# Gert Labs leaderboard

Agentic benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/agentic-gert-labs

Gert Labs Composite Game Benchmark. Every model the catalog carries a published Gert Labs value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Composite game leaderboard |
| Tasks | Novel game environments |
| Difficulty | Agentic coding and decision-making |
| Published by | [Gert Labs rankings](https://gertlabs.com/rankings) |

A game-environment benchmark that evaluates AI models in novel games covering strategic planning, resource management, spatial reasoning, cooperation, and theory of mind.

## Gert Labs ranking

52 models with a published Gert Labs value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Composite game leaderboard | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Opus 4.8](https://modelscale.dev/models/claude-opus-4-8) | Anthropic | 72.97 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-5.5](https://modelscale.dev/models/gpt-5-5) | OpenAI | 72.93 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Opus 4.7](https://modelscale.dev/models/claude-opus-4-7) | Anthropic | 65.59 | Observed 2026-11-21 · source benchlm:models |
| 4 | [GPT-5.4](https://modelscale.dev/models/gpt-5-4) | OpenAI | 64.89 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Qwen3.7 Max](https://modelscale.dev/models/qwen3-7-max) | Alibaba | 64.27 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | 64.23 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Gemini 3 Pro](https://modelscale.dev/models/gemini-3-pro) | Google | 63.23 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Claude Sonnet 4.6](https://modelscale.dev/models/claude-sonnet-4-6) | Anthropic | 62.92 | Observed 2026-11-21 · source benchlm:models |
| 9 | [MiMo-V2.5-Pro](https://modelscale.dev/models/mimo-v2-5-pro) | Xiaomi | 62.70 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Claude Opus 4.6](https://modelscale.dev/models/claude-opus-4-6) | Anthropic | 61.85 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Gemini 3.5 Flash](https://modelscale.dev/models/gemini-3-5-flash) | Google | 61.85 | Observed 2026-11-21 · source benchlm:models |
| 12 | [GLM-5.1](https://modelscale.dev/models/glm-5-1) | Z.AI | 60.11 | Observed 2026-11-21 · source benchlm:models |
| 13 | [GPT-5.3 Codex](https://modelscale.dev/models/gpt-5-3-codex) | OpenAI | 57.47 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Gemini 3.1 Pro](https://modelscale.dev/models/gemini-3-1-pro) | Google | 56.87 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Kimi K2.6](https://modelscale.dev/models/kimi-2-6) | Moonshot AI | 56.82 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Gemini 3 Flash](https://modelscale.dev/models/gemini-3-flash) | Google | 56.63 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Qwen3.6-27B](https://modelscale.dev/models/qwen3-6-27b) | Alibaba | 54.84 | Observed 2026-11-21 · source benchlm:models |
| 18 | [GPT-5.2-Codex](https://modelscale.dev/models/gpt-5-2-codex) | OpenAI | 51.79 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Step 3.7 Flash](https://modelscale.dev/models/step-3-7-flash) | StepFun | 51.57 | Observed 2026-11-21 · source benchlm:models |
| 20 | [GLM-5](https://modelscale.dev/models/glm-5) | Z.AI | 50.99 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Qwen3.6 Plus](https://modelscale.dev/models/qwen3-6-plus) | Alibaba | 50.60 | Observed 2026-11-21 · source benchlm:models |
| 22 | [GPT-5.1-Codex](https://modelscale.dev/models/gpt-5-1-codex) | OpenAI | 49.68 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Grok Build 0.1](https://modelscale.dev/models/grok-build-0-1) | xAI | 49.15 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Claude Sonnet 4.5](https://modelscale.dev/models/claude-sonnet-4-5) | Anthropic | 48.51 | Observed 2026-11-21 · source benchlm:models |
| 25 | [Grok 4.1 Fast](https://modelscale.dev/models/grok-4-1-fast) | xAI | 47.32 | Observed 2026-11-21 · source benchlm:models |
| 26 | [MiMo-V2.5](https://modelscale.dev/models/mimo-v2-5) | Xiaomi | 46.89 | Observed 2026-11-21 · source benchlm:models |
| 27 | [Qwen3.5 397B](https://modelscale.dev/models/qwen3-5-397b) | Alibaba | 46.76 | Observed 2026-11-21 · source benchlm:models |
| 28 | [GPT-5.2](https://modelscale.dev/models/gpt-5-2) | OpenAI | 46.54 | Observed 2026-11-21 · source benchlm:models |
| 29 | [Kimi K2.5](https://modelscale.dev/models/kimi-k2-5) | Moonshot AI | 45.88 | Observed 2026-11-21 · source benchlm:models |
| 30 | [Grok 4.3](https://modelscale.dev/models/grok-4-3) | xAI | 43.86 | Observed 2026-11-21 · source benchlm:models |
| 31 | [Qwen3 Max](https://modelscale.dev/models/qwen3-max) | Alibaba | 43.74 | Observed 2026-11-21 · source benchlm:models |
| 32 | [Qwen3.6-35B-A3B](https://modelscale.dev/models/qwen3-6-35b-a3b) | Alibaba | 42.65 | Observed 2026-11-21 · source benchlm:models |
| 33 | [Grok 4](https://modelscale.dev/models/grok-4) | xAI | 42.34 | Observed 2026-11-21 · source benchlm:models |
| 34 | [Gemini 2.5 Pro](https://modelscale.dev/models/gemini-2-5-pro) | Google | 42.01 | Observed 2026-11-21 · source benchlm:models |
| 35 | [GPT-5.1](https://modelscale.dev/models/gpt-5-1) | OpenAI | 41.24 | Observed 2026-11-21 · source benchlm:models |
| 36 | [MiniMax M2.7](https://modelscale.dev/models/minimax-m2-7) | MiniMax | 40.40 | Observed 2026-11-21 · source benchlm:models |
| 37 | [GLM-4.7](https://modelscale.dev/models/glm-4-7) | Z.AI | 39.95 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Claude 4 Sonnet](https://modelscale.dev/models/claude-4-sonnet) | Anthropic | 39.66 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Qwen3.5-27B](https://modelscale.dev/models/qwen3-5-27b) | Alibaba | 39.41 | Observed 2026-11-21 · source benchlm:models |
| 40 | [Mistral Medium 3.5 128B](https://modelscale.dev/models/mistral-medium-3-5-128b) | Mistral | 39.10 | Observed 2026-11-21 · source benchlm:models |
| 41 | [Gemini 3.1 Flash-Lite](https://modelscale.dev/models/gemini-3-1-flash-lite) | Google | 38.46 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Grok 4.20](https://modelscale.dev/models/grok-4-20-beta) | xAI | 38.36 | Observed 2026-11-21 · source benchlm:models |
| 43 | [Hy3 Preview](https://modelscale.dev/models/hy3-preview) | Tencent | 36.91 | Observed 2026-11-21 · source benchlm:models |
| 44 | [MiMo-V2-Pro](https://modelscale.dev/models/mimo-v2-pro) | Xiaomi | 36.68 | Observed 2026-11-21 · source benchlm:models |
| 45 | [Gemma 4 31B](https://modelscale.dev/models/gemma-4-31b) | Google | 35.26 | Observed 2026-11-21 · source benchlm:models |
| 46 | [Kimi K2.5 (Reasoning)](https://modelscale.dev/models/kimi-k2-5-reasoning) | Moonshot AI | 32.58 | Last good 2026-11-18 · source benchlm:models |
| 47 | [Trinity-Large-Thinking](https://modelscale.dev/models/trinity-large-thinking) | Arcee AI | 32.55 | Observed 2026-11-21 · source benchlm:models |
| 48 | [GLM-5V-Turbo](https://modelscale.dev/models/glm-5v-turbo) | Z.AI | 30.76 | Observed 2026-11-21 · source benchlm:models |
| 49 | [GPT-OSS 120B](https://modelscale.dev/models/gpt-oss-120b) | OpenAI | 29.61 | Observed 2026-11-21 · source benchlm:models |
| 50 | [DeepSeek V3.2](https://modelscale.dev/models/deepseek-v3-2) | DeepSeek | 29.57 | Observed 2026-11-21 · source benchlm:models |
| 51 | [Qwen3.5-35B-A3B](https://modelscale.dev/models/qwen3-5-35b-a3b) | Alibaba | 28.96 | Observed 2026-11-21 · source benchlm:models |
| 52 | [GPT-4.1](https://modelscale.dev/models/gpt-4-1) | OpenAI | 25.65 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
