Hugging Face Evaluations

Source-qualified evaluations, report statistics and safety observations.

intel-ai/GLM-5.1-MXFP4-Mixed-CT-AutoRound

MathArena/hmmt_feb_2026 · 82.6 source-defined score; unit unspecified

openpangu/openPangu-2.0-Flash

MathArena/aime_2026 · 93.3 source-defined score; unit unspecified

JetBrains/Mellum2-12B-A2.5B-Base-Pretrain

diamond · 31.31 source-defined score; unit unspecified

swiss-ai/Apertus-v1.5-70B

main · 35.9375 source-defined score; unit unspecified

nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16

pass-rate-strict · 9.18 source-defined score; unit unspecified

upstage/Solar-Open2-250B

swe_bench_%_resolved · 70.4 source-defined score; unit unspecified

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace