Agentic benchmark
Gert Labs leaderboard
Gert Labs Composite Game Benchmark. Every model the catalog carries a published Gert Labs value for, ranked by that value.
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 |
|---|---|---|---|
| 1 |  Claude Opus 4.8 | Anthropic | 72.97 |
| 2 |  GPT-5.5 | OpenAI | 72.93 |
| 3 | Claude Opus 4.7 | Anthropic | 65.59 |
| 4 | GPT-5.4 | OpenAI | 64.89 |
| 5 |  Qwen3.7 Max | Alibaba | 64.27 |
| 6 | Claude Opus 4.5 | Anthropic | 64.23 |
| 7 |  Gemini 3 Pro | 63.23 | |
| 8 | Claude Sonnet 4.6 | Anthropic | 62.92 |
| 9 |  MiMo-V2.5-Pro | Xiaomi | 62.70 |
| 10 | Claude Opus 4.6 | Anthropic | 61.85 |
| 10 | Gemini 3.5 Flash | 61.85 | |
| 12 |  GLM-5.1 | Z.AI | 60.11 |
| 13 | GPT-5.3 Codex | OpenAI | 57.47 |
| 14 | Gemini 3.1 Pro | 56.87 | |
| 15 |  Kimi K2.6 | Moonshot AI | 56.82 |
| 16 | Gemini 3 Flash | 56.63 | |
| 17 | Qwen3.6-27B | Alibaba | 54.84 |
| 18 | GPT-5.2-Codex | OpenAI | 51.79 |
| 19 |  Step 3.7 Flash | StepFun | 51.57 |
| 20 | GLM-5 | Z.AI | 50.99 |
| 21 | Qwen3.6 Plus | Alibaba | 50.60 |
| 22 | GPT-5.1-Codex | OpenAI | 49.68 |
| 23 |  Grok Build 0.1 | xAI | 49.15 |
| 24 | Claude Sonnet 4.5 | Anthropic | 48.51 |
| 25 | Grok 4.1 Fast | xAI | 47.32 |
| 26 | MiMo-V2.5 | Xiaomi | 46.89 |
| 27 | Qwen3.5 397B | Alibaba | 46.76 |
| 28 | GPT-5.2 | OpenAI | 46.54 |
| 29 | Kimi K2.5 | Moonshot AI | 45.88 |
| 30 | Grok 4.3 | xAI | 43.86 |
| 31 | Qwen3 Max | Alibaba | 43.74 |
| 32 | Qwen3.6-35B-A3B | Alibaba | 42.65 |
| 33 | Grok 4 | xAI | 42.34 |
| 34 | Gemini 2.5 Pro | 42.01 | |
| 35 | GPT-5.1 | OpenAI | 41.24 |
| 36 |  MiniMax M2.7 | MiniMax | 40.40 |
| 37 | GLM-4.7 | Z.AI | 39.95 |
| 38 | Claude 4 Sonnet | Anthropic | 39.66 |
| 39 | Qwen3.5-27B | Alibaba | 39.41 |
| 40 |  Mistral Medium 3.5 128B | Mistral | 39.10 |
| 41 | Gemini 3.1 Flash-Lite | 38.46 | |
| 42 | Grok 4.20 | xAI | 38.36 |
| 43 |  Hy3 Preview | Tencent | 36.91 |
| 44 | MiMo-V2-Pro | Xiaomi | 36.68 |
| 45 | Gemma 4 31B | 35.26 | |
| 46 | Kimi K2.5 (Reasoning) | Moonshot AI | 32.58 |
| 47 |  Trinity-Large-Thinking | Arcee AI | 32.55 |
| 48 | GLM-5V-Turbo | Z.AI | 30.76 |
| 49 | GPT-OSS 120B | OpenAI | 29.61 |
| 50 |  DeepSeek V3.2 | DeepSeek | 29.57 |
| 51 | Qwen3.5-35B-A3B | Alibaba | 28.96 |
| 52 | GPT-4.1 | OpenAI | 25.65 |
Evidence key: Observed
Rows are ordered by the value Gert Labs rankings published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.