ToolRL-Qwen2.5-1.5B: benchmark results
Provider: Other.
Aggregate Rating 1503 ± 51, rank #2299 of 10916 rated models, from 24 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| RobustBench-TC - Authentication Error | 30.2 | Tool-call accuracy (%) under the AuthErr perturbation (trans | 82.4 |
| RobustBench-TC - Parameter Description Paraphrase | 70.4 | Tool-call accuracy (%) under the ParamPara perturbation (obs | 82.4 |
| RobustBench-TC - Typo | 62.8 | Tool-call accuracy (%) under the Typo perturbation (observat | 82.4 |
| RobustBench-TC - Duplicate Tool With Wrong Parameters | 56.3 | Tool-call accuracy (%) under the Dup-WrongP perturbation (ac | 76.5 |
| RobustBench-TC - Redundant Tool | 59.3 | Tool-call accuracy (%) under the RedunTool perturbation (act | 73.5 |
| RobustBench-TC - Duplicate Tool With Description and Wrong Parameters | 52.8 | Tool-call accuracy (%) under the Dup-DescWP perturbation (ac | 67.6 |
| RobustBench-TC - Query Paraphrase | 66.8 | Tool-call accuracy (%) under the QueryPara perturbation (obs | 67.6 |
| RobustBench-TC - Clean | 70.4 | Tool-call accuracy (%) on the 199 unperturbed baseline sampl | 64.7 |
| RobustBench-TC - Rate Limit | 25.6 | Tool-call accuracy (%) under the RateLim perturbation (trans | 58.8 |
| RobustBench-TC - Duplicate Tool With Swapped Description | 51.6 | Tool-call accuracy (%) under the Dup-SwapDP perturbation (ac | 52.9 |
| RobustBench-TC - Schema Drift | 37.2 | Tool-call accuracy (%) under the SchemaD perturbation (trans | 50 |
| RobustBench-TC - Duplicate Tool Without Description | 48.1 | Tool-call accuracy (%) under the Dup-NoDesc perturbation (ac | 47.1 |
Interactive version: theaggregate.ai/model?slug=toolrl-qwen2-5-1-5b · How It Works · Data refreshed daily, snapshot 2026-11-08.