T-pro-it-2.0: benchmark results

Provider: Other. Access: Open.

Unified ELO 1583 ± 1, rank #311 of 1392 rated models, from 25 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MERA - CheGeKa51.79F1 (%)92.3
MERA - ruWorldTree99.24Accuracy (%)92.1
MERA - PARus93.2Accuracy (%)89.7
MERA - ruHHH87.64Accuracy (%)88.7
MERA - ruCodeEval54.27pass@1 (%)87.6
MERA - ruTiE87.6Accuracy (%)87.1
MERA - ruOpenBookQA94Accuracy (%)86.6
MERA - ruHateSpeech86.42Accuracy (%)86.1
MERA - MaMuRAMu85.08Accuracy (%)83.7
MERA - ruMMLU78.97Accuracy (%)82.8
MERA - ruMultiAr48.73EM (%)81.3
MERA0.66Total score80.7

Interactive version: theaggregate.ai/model?slug=t-pro-it-2-0 · How It Works · Data refreshed daily, snapshot 2026-09-05.