Ling-flash-2.0 — benchmark results

InclusionAI's speed-oriented open MoE (100B total/6.1B active), matching ~40B dense models at higher speed (September 2025). Provider: InclusionAI. Released 2025-09-17. Access: Open.

Unified ELO 1567 ± 18, rank #573 of 1776 rated models, from 83 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Medmarks - MedHallu Easy76.47Score (%)95.7
Medmarks - MedHallu Hard54.44Score (%)95.7
Medmarks - MedHallu Medium72.2Score (%)95.7
SciEval - Astronomy48.12Astronomy (%)94.4
Medmarks - PubHealthBench Reviewed86.49Score (%)80
Medmarks - PubMedQA76.47Score (%)72.9
Medmarks - Med-HALT Reasoning NOTA61.51Score (%)71.4
SciEval - Earth Sciences69.55Earth Sciences (%)66.7
Medmarks - SuperGPQA Medicine Easy54.68Score (%)65.7
AA LiveCodeBench58.94Pass@1 (%)64.6
AA AIME 202565.33Accuracy (%)60.7
Medmarks - HEAD-QA v283.71Score (%)60

Interactive version: theaggregate.ai/model?slug=ling-flash-2-0 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.