MobileWorld - User Interaction: leaderboard
The user-interaction split of MobileWorld: 44 tasks requiring mid-task clarification or input from a simulated user; success rate %, end-to-end models only.
Metric: Success Rate (%). Source: tongyi-mai.github.io. Saturation forecast: Not forecast. 24 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed 2.0 Pro | 61.4 | #122 |
| 2 | Claude Opus 4.7 | 59.1 | #51 |
| 3 | Kimi K2.6 | 56.8 | #113 |
| 4 | Qwen 3.5 397B A17B | 54.4 | #154 |
| 5 | Kimi K2.5 | 51.2 | #152 |
| 6 | Qwen 3.5 122B A10B | 40.9 | #184 |
| 7 | Claude Sonnet 4.5 | 38.6 | #148 |
| 8 | GPT-5.5 | 34.1 | #33 |
| 9 | Claude Opus 4.6 | 34.1 | #67 |
| 10 | Gemini 3 Pro | 29.5 | #82 |
| 11 | Seed 1.8 | 29.5 | #143 |
| 12 | Gemini 3.1 Pro (Preview) | 22.7 | #64 |
| 13 | Qwen 3 VL 235B A22B | 4.4 | #251 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mobileworld-user-interaction · How It Works · Data refreshed daily, snapshot 2026-11-05.