LetTokenBurnBenchHub

Model

InternVL3.5-8B-Instruct

Shanghai AI Lab · open weights

internlm.intern-ai.org.cn

Knowledge & Reasoning

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
WorldFact-Bench	8.9	accuracy	direct judgment	Independent	medium	arxiv.org

Multimodal

Benchmark	Score	Metric	Harness	Source	Confidence	Link
4MT-VLM	28.0	accuracy	N/A	Independent	medium	arxiv.org
Counterfactual Physical Consistency Benchmark	93.3	bin._mf1	lora	Independent	medium	arxiv.org
CROSS-Bench	63.0	accuracy	N/A	Independent	medium	arxiv.org
DataVista	46.1	accuracy	N/A	Independent	medium	arxiv.org
EgoExo-Next	32.9	accuracy	N/A	Independent	medium	arxiv.org
EgoTools-Bench	45.9	egotools-bench_overall	N/A	Independent	medium	arxiv.org
FG-Sudoku	0.2	accuracy	N/A	Independent	medium	arxiv.org
InstanceBench	34.9	[email protected]	N/A	Independent	medium	arxiv.org
Knossos	40.7	f1	N/A	Independent	medium	arxiv.org
MVGraph	5.4	accuracy	N/A	Independent	medium	arxiv.org
NegT2IBench	69.2	spearman_ρ	N/A	Independent	medium	arxiv.org
OmniVCBench	30.3	accuracy	N/A	Independent	medium	arxiv.org
RoadSceneVQA-G	36.9	f1	N/A	Independent	medium	arxiv.org
SpaceConflict	57.8	accuracy	N/A	Independent	medium	arxiv.org
SpatialChain	79.3	accuracy	N/A	Independent	medium	arxiv.org
Video-Index	15.2	accuracy	N/A	Independent	medium	arxiv.org
VisualNoiseQA	46.5	accuracy	bp	Independent	medium	arxiv.org

Safety & Alignment

Safety & Alignment

Benchmark	Score	Metric	Harness	Source	Confidence	Link
OR-Bench	50.9	accuracy	N/A	Independent	medium	arxiv.org

Abstract Reasoning

Abstract Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
FoldBench	0.2	tm-score	N/A	Independent	medium	arxiv.org

Reproduced by the community