers/anthropic) | 8,018 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 13 | [GPT-5.5](https://noometry.com/models/gpt-5-5) | [OpenAI](https://noometry.com/providers/openai) | 7,524 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 14 | [GPT-5.6 Terra](https://noometry.com/models/gpt-5-6-terra) | [OpenAI](https://noometry.com/providers/openai) | 7,343 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 15 | [Claude Sonnet 4.6](https://noometry.com/models/claude-sonnet-4-6) | [Anthropic](https://noometry.com/providers/anthropic) | 7,204 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 16 | [Muse Spark 1.1](https://noometry.com/models/muse-spark-1-1) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 6,520 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 17 | [Claude Sonnet 5](https://noometry.com/models/claude-sonnet-5) | [Anthropic](https://noometry.com/providers/anthropic) | 6,378 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 18 | [Kimi K2.6](https://noometry.com/models/kimi-k2-6) | [Moonshot AI](https://noometry.com/providers/moonshot) | 6,205 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 19 | [GPT-5.4](https://noometry.com/models/gpt-5-4) | [OpenAI](https://noometry.com/providers/openai) | 6,144 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 20 | [GPT-5.3 Codex](https://noometry.com/models/gpt-5-3-codex) | [OpenAI](https://noometry.com/providers/openai) | 5,940 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 21 | [Claude Opus 4.8](https://noometry.com/models/claude-opus-4-8) | [Anthropic](https://noometry.com/providers/anthropic) | 5,787 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 22 | [Claude Fable 5](https://noometry.com/models/claude-fable-5) | [Anthropic](https://noometry.com/providers/anthropic) | 5,680 | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 23 | [GLM-5.1](https://noometry.com/models/glm-5-1) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 5,634 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 24 | [Gemini 3 Pro](https://noometry.com/models/gemini-3-pro) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 5,478 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 25 | [Claude Fable 5.1](https://noometry.com/models/claude-fable-5-1) | [Anthropic](https://noometry.com/providers/anthropic) | 5,422 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 26 | [Gemini 3.5 Flash](https://noometry.com/models/gemini-3-5-flash) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 5,396 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 27 | [Kimi K3](https://noometry.com/models/kimi-k3) | [Moonshot AI](https://noometry.com/providers/moonshot) | 5,165 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 28 | [Qwen3.6 Plus](https://noometry.com/models/qwen3-6-plus) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 5,115 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 29 | [Gemini 3.8 Flash](https://noometry.com/models/gemini-3-8-flash) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 5,094 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 30 | [Kimi K2.7 Code](https://noometry.com/models/kimi-k2-7-code) | [Moonshot AI](https://noometry.com/providers/moonshot) | 5,083 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 31 | [Claude Opus 4.5](https://noometry.com/models/claude-opus-4-5) | [Anthropic](https://noometry.com/providers/anthropic) | 4,967 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 32 | [Grok 4.20 (Non-Reasoning)](https://noometry.com/models/grok-4-20) | [xAI](https://noometry.com/providers/xai) | 4,663 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 33 | [GLM-5](https://noometry.com/models/glm-5) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 4,432 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 34 | [Qwen3.6 Max Preview](https://noometry.com/models/qwen3-6-max-preview) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 4,254 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 35 | [GPT-5.6 Luna](https://noometry.com/models/gpt-5-6-luna) | [OpenAI](https://noometry.com/providers/openai) | 4,095 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 36 | [Grok 4.5](https://noometry.com/models/grok-4-5) | [xAI](https://noometry.com/providers/xai) | 3,887 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 37 | [Claude Sonnet 4.5](https://noometry.com/models/claude-sonnet-4-5) | [Anthropic](https://noometry.com/providers/anthropic) | 3,839 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 38 | [Gemini 3.1 Pro Preview](https://noometry.com/models/gemini-3-1-pro-preview) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 3,774 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 39 | [Gemini 3 Flash Preview](https://noometry.com/models/gemini-3-flash-preview) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 3,635 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 40 | [GPT-5.2](https://noometry.com/models/gpt-5-2) | [OpenAI](https://noometry.com/providers/openai) | 3,591 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 41 | [DeepSeek V4 Pro](https://noometry.com/models/deepseek-v4-pro) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 3,285 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 42 | [GLM-4.7](https://noometry.com/models/glm-4-7) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 2,377 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 43 | [MiniMax-M3](https://noometry.com/models/minimax-m3) |  [![](/logos/minimax.svg) MiniMax](https://noometry.com/providers/minimax) | 2,158 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 44 | [GPT-5.1](https://noometry.com/models/gpt-5-1) | [OpenAI](https://noometry.com/providers/openai) | 1,473 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 45 | [Kimi K2.5](https://noometry.com/models/kimi-k2-5) | [Moonshot AI](https://noometry.com/providers/moonshot) | 1,198 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 46 | [Grok 4.1 Fast](https://noometry.com/models/grok-4-1-fast) | [xAI](https://noometry.com/providers/xai) | 1,107 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 47 | [DeepSeek-V3.2-Exp](https://noometry.com/models/deepseek-v3-2-exp) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 1,034 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 48 | [Gemini 2.5 Pro](https://noometry.com/models/gemini-2-5-pro) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 573.64 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 49 | [Gemini 2.5 Flash](https://noometry.com/models/gemini-2-5-flash) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 548.84 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 50 | [Qwen3.5-Flash](https://noometry.com/models/qwen3-5-flash) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 462.69 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 51 | [Claude Haiku 4.5](https://noometry.com/models/claude-haiku-4-5) | [Anthropic](https://noometry.com/providers/anthropic) | 458.89 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 52 | [Qwen3.5 27B](https://noometry.com/models/qwen3-5-27b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 201.98 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 53 | [MiniMax-M2](https://noometry.com/models/minimax-m2) |  [![](/logos/minimax.svg) MiniMax](https://noometry.com/providers/minimax) | 160.6 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 54 | [Qwen3 Max](https://noometry.com/models/qwen3-max) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 71.56 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 55 | [Grok 4.3](https://noometry.com/models/grok-4-3) | [xAI](https://noometry.com/providers/xai) | 35.26 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 56 | [Qwen3.5 Plus](https://noometry.com/models/qwen3-5-plus) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 0.54 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 57 | [Qwen3 235B-A22B](https://noometry.com/models/qwen3-235b-a22b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | \-11.34 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 58 | [gpt-oss-120b](https://noometry.com/models/gpt-oss-120b) | [OpenAI](https://noometry.com/providers/openai) | \-21.53 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 59 | [MiniMax-M2.5](https://noometry.com/models/minimax-m2-5) |  [![](/logos/minimax.svg) MiniMax](https://noometry.com/providers/minimax) | \-23.16 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 60 | [GPT-5 Mini](https://noometry.com/models/gpt-5-mini) | [OpenAI](https://noometry.com/providers/openai) | \-31.18 |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

## Compare the leaders

-   [GPT-6 Astra vs GPT-6 Sol](https://noometry.com/compare/gpt-6-astra-vs-gpt-6-sol)
-   [GPT-6 Astra vs Gemini 4 Argon](https://noometry.com/compare/gemini-4-argon-vs-gpt-6-astra)
-   [GPT-6 Astra vs Claude Opus 5](https://noometry.com/compare/claude-opus-5-vs-gpt-6-astra)
-   [GPT-6 Astra vs Claude Opus 4.7](https://noometry.com/compare/claude-opus-4-7-vs-gpt-6-astra)
-   [GPT-6 Sol vs Gemini 4 Argon](https://noometry.com/compare/gemini-4-argon-vs-gpt-6-sol)
-   [GPT-6 Sol vs Claude Opus 5](https://noometry.com/compare/claude-opus-5-vs-gpt-6-sol)

## Other agentic & tool use benchmarks

-   [Terminal-Bench](https://noometry.com/benchmarks/terminal-bench)
-   [APEX-Agents](https://noometry.com/benchmarks/apex-agents)
-   [Berkeley Function Calling Leaderboard](https://noometry.com/benchmarks/bfcl)
-   [OSWorld 2.0](https://noometry.com/benchmarks/osworld-2)
-   [GDPval](https://noometry.com/benchmarks/gdpval)
-   [Remote Labor Index](https://noometry.com/benchmarks/remote-labor-index)
-   [TheAgentCompany](https://noometry.com/benchmarks/the-agent-company)
-   [τ²-bench Airline](https://noometry.com/benchmarks/tau2-airline)
-   [τ²-bench Banking](https://noometry.com/benchmarks/tau2-banking)
-   [τ²-bench Retail](https://noometry.com/benchmarks/tau2-retail)
-   [τ²-bench Telecom](https://noometry.com/benchmarks/tau2-telecom)
-   [Cybench](https://noometry.com/benchmarks/cybench)

## Frequently asked questions

### What does Vending-Bench 2 measure?

Running a simulated vending-machine business over a long horizon. The score is the final bank balance.

### Which model has the highest Vending-Bench 2 score?

As of October 2026, GPT-6 Astra has the highest published Vending-Bench 2 score on Noometry at 15,515, out of 60 models with results.

### What is the best open-weight model on Vending-Bench 2?

GLM-5.2 has the highest Vending-Bench 2 score among open-weight models at 8,314, ranking 10 of 60 overall.

### Cite this page

Noometry. (2026). Vending-Bench 2 leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/vending-bench-2

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/benchmarks/vending-bench-2.md).