Qwen-AgentWorld-35B-A3B: benchmark results
Provider: Alibaba. Released 2026-06-24. Access: Open.
Aggregate Rating 1738 ± 26, rank #213 of 10916 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA v2 - IFHardBench | 75.7 | Score (%) | 89.1 |
| MERA v2 - Agentic | 56.5 | Score (%) | 87 |
| MERA v2 - GorillaHard | 62.9 | Score (%) | 87 |
| MERA v2 - NewReasoning | 70.1 | Score (%) | 87 |
| MERA v2 | 0.47 | Total score | 78.3 |
| MERA v2 - SOB-Hard | 37.9 | Score (%) | 76.1 |
| MERA v2 - Human Centric | 45.1 | Score (%) | 73.9 |
| Qwen-AgentWorld | 56.39 | Overall (imported) | 73.3 |
| MERA v2 - SAGE | 67.3 | Score (%) | 72.8 |
| MERA v2 - Humor | 34.7 | Score (%) | 71.7 |
| MERA v2 - Riddles | 47.8 | Score (%) | 71.7 |
| MERA v2 - Reasoning | 56.6 | Score (%) | 69.6 |
Interactive version: theaggregate.ai/model?slug=qwen-agentworld-35b-a3b · How It Works · Data refreshed daily, snapshot 2026-11-08.