priorsBuilder

Tencent

Hy4

Measured on 29 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 29 benchmarks

show 29 more

agentic

Agent Arena

50 results
  1. #19default of 503.6%

Leader: Opus 5.5 · 15.5%

agentic

BioMysteryBench

27 results
  1. #14default of 2769.3%

Leader: Sonnet 5.5 · 81.1%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #22default of 799.2%

Leader: Muse Spark 1.2 · 25.4%

agentic

Legal Research Bench

78 results
  1. #18default of 7845.2%

Leader: Muse Spark 1.3 · 55.3%

agentic

Tax Agent Bench

69 results
  1. #16default of 6932.6%

Leader: Fable 5.1 · 49.2%

agentic

Terminal-Bench 4.0 (Vals)

47 results
  1. #38default of 478.1%

Leader: Opus 5.5 · 65.2%

agentic

Terminal-Bench Science (Vals)

40 results
  1. #35default of 401.4%

Leader: GPT-6 Astra · 62.9%

coding

Arena WebDev

122 results
  1. #17default of 1221632

Leader: Opus 5.5 · 1813

coding

Code Migration

77 results
  1. #14default of 7747.4%

Leader: Sonnet 5.5 · 69.8%

coding

IOI

44 results
  1. #17default of 4459.3%

Leader: Gemini 4 · 100.0%

coding

ProgramBench v1 Almost Resolved

62 results
  1. #20default of 6214.5%

Leader: Opus 5.5 · 65.0%

coding

ProgramBench v1 Fully Resolved

62 results
  1. #59default of 620.0%

Leader: Opus 5.5 · 18.5%

coding

ProgramBench v1 Raw Pass Rate

62 results
  1. #23default of 6269.2%

Leader: Opus 5.5 · 87.0%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #48default of 7455.1%

Leader: Opus 5.5 · 87.6%

coding

Vibe Code Bench v1.1

105 results
  1. #30default of 10577.5%

Leader: Sonnet 5.5 · 92.4%

composite

Vals Index

47 results
  1. #31default of 4749.9%

Leader: Gemini 4 · 68.9%

economics

Excel Modeling Benchmark

74 results
  1. #37default of 7458.1%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #21default of 7855.1%

Leader: Gemini 4 · 65.4%

knowledge

MedCode

94 results
  1. #44default of 9443.2%

Leader: Opus 5 · 63.6%

knowledge

MedScribe

96 results
  1. #42default of 9683.6%

Leader: Opus 5.5 · 91.4%

knowledge

Public Benefits Bench v1.1

50 results
  1. #9default of 5068.6%

Leader: Opus 5 · 76.9%

math

ProofBench v1.1

52 results
  1. #18default of 5275.0%

Leader: Sonnet 5.5 · 100.0%

reasoning

LegalBench

135 results
  1. #49default of 13583.8%

Leader: Fable 5 · 88.6%

reliability

Tool-call error rate

171 results
  1. #16default of 1710.1%

Leader: GPT-5.4 Pro · 0.0%

reliability

Uptime (7d)

181 results
  1. #135default of 18198.4%

Leader: GPT-5 Pro · 100.0%

safety

CyberBench v1.1

45 results
  1. #32default of 4565.4%

Leader: Wonder · 80.4%

safety

SRE Bench

32 results
  1. #22default of 322.3%

Leader: GPT-6 Astra · 56.9%

speed

Provider latency

177 results
  1. #144default of 1772.9s

Leader: Qwen 2.5 7B · 0.2s

speed

Provider throughput

176 results
  1. #131default of 17646.0

Leader: Muse Spark 1.1 · 204.3