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 4.8 vs o3

AnthropicvsOpenAI26 shared benchmarks233 head-to-head
BenchmarkClaude Opus 4.8o3
AA Agentic Index49.436.1
AA Intelligence57.331.1
AA-LCR7373.3
AA-Omniscience28.8-15.3
arc_agi_192.560.8
ARC-AGI-272.16.5
arena_vision12801217
Artificial Analysis Coding Index74.338.4
browsecomp88.549.7
critpt20.91.1
Fortress18.216
frontiermath_tier_431.32.1
gdpval54.212.8
GPQA Diamond93.683.3
HLE57.920.3
IFBench62.271.4
longbench_v269.158.8
MMMU-Pro78.976.4
OmniScience Accuracy48.838.6
OmniScience Non-Hallucination60.712.9
scicode53.541
simplebench64.853.1
simpleqa_verified39.553
SWE-bench Verified88.669.1
Terminal-Bench Hard58.337.1
τ²-Bench Telecom (AA run)94.480.7

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.