BenchLeader
UnknownAuto-detected

Smaug Flash

Not yet ranked: too few independent results so far.

Blended price
Output speed
First answer
Context
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Composite59

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

BenchmarkdefaultSource
LiveBench Reasoningnot in index86.2%#24LiveBench

Coding

BenchmarkdefaultSource
LiveBench Codingnot in index77.1%#30LiveBench

Agents & tools

BenchmarkdefaultSource
LiveBench Agentic Codingnot in index61.1%#10LiveBench

Maths

BenchmarkdefaultSource
LiveBench Mathematicsnot in index90.1%#24LiveBench

Knowledge

BenchmarkdefaultSource
LiveBench Data Analysisnot in index79.1%#12LiveBench

Instruction following

BenchmarkdefaultSource
LiveBench Languagenot in index79.2%#27LiveBench

Composite

BenchmarkdefaultSource
LiveBench77.4%#15LiveBench

See also

Data as of 9 Sept 2026. Compare with another model.