Seed 2.0 Pro (Thinking): benchmark results

Provider: ByteDance. Released 2026-02-14. Access: API.

Unified ELO 1661 ± 1, rank #280 of 3078 rated models, from 15 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LLMEval-Logic Base75.5Accuracy (%)100
VitaBench 2.047.4Avg@4 Full Context (self-reported)92
LLMEval-Logic Formalization Fixed56.9Accuracy (%)65.4
LLMEval-Logic Formalization Free35.8Accuracy (%)53.8
ComboShoppingBench - Response Quality81.8Pass rate (%; LLM-judged)47.6
LLMEval-Logic Hard Sub-Q63.3Accuracy (%)38.5
ComboShoppingBench - Overall Success17.5Pass rate (%; all judged and rule-based checks)38.1
ComboShoppingBench - Budget Compliance72.9Pass rate (%)33.3
ComboShoppingBench - Coupon-ID Validity96.2Pass rate (%)33.3
LLMEval-Logic Hard20.4Accuracy (%)30.8
ComboShoppingBench - Claim Faithfulness69.4Pass rate (%; LLM-judged)28.6
ComboShoppingBench - Coupon Optimality56Pass rate (%)23.8

Interactive version: theaggregate.ai/model?slug=seed-2-0-pro-thinking · How It Works · Data refreshed daily, snapshot 2026-09-19.