Mercury 2.5 Benchmark Details

Mercury 2.5 currently shows benchmark results led by MedCode (94 / 105, score 31.33), Vibe Code Bench v1.1 (102 / 112, score 3.68), Legal Research Bench (76 / 81, score 4.33).

Benchmark Results

Mercury 2.5

Benchmark Results

Legal

1 evaluations

Benchmark / mode

Score

Rank/total

Legal Research Bench

Thinking Level · HighTools

4.33

76 / 81

Maintenance & Optimization

1 evaluations

Benchmark / mode

Score

Rank/total

Code Migration

Thinking Level · HighTools

4.52

75 / 78

Code Generation & Editing

1 evaluations

Benchmark / mode

Score

Rank/total

Vibe Code Bench v1.1

Thinking Level · HighTools

3.68

102 / 112

Algorithmic Coding

1 evaluations

Benchmark / mode

Score

Rank/total

IOI (Vals v2)

Thinking Level · HighTools

2.44

45 / 45

Finance

1 evaluations

Benchmark / mode

Score

Rank/total

EMB (Excel Modeling)

Thinking Level · HighTools

8.79

74 / 75

Mathematics

1 evaluations

Benchmark / mode

Score

Rank/total

ProofBench v1.1 (Lean 4)

Thinking Level · HighTools

49 / 51

Service Workflows

1 evaluations

Benchmark / mode

Score

Rank/total

Public Benefits Bench v1.1

Thinking Level · HighTools

45.26

47 / 50

Clinical Workflows

2 evaluations

Benchmark / mode

Score

Rank/total

MedScribe

Thinking Level · HighTools

55.09

104 / 107

MedCode

Thinking Level · HighTools

31.33

94 / 105

Compare with other models