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

AnthropicvsOpenAI30 shared benchmarks291 head-to-head
BenchmarkClaude Fable 5GPT-5
AA Agentic Index56.649.7
AA Intelligence62.135.3
AA-LCR76.776.3
AA-Omniscience43.3-8.7
arc_agi_190.556.2
ARC-AGI-276.87.5
arena_vision13071212
Artificial Analysis Coding Index76.538.9
browsecomp8854.9
coding_arena_elo16261419
critpt28.65.7
gdpval61.932.5
GPQA Diamond92.687.3
HLE64.528.5
HLE (with tools)64.535.2
IFBench63.573.1
MMMU-Pro84.278.4
OmniScience Accuracy65.340.3
OmniScience Non-Hallucination36.421
scicode60.243
simplebench81.956.7
simpleqa_verified68.350.6
SWE-bench Multilingual86.655.3
SWE-bench Pro8041.8
SWE-bench Verified9574.9
TauBench V3 - Banking38.122.1
Terminal-Bench 2.18835.2
Terminal-Bench Hard62.937.9
τ²-Bench Telecom (AA run)98.586.5
τ³-Bench26.819.6

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.