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

Claude Opus 4.6 vs DeepSeek-R1

AnthropicvsDeepSeek34 shared benchmarks313 head-to-head
BenchmarkClaude Opus 4.6DeepSeek-R1
AA Agentic Index67.63.1
AA Intelligence44.918.6
AA-LCR74.356
AA-Omniscience13.7-31.3
AIME 202599.887.5
arc_agi_19321.2
ARC-AGI-268.81.3
Artificial Analysis Coding Index48.124.6
browsecomp86.88.9
Chinese SimpleQA (C-SimpleQA)76.463.7
critpt12.60.6
Fortress20.574.4
gdpval55.91.5
GPQA Diamond91.381
HLE53.117.7
IFBench62.539
LiveCodeBench88.884.4
MMLU-Pro89.185
multichallenge5645
MultiNRC57.127.6
OmniScience Accuracy4730.7
OmniScience Non-Hallucination37.210.5
scicode5235.7
simplebench67.640.8
simpleqa_verified46.527.4
SWE-bench Multilingual77.830.5
SWE-bench Verified80.857.6
Terminal-Bench Hard65.46.1
vectara_answer_rate99.897
vectara_avg_summary_length137.693.5
vectara_factual_consistency87.888.7
vectara_hallucination_rate12.211.3
τ²-Bench Telecom (AA run)99.311.4
τ³-Bench72.46.4

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.