Qwen-AgentWorld-397B-A17B vs Kimi K3
New ComparisonScores are fetched live from the current database on every visit — nothing is cached.
Benchmark Scores Comparison
Qwen-AgentWorld-397B-A17B
Kimi K3
Qwen-AgentWorld-397B-A17B
Score: 15.0
Kimi K3
Score: 15.0
Coverage matrix
2 models × 14 benchmarks — hover a benchmark name for its category
Shading = score relative to the best score among the selected models:
Low
Mid
High
Missing (—)
The totals row shows how many of the 14 benchmarks each model has scores for.
| Benchmark | Qwen-AgentWorld-397B-A17B Qwen Team (Alibaba Cloud) | Kimi K3 Moonshot AI |
|---|---|---|
| AgentWorldBench Terminal | 57.73 | — |
| AgentWorldBench Overall | 58.71 | — |
| WMDP (Bio) | — | 89.1 |
| AgentWorldBench Web | 50.98 | — |
| HPCT | — | 59.6 |
| AgentWorldBench Search | 37.82 | — |
| Lab Bench (ProtocolQA) | — | 81.9 |
| WMDP (Chem) | — | 84.2 |
| AgentWorldBench OS | 67.89 | — |
| AgentWorldBench MCP | 68.24 | — |
| AgentWorldBench SWE | 68.49 | — |
| AgentWorldBench Android | 60.2 | — |
| MBCT | — | 58.9 |
| VCT | — | 48 |
| Covered | 8/14 | 6/14 |
Scorecard
Overall 0–100 score — category strengths (50%), shared-benchmark wins (30%), coverage (20%)
| Model | Overall score | Shared benchmark wins | Coverage | Strongest at | Weakest at |
|---|---|---|---|---|---|
| Qwen-AgentWorld-397B-A17B | 57.1 | — | 8 of 14 (57.0%) | — | — |
| Kimi K3 | 42.9 | — | 6 of 14 (43.0%) | — | — |
Partial coverage benchmarks
Scored by at least one but not all selected models (14) — missing scores show as —
| Benchmark | Category | Qwen-AgentWorld-397B-A17B | Kimi K3 |
|---|---|---|---|
| AgentWorldBench Terminal 1/2 models | general_agent | 57.73 | — |
| AgentWorldBench Overall 1/2 models | general_agent | 58.71 | — |
| WMDP (Bio) 1/2 models | safety | — | 89.1 |
| AgentWorldBench Web 1/2 models | general_agent | 50.98 | — |
| HPCT 1/2 models | safety | — | 59.6 |
| AgentWorldBench Search 1/2 models | general_agent | 37.82 | — |
| Lab Bench (ProtocolQA) 1/2 models | safety | — | 81.9 |
| WMDP (Chem) 1/2 models | safety | — | 84.2 |
| AgentWorldBench OS 1/2 models | general_agent | 67.89 | — |
| AgentWorldBench MCP 1/2 models | general_agent | 68.24 | — |
| AgentWorldBench SWE 1/2 models | general_agent | 68.49 | — |
| AgentWorldBench Android 1/2 models | general_agent | 60.2 | — |
| MBCT 1/2 models | safety | — | 58.9 |
| VCT 1/2 models | safety | — | 48 |