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 Fable 5 vs GPT-5.1

AnthropicvsOpenAI31 shared benchmarks282 head-to-head
BenchmarkClaude Fable 5GPT-5.1
AA Agentic Index56.632.2
AA Intelligence62.137.5
AA-LCR76.776.7
AA-Omniscience43.35.4
arc_agi_190.572.8
ARC-AGI-276.817.6
arena_elo15081439
arena_text_factuality14861445
arena_vision13071250
Artificial Analysis Coding Index76.549.4
browsecomp8850.8
coding_arena_elo16261421
critpt28.64.9
gdpval61.925
GPQA Diamond92.688.1
HLE64.528.5
HLE (with tools)64.542.7
IFBench63.572.9
MCP Atlas84.750.1
MMMU-Pro84.275.5
OmniScience Accuracy65.337.7
OmniScience Non-Hallucination36.448.1
scicode60.243.3
simplebench81.953.2
simpleqa_verified68.348.9
SWE-bench Verified9576.3
TauBench V3 - Banking38.115.9
Terminal-Bench 2.18852.4
Terminal-Bench Hard62.945.5
τ²-Bench Telecom (AA run)98.581.9
τ³-Bench26.814

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.