VECTOR WIREAI INTELLIGENCE
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models Deals Regulatory Sources

Gemma 4 31B vs Opus 5

GooglevsAnthropic24 shared benchmarks024 head-to-head
BenchmarkGemma 4 31BOpus 5
AA Agentic Index14.459.2
AA Intelligence29.763.1
AA-LCR68.378.7
AA-Omniscience-47.937.1
arena_elo14511487
arena_text_factuality14491481
Artificial Analysis Coding Index43.478
coding_arena_elo13641662
critpt1.429.1
gdpval15.567.2
GPQA Diamond85.793.7
HLE26.564.7
HLE (with tools)26.564.7
MCP Atlas57.285.8
MMMU-Pro76.984.7
OmniScience Accuracy2060.9
OmniScience Non-Hallucination18.140.5
scicode43.455.7
simpleqa_verified9.656.7
SWE-bench Multilingual51.789.5
SWE-bench Pro35.779.2
SWE-bench Verified5296
TauBench V3 - Banking14.844.7
Terminal-Bench 2.143.489.1

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.