plamo-2-1B: benchmark results

Provider: Other. Access: Open.

Unified ELO 1267 ± 46, rank #2546 of 2656 rated models, from 26 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
pfgen-bench - Completion Mode - Fluency0.6Fluency Score57.8
pfgen-bench - Completion Mode - Truthfulness0.77Truthfulness Score57.7
pfgen-bench - Completion Mode - Score0.5pfgen Score (mean of three)56.2
pfgen-bench - Completion Mode - Helpfulness0.12Helpfulness Score50.5
Swallow - Pre-trained Japanese - WMT20 En-Ja23.6BLEU44.9
Swallow - Pre-trained Japanese - JEMHopQA46.3Character F1 (%)37.8
Swallow - Pre-trained Japanese - NIILC43.4Character F1 (%)34.7
Swallow - Pre-trained English - SQuAD250.1Exact Match (%)14.3
Swallow - Pre-trained English - MATH3.4Exact Match (%)13.3
Swallow - Pre-trained Japanese - WMT20 Ja-En11.9BLEU13.3
Swallow - Pre-trained English - GSM8K7.2Exact Match (%)10.2
Swallow - Pre-trained English - HumanEval8Pass@1 (%)10.2

Interactive version: theaggregate.ai/model?slug=plamo-2-1b · How It Works · Data refreshed daily, snapshot 2026-09-19.