priorsBuilder

Inception · released 2026-09-08

Mercury 2.5

Measured on 36 benchmarks.

General frontier

16.2

#120 of 135 models

includes estimates: 24% of the mix is measured for this model

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #280default of 58711.8%

Leader: Opus 5.5 · 61.4%

knowledge

AA-Omniscience

526 results
  1. #308default of 526-39.5

Leader: Opus 5.5 · 46.4

All 36 benchmarks

show 34 more

agentic

AA-Briefcase v1.1

224 results
  1. #185default of 224378

Leader: Sonnet 5.5 · 1823

agentic

AutomationBench-AA

219 results
  1. #174default of 2192.4%

Leader: Gemini 4 · 77.5%

agentic

Harvey's Legal Agent Benchmark

79 results
  1. #64high of 790.0%

Leader: Muse Spark 1.2 · 25.4%

agentic

Legal Research Bench

78 results
  1. #73high of 784.3%

Leader: Muse Spark 1.3 · 55.3%

agentic

SkillsBench

34 results
  1. #34high of 3418.1%

Leader: DeepSeek V4.1 Flash · 69.8%

agentic

Tax Agent Bench

69 results
  1. #69high of 692.5%

Leader: Fable 5.1 · 49.2%

agentic

Terminal-Bench 4.0 (Vals)

47 results
  1. #47high of 470.0%

Leader: Opus 5.5 · 65.2%

agentic

Terminal-Bench Science (Vals)

40 results
  1. #37high of 400.0%

Leader: GPT-6 Astra · 62.9%

coding

Code Migration

77 results
  1. #73high of 774.5%

Leader: Sonnet 5.5 · 69.8%

coding

IOI

44 results
  1. #44high of 442.4%

Leader: Gemini 4 · 100.0%

coding

SciCode

226 results
  1. #182default of 22638.5%

Leader: Opus 5.5 · 66.9%

coding

Terminal-Bench 2.1 (Vals)

74 results
  1. #69high of 7434.5%

Leader: Opus 5.5 · 87.6%

coding

Terminal-Bench v4-AA

216 results
  1. #182default of 2160.0%

Leader: Sonnet 5.5 · 63.6%

coding

Vibe Code Bench v1.1

105 results
  1. #94high of 1053.7%

Leader: Sonnet 5.5 · 92.4%

composite

AA Intelligence Index v4.3.2

610 results
  1. #327default of 61012.3

Leader: Opus 5.5 · 57.6

composite

Vals Index

47 results
  1. #47high of 478.9%

Leader: Gemini 4 · 68.9%

cost

AA Intelligence Index Cost per Task

177 results
  1. #41default of 177$0.12

Leader: GPT-6 Luna · $0.00

cost

Cost to Run AA Intelligence Index

177 results
  1. #43default of 177$218

Leader: GPT-6 Luna · $10.63

economics

Excel Modeling Benchmark

74 results
  1. #73high of 748.8%

Leader: Fable 5.1 · 76.7%

economics

Finance Agent v2

78 results
  1. #75high of 7818.9%

Leader: Gemini 4 · 65.4%

economics

GDP.pdf

210 results
  1. #172default of 2103.6%

Leader: Muse Wonder Full (Max) · 32.6%

economics

GDPval-AA v2.1

288 results
  1. #218default of 288474

Leader: Opus 5.5 · 1866

knowledge

AA-Omniscience Accuracy

526 results
  1. #260default of 52622.7%

Leader: Fable 5.1 · 67.2%

knowledge

AA-Omniscience Non-hallucination

526 results
  1. #277default of 52619.7%

Leader: MiniCPM5-1B (Non-reasoning) · 99.1%

knowledge

MedCode

94 results
  1. #86high of 9431.3%

Leader: Opus 5 · 63.6%

knowledge

MedScribe

96 results
  1. #93high of 9655.1%

Leader: Opus 5.5 · 91.4%

knowledge

Public Benefits Bench v1.1

50 results
  1. #47high of 5045.3%

Leader: Opus 5 · 76.9%

long-context

AA-LCR v1.1

523 results
  1. #199default of 52371.7%

Leader: Kimi K3 · 88.7%

math

ProofBench v1.1

52 results
  1. #50high of 523.0%

Leader: Sonnet 5.5 · 100.0%

reasoning

CritPt

529 results
  1. #352default of 5290.0%

Leader: Muse Wonder Full (Max) · 32.9%

reasoning

LegalBench

135 results
  1. #60high of 13583.1%

Leader: Fable 5 · 88.6%

safety

CyberBench v1.1

45 results
  1. #38high of 4545.5%

Leader: Wonder · 80.4%

speed

Latency (Time to First Token)

351 results
  1. #218default of 3513.7s

Leader: Gemini 2.5 Flash Lite · 0.3s

speed

Output Speed (tokens/s)

351 results
  1. #2default of 351761.8

Leader: Celeris-1 · 1564.1