priorsBuilder

Meta

Wonder

Measured on 16 benchmarks.

General frontier

Not ranked in this mix — too little measured data for its benchmarks.

Your mix’s benchmarks

0 of 8 measured

This model has no results on your mix’s benchmarks.

All 16 benchmarks

show 16 more

agentic

BioMysteryBench

27 results
  1. #19max of 2767.0%

Leader: Sonnet 5.5 · 81.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #8max of 7917.1%

Leader: Muse Spark 1.2 · 25.4%

agentic

Legal Research Bench

78 results
  1. #6max of 7850.5%

Leader: Muse Spark 1.3 · 55.3%

agentic

Tax Agent Bench

69 results
  1. #10max of 6936.3%

Leader: Fable 5.1 · 49.2%

agentic

Terminal-Bench 4.0 (Vals)

47 results
  1. #9max of 4749.5%

Leader: Opus 5.5 · 65.2%

agentic

Terminal-Bench Science (Vals)

40 results
  1. #9max of 4022.9%

Leader: GPT-6 Astra · 62.9%

coding

Code Migration

77 results
  1. #6max of 7762.6%

Leader: Sonnet 5.5 · 69.8%

coding

IOI

44 results
  1. #15max of 4466.9%

Leader: Gemini 4 · 100.0%

coding

Vibe Code Bench v1.1

105 results
  1. #18max of 10583.1%

Leader: Sonnet 5.5 · 92.4%

composite

Vals Index

47 results
  1. #10max of 4761.1%

Leader: Gemini 4 · 68.9%

economics

Excel Modeling Benchmark

74 results
  1. #18max of 7467.1%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #16max of 7856.6%

Leader: Gemini 4 · 65.4%

knowledge

Public Benefits Bench v1.1

50 results
  1. #6max of 5070.2%

Leader: Opus 5 · 76.9%

math

ProofBench v1.1

52 results
  1. #14max of 5284.0%

Leader: Sonnet 5.5 · 100.0%

reasoning

MysteryMechanism

27 results
  1. #15max of 2727.5%

Leader: GPT-6 Astra · 53.2%

safety

CyberBench v1.1

45 results
  1. #1max of 4580.4%

Leader: this model · 80.4%