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 Claude Opus 4.5

AnthropicvsAnthropic43 shared benchmarks412 head-to-head
BenchmarkClaude Fable 5Claude Opus 4.5
AA Agentic Index56.659.6
AA Intelligence62.141.9
AA-LCR76.776
AA-Omniscience43.314
arc_agi_190.582
ARC-AGI-276.837.6
arena_elo15081473
arena_text_factuality14861458
Artificial Analysis Coding Index76.547.8
browsecomp8837
charxiv_rq89.468.5
coding_arena_elo16261495
critpt28.64.6
deepsearchqa_f194.276.1
gdpval61.947.3
GPQA Diamond92.687
HLE64.530.8
HLE (with tools)64.543.4
IFBench63.558
livebench78.376
livebench_agentic_coding62.239.7
livebench_coding8679.7
livebench_data_analysis80.574.4
livebench_instruction_following75.862.5
livebench_language90.781.3
livebench_math9690.4
livebench_reasoning89.780.1
mathvision94.877.1
MCP Atlas84.769.8
MMMU-Pro84.274
OmniScience Accuracy65.346.6
OmniScience Non-Hallucination36.439
OSWorld-Verified8566.3
PaperBench88.872.9
scicode60.250
simplebench81.962
simpleqa_verified68.341.8
SWE-bench Multilingual86.677.5
SWE-bench Pro8057.1
SWE-bench Verified9581.5
Terminal-Bench Hard62.947
toolathlon61.743.5
τ²-Bench Telecom (AA run)98.589.5

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.