MUA-RL-14B: benchmark results
Provider: Other.
Aggregate Rating 1551 ± 50, rank #1690 of 10916 rated models, from 24 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| RobustBench-TC - Duplicate Tool With Swapped Description | 69 | Tool-call accuracy (%) under the Dup-SwapDP perturbation (ac | 94.1 |
| RobustBench-TC - Rate Limit | 35.2 | Tool-call accuracy (%) under the RateLim perturbation (trans | 88.2 |
| RobustBench-TC - Misleading Description | 38.2 | Tool-call accuracy (%) under the MisDesc perturbation (rewar | 82.4 |
| RobustBench-TC - Misleading Description (Abbreviated Name) | 11.8 | Tool-call accuracy (%) under the MisDesc-Abbr perturbation ( | 82.4 |
| RobustBench-TC - Response-Time Description | 33.3 | Tool-call accuracy (%) under the TimeDesc perturbation (rewa | 79.4 |
| RobustBench-TC - Response-Time Description (Abbreviated Name) | 17.4 | Tool-call accuracy (%) under the TimeDesc-Abbr perturbation | 79.4 |
| RobustBench-TC - Response-Time Description (Neutral Suffix) | 44.1 | Tool-call accuracy (%) under the TimeDesc-N perturbation (re | 67.6 |
| RobustBench-TC - Server Error | 48.7 | Tool-call accuracy (%) under the 5xxErr perturbation (transi | 64.7 |
| RobustBench-TC - Misleading Description (Neutral Suffix) | 44.1 | Tool-call accuracy (%) under the MisDesc-N perturbation (rew | 61.8 |
| RobustBench-TC - Authentication Error | 18.1 | Tool-call accuracy (%) under the AuthErr perturbation (trans | 58.8 |
| RobustBench-TC - Malformed Response | 58.8 | Tool-call accuracy (%) under the Malform perturbation (trans | 58.8 |
| RobustBench-TC - Schema Drift | 37.7 | Tool-call accuracy (%) under the SchemaD perturbation (trans | 58.8 |
Interactive version: theaggregate.ai/model?slug=mua-rl-14b · How It Works · Data refreshed daily, snapshot 2026-11-08.