Benchmark Almanac

Intern-S2-397B

Intern-S2-397B ranks first on 3 of the 12 benchmarks it has scores on.

Shanghai AI Lab Released 13 Sep 2026 Family Intern-S2 The lab's model card
21
Benchmarks with a score
3
Ranked first, out of five or more models
4
In the top three
Shanghai AI Lab Sep 2026

Intern-S2-397B

Open weights Flagship

No Epoch Capabilities Index score yet
  • MMMU-Pro 81.7% #6 /72
  • SciCode 47.6% #14 /47
  • ChartQA Pro 71.1% #3 /8

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
MMLU-Pro 89.8% #1 of 151 Model card
AdvancedIF 71.6% #5 of 6 Model card

Math and science

BenchmarkScoreRankSource
FrontierScience 87% #1 of 7 Model card
HMMT 2026 93.6% #5 of 18 Model card
SciReasoner evaluation suite 63.3% #1 of 2 Model card
IMO-ProofBench 38.4% #5 of 5 Model card
AdvancedMathBench 58.1% #1 of 1 Model card
SGI-Bench 51.9% #1 of 1 Model card

Coding

BenchmarkScoreRankSource
SWE-bench Multilingual 84% #8 of 70 Model card
SWE-Bench Pro 68.5% #9 of 77 Model card
SciCode 47.6% #14 of 47 Model card

Agents and tools

BenchmarkScoreRankSource
Terminal-Bench 2.1 64% #39 of 53 Model card

Vision, audio and robotics

BenchmarkScoreRankSource
MMMU-Pro 81.7% #6 of 72 Model card
Scientists' First Exam (SFE) 60.7% #1 of 5 Model card
MicroVQA 69.7% #1 of 3 Model card
ChartQA Pro 71.1% #3 of 8 Model card
XLRS-Bench 51.4% #4 of 4 Model card

Safety and security

BenchmarkScoreRankSource
Biology-Instructions 55.7% #1 of 2 Model card
Mol-Instructions 54% #1 of 2 Model card
MolecularIQ 62.4% #1 of 1 Model card
TOMG-Bench 66.8% #1 of 1 Model card

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.