TinySwallow-1.5B-Instruct: benchmark results

Provider: Other. Access: Open.

Unified ELO 1450 ± 44, rank #1525 of 2656 rated models, from 18 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
pfgen-bench - Completion Mode - Fluency0.66Fluency Score64.4
pfgen-bench - Completion Mode - Truthfulness0.81Truthfulness Score64.2
pfgen-bench - Completion Mode - Score0.55pfgen Score (mean of three)63.3
pfgen-bench - QA Mode - Truthfulness0.8Truthfulness Score60.6
pfgen-bench - Completion Mode - Helpfulness0.18Helpfulness Score60.4
pfgen-bench - QA Mode - Fluency0.62Fluency Score57.6
pfgen-bench - QA Mode - Score0.53pfgen Score (mean of three)54.2
pfgen-bench - QA Mode - Helpfulness0.17Helpfulness Score48.8
Ebisu - JF-TE - F119.37Maximal-Term F1 (%)42.9
pfgen-bench - Chat Mode - Fluency0.59Fluency Score39.7
Ebisu - JF-TE - Hit Rate@12.64Hit Rate@1 (%)38.1
Ebisu - JF-TE - Hit Rate@57.12Hit Rate@5 (%)38.1

Interactive version: theaggregate.ai/model?slug=tinyswallow-1-5b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-19.