Which is better, Claude Sonnet 4 or HyperNova 60B 2605 (high, based on gpt-oss-120b)?

Refresh Models —Deals —Regulatory —Sources —

Claude Sonnet 4 vs HyperNova 60B 2605 (high, based on gpt-oss-120b)

17 SHARED BENCHMARKS

Across 17 shared benchmarks, Claude Sonnet 4 scores higher on 15 and HyperNova 60B 2605 (high, based on gpt-oss-120b) on 2. The widest gap is AA Agentic Index, where Claude Sonnet 4 scores 39.2 against 6.8.

ANTHROPICVSOPENAI17 SHARED15–2 HEAD-TO-HEAD

BenchmarkClaude Sonnet 4MARGINHyperNova 60B 2605 (high, based on gpt-oss-120b)

AA Agentic Index39.26.8

AA Intelligence29.818.3

AA-LCR69.735.3

AA-Omniscience0.2-54.6

Artificial Analysis Coding Index37.623.2

critpt1.10.9

gdpval31.28

GPQA Diamond7873.3

HLE10.716.6

IFBench5566.5

OmniScience Accuracy22.715.2

OmniScience Non-Hallucination70.917.7

scicode4033

TauBench V3 - Banking16.75.6

Terminal-Bench 2.136.318.4

Terminal-Bench Hard31.123.5

τ²-Bench Telecom (AA run)64.663.2

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.