TapTap Maker Benchmark
What it measures and how
Use only the official main_board L2 pass rate. Cost, speed, Held-out and category scores add no votes. Select one representative row per base model using fixed reasoning-tier priority, without considering scores.
How this evidence is used
Receives 2.4% from the coding and design budget, using a fixed engine and L2 metric.
Benchmark results
Fixed rules select one representative configuration per public model. Anonymous test models are omitted. Original source ranks are retained, with up to 30 models per benchmark.
| Source rank | Source model name | Raw result | Representative configuration |
|---|---|---|---|
| 1 | gpt-6-astraOpenAI | 85.8% | xHigh reasoning |
| 2 | claude-fable-5-1Anthropic | 85.5% | High reasoning |
| 3 | claude-opus-5-5Anthropic | 85.5% | xHigh reasoning |
| 4 | gpt-6.1-solOpenAI | 85.3% | xHigh reasoning |
| 5 | claude-sonnet-5-5Anthropic | 83.6% | xHigh reasoning |
| 7 | gemini-3.8-flashGoogle | 79.8% | High reasoning |
| 8 | gpt-5.6-solOpenAI | 79.8% | xHigh reasoning |
| 9 | grok-4.7-xhighxai | 77.8% | xHigh reasoning |
| 10 | gpt-6-solOpenAI | 76.8% | xHigh reasoning |
| 11 | gpt-6-lunaOpenAI | 76.6% | xHigh reasoning |
| 12 | qwen3.8-max-0902Alibaba | 76.2% | xHigh reasoning |
| 13 | glm-5.3Z.ai | 76.2% | Max reasoning |
| 14 | deepseek-v4.1-flashDeepSeek | 76.1% | Max reasoning |
| 15 | qwen3.8-flashAlibaba | 76.0% | xHigh reasoning |
| 16 | claude-haiku-5-5Anthropic | 75.8% | xHigh reasoning |
| 17 | glm-5.3-flashZ.ai | 75.0% | Max reasoning |
| 18 | gpt-5.6-terraOpenAI | 74.2% | xHigh reasoning |
| 19 | hy4-previewTencent | 72.5% | High reasoning |
| 20 | kimi-k3Moonshot AI | 72.3% | Source default configuration |
| 21 | gpt-5.6-lunaOpenAI | 72.2% | xHigh reasoning |
| 22 | doubao-seed-evolvingByteDance | 71.6% | High reasoning |
| 23 | deepseek-v4-proDeepSeek | 70.5% | Max reasoning |
| 25 | deepseek-v4-flashDeepSeek | 69.1% | Max reasoning |
| 26 | gemini-3.1-pro-previewGoogle | 59.5% | Source default configuration |
| 27 | MiniMax-M3MiniMax | 54.1% | Source default configuration |
| 28 | claude-haiku-4-5Anthropic | 38.5% | High reasoning |
Limitations and attribution
One engine and one language do not generalize to other stacks. Models may use different agent drivers. The closed-source harness prevents task-by-task replication.
Data license: Official public results; public display retains official attribution. Full redistribution authorization remains subject to Yiwan / TapTap terms.
Results are published by TapTap Maker. Raw scores and the e/acc consensus index use different scales and cannot be added directly.