benchgap
Other · model

Ling 3.0 Flash FP8 benchmark scores

As of 2026-11-22, Ling 3.0 Flash FP8 (Other) has measured scores on 4 benchmarks and estimated scores on 32 more.

BenchmarkScoreSource
AA-GPQA Diamond82.7%estimated ± 4.4 pp, high confidence
AA-HLE23.3%estimated ± 3.9 pp, high confidence
AA-SciCode40.5%estimated ± 3.0 pp, high confidence
Artificial Analysis Intelligence Index17.2%estimated ± 7.4 pp, medium confidence
CritPt1.2%estimated ± 4.0 pp, high confidence
GPQA Diamond84.0%measured
HLE22.5%estimated ± 6.5 pp, medium confidence
IFBench73.4%measured
LiveCodeBench v679.8%estimated ± 4.4 pp, high confidence
AA-Omniscience Accuracy21.7%estimated ± 8.4 pp, medium confidence
SciCode40.4%measured
IFEval93.4%estimated ± 3.6 pp, high confidence
AA Coding Index40.8%estimated ± 9.2 pp, medium confidence
SWE-bench Verified68.4%estimated ± 5.6 pp, medium confidence
SWE-bench Pro49.1%estimated ± 10.1 pp, low confidence
MMLU-Pro84.1%estimated ± 4.4 pp, high confidence
AA-IFBench59.4%estimated ± 7.4 pp, medium confidence
GPQA84.0%measured
MMLU88.1%estimated ± 4.2 pp, medium confidence
Vals GPQA Diamond83.4%estimated ± 2.1 pp, medium confidence
Vals LiveCodeBench84.0%estimated ± 0.8 pp, low confidence
Vals MMLU-Pro83.3%estimated ± 1.6 pp, medium confidence
MMMLU87.2%estimated ± 1.1 pp, medium confidence
AA MMLU-Pro86.4%estimated ± 1.2 pp, low confidence
ARC-AGI-178.9%estimated ± 2.5 pp, medium confidence
ARC-AGI-224.2%estimated ± 9.7 pp, low confidence
Vals SWE-bench64.4%estimated ± 5.3 pp, low confidence
DeepSWE36.5%estimated ± 8.4 pp, low confidence
HLE w/o tools19.9%estimated ± 4.3 pp, high confidence
ARC-AGI-30.0%estimated ± 8.6 pp, low confidence
C-Eval91.7%estimated ± 1.2 pp, high confidence
MMLU-Redux93.6%estimated ± 1.7 pp, high confidence
SuperGPQA66.8%estimated ± 8.5 pp, low confidence
MedXpertQA (Text)39.8%estimated ± 4.5 pp, low confidence
MMLU-Pro (Arcee)84.8%estimated ± 3.4 pp, medium confidence
SimpleQA38.6%estimated ± 13.4 pp, low confidence