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 Gemini 3 Pro

AnthropicvsGoogle36 shared benchmarks342 head-to-head
BenchmarkClaude Fable 5Gemini 3 Pro
AA Agentic Index56.652
AA Intelligence62.140.6
AA-LCR76.773
AA-Omniscience43.315.3
arc_agi_190.575
ARC-AGI-276.854
arena_elo15081485
arena_text_factuality14861481
arena_vision13071290
Artificial Analysis Coding Index76.546.5
browsecomp8859.2
charxiv_rq89.481.4
coding_arena_elo16261438
critpt28.69.1
deepsearchqa_f194.263.2
gdpval61.934.2
GDPval-AA (Elo)19321195
GPQA Diamond92.691.9
HLE64.545.8
HLE (with tools)64.545.8
IFBench63.570.4
livebench78.373.4
mathvision94.886.1
MCP Atlas84.770.3
MMMU-Pro84.281
OmniScience Accuracy65.355.8
OmniScience Non-Hallucination36.410
scicode60.256.1
simplebench81.976.4
simpleqa_verified68.372.9
SWE-bench Multilingual86.668.7
SWE-bench Pro8043.3
SWE-bench Verified9578
Terminal-Bench Hard62.956.9
toolathlon61.736.4
τ²-Bench Telecom (AA run)98.598

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.