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

GPT-5.1 vs Opus 5

OpenAIvsAnthropic27 shared benchmarks126 head-to-head
BenchmarkGPT-5.1Opus 5
AA Agentic Index32.259.2
AA Intelligence37.563.1
AA-LCR76.778.7
AA-Omniscience5.437.1
arc_agi_172.897.5
ARC-AGI-217.690.4
arena_elo14391487
arena_text_factuality14451481
Artificial Analysis Coding Index49.478
browsecomp50.890.8
coding_arena_elo14211662
critpt4.929.1
gdpval2567.2
GPQA Diamond88.193.7
healthbench_length_adjusted50.957.8
HLE28.564.7
HLE (with tools)42.764.7
MCP Atlas50.185.8
MMMU-Pro75.584.7
OmniScience Accuracy37.760.9
OmniScience Non-Hallucination48.140.5
scicode43.355.7
simplebench53.280.6
simpleqa_verified48.956.7
SWE-bench Verified76.396
TauBench V3 - Banking15.944.7
Terminal-Bench 2.152.489.1

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.