Intern-S1-Pro

Intern-S1-Pro places in the top three on 2 benchmarks.

Shanghai AI Lab Released 2 Feb 2026 Family Intern-S1 The lab's model card

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Shanghai AI Lab Feb 2026

Open weights Flagship

No Epoch Capabilities Index score yet

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.

Benchmark	Score		Rank	Source
MMLU-Pro	86.6%		#14 of 151	Model card
IFBench	71.2%		#38 of 70	Model card

Benchmark	Score	Rank	Source
AIME 2025	93.1%	#33 of 143	Model card
IMO-AnswerBench	77.3%	#30 of 37	Model card
Matbench	72.8	#2 of 2	Model card
SciReasoner evaluation suite	55.5%	#2 of 2	Model card

Benchmark	Score		Rank	Source
LiveCodeBench v6	74.3%		#41 of 76	Model card
SArena	83.5		#1 of 1	Model card

Benchmark	Score	Rank	Source
ScreenSpot-v2	93.6%	#4 of 14	Model card
tau2-bench	80.9%	#30 of 69	Model card
GAIA	77.4%	#3 of 5	Model card

Benchmark	Score	Rank	Source
RefCOCO / RefCOCO+ / RefCOCOg	91.9%	#7 of 19	Model card
MMMU-Pro	72.8%	#41 of 72	Model card
Scientists' First Exam (SFE)	52.7%	#3 of 5	Model card
OCRBench v2	60.1%	#14 of 20	Model card
XLRS-Bench	52.8%	#3 of 4	Model card
MicroVQA	63.3%	#3 of 3	Model card
MSEarth	65.2%	#2 of 2	Model card

Benchmark	Score	Rank	Source
SMolInstruct	74.8%	#1 of 2	Model card
Biology-Instructions	52.5%	#2 of 2	Model card
Mol-Instructions	48.8%	#2 of 2	Model card

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

Every result in the longer documents the lab published with it. 1 of them isn't in the launch post.