InternVL2-8B — benchmark results

OpenGVLab's 8B vision-language model (July 2024) pairing InternViT-300M with internlm2_5-7b-chat for image, document and video understanding. Provider: Shanghai AI Lab. Released 2024-07-15. Access: Open.

Unified ELO 1414 ± 7, rank #1158 of 1776 rated models, from 1056 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LMM Reasoning - MMMath - Difficulty-easy45.4Accuracy (%)100
Open LMM Reasoning - MMMath - Knowledge-L1-Properties of Shapes29.4Accuracy (%)100
Open LMM Reasoning - MMMath - Knowledge-L2-Acute Angle Trigonometric Functions19.7Accuracy (%)100
Open LMM Reasoning - MMMath - Knowledge-L2-Circle34.3Accuracy (%)100
Open LMM Reasoning - MMMath - Knowledge-L2-Intersecting and Parallel Lines33.8Accuracy (%)100
Open LMM Reasoning - MMMath - Knowledge-L2-Symmetry of Shapes11.9Accuracy (%)100
OpenVLM MMT-Bench - Disease Diagnosis100Score (%)99.8
OpenVLM MMT-Bench - Chemical Apparatus Recognition80Score (%)99
MEGA-Bench Task - Code Solution Compare50Task Score (%)98.8
MEGA-Bench Task - TQA Textbook QA100Task Score (%)97.7
OpenVLM MMT-Bench - GUI Install65Score (%)97.1
OpenVLM MMBench V1.1 CN - Image Scene92.4Accuracy (%)96.6

Interactive version: theaggregate.ai/model?slug=internvl2-8b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.