PEGASUS EVAL / RESULTS EXPLORER

Observed benchmark evidence · read-only
Benchmark
Pattern IQ v3
pattern-iq@3.0.0
Questions
50
Models
7
All Models Pass
28
All Fail / Disagreement
0 / 22

Observed model totals · sorted by accuracy

Question × model matrix (50 shown)

Models: 7 of 7 selected
Reset
Questiongpt-5.6Qwen 32B AWQGPT-4o-miniQwen 2.5 14BGemma 2 9B ITQwen 2.5 14B AWQPhi-3 Medium
piq01_numeric_add_3
Find the next number in the sequence: 2, 5, 8, 11, ?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq02_numeric_multiply_add
Find the next number in the sequence: 1, 3, 7, 15, ?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq03_numeric_alternating
Find the next number. The operations alternate +5, then -2: 4, 9, 7, 12, 10, 15, ?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq04_numeric_squares
Find the missing number: 1, 4, 9, ?, 25
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq05_numeric_even_odd_pattern
Fill in the blank: 2, 4, 7, 11, 16, ?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq06_letters_forward_step
Find the next letter: C, F, I, L, ?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq07_letters_skip_pattern
Find the next letter when alphabet-position increments are +2, +3, +4, +5: A, C, F, J, ?
✓ PASS✗ FAIL✓ PASS✓ PASS✓ PASS✓ PASS✗ FAIL
piq08_letters_mirror
Find the missing letter: A, Z, B, Y, C, X, ?
✓ PASS✓ PASS✓ PASS✓ PASS✗ FAIL✗ FAIL✓ PASS
piq09_letters_double_step
Find the next letter when alphabet-position increments are +3, +4, +5, +6: D, G, K, P, ?
✓ PASS✓ PASS✓ PASS✗ FAIL✗ FAIL✗ FAIL✗ FAIL
piq10_letters_two_streams
Find the next pair: (A, Z), (B, Y), (C, X), ?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq11_numeric_mixed_ops
Find the next number: 3, 6, 10, 15, 21, ?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq12_numeric_second_difference
Fill in the blank: 2, 5, 11, 20, 32, ?
✓ PASS✓ PASS✗ FAIL✗ FAIL✓ PASS✓ PASS✓ PASS
piq13_numeric_fraction_pattern
Find the next term: 1/2, 2/3, 3/4, 4/5, ?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq14_numeric_combined_sequence
In the sequence 1, 2, 4, 7, 11, 16, ?, each term after the first adds an increment that increases by
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq15_numeric_prime_pattern
Find the next prime: 2, 3, 5, 7, 11, ?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq16_letter_numeric_combo
Fill in the blank: A1, C2, F3, J4, ?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq17_letter_position_math
Using A=1, B=2, ..., each letter position is the sum of the previous two positions. Starting A(1), B
✓ PASS✓ PASS✓ PASS✗ FAIL✗ FAIL✗ FAIL✗ FAIL
piq18_letters_backward_forward
Pattern: move +3, then -1 repeatedly. Starting from D: D, G, F, I, H, K, ?
✓ PASS✓ PASS✗ FAIL✓ PASS✗ FAIL✓ PASS✗ FAIL
piq19_mixed_odd_even
Given: 2, 9, 4, 11, 6, 13, ? The even numbers increase by 2, the odd numbers increase by 2. What is
✓ PASS✗ FAIL✗ FAIL✓ PASS✓ PASS✓ PASS✓ PASS
piq20_numeric_ratio
Find the missing number: 3, 6, 12, 24, ?, 96
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq21_logic_odd_one_out_numbers
Which number is the only square of an odd integer: 16, 36, 49, 64?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq22_logic_odd_one_letters
Find the next pair in the sequence (A, Z), (C, X), (E, V), (G, T), ?. The first letter advances by 2
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq23_logic_two_dimension
In a 2x2 grid, top row is 2, 4; bottom row is 6, ?. Pattern: each row increases by 2, each column in
✓ PASS✓ PASS✓ PASS✗ FAIL✗ FAIL✓ PASS✗ FAIL
piq24_arithmetic_progression_missing
Find the missing term in the arithmetic pattern: 5, 11, ?, 23, 29
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq25_geometric_progression_missing
Find the missing term in the geometric pattern: 3, 6, 12, ?, 48
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq26_hard_numeric_second_order
Sequence: 1, 2, 4, 7, 11, 16, 22, ?; the differences are 1,2,3,4,5,6,... What is the next term?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq27_hard_numeric_cubic_like
Sequence: 1, 8, 27, 64, ?. Each term is the cube of its position. What is the next term?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq28_hard_numeric_two_interleaved
Sequence: 2, 9, 4, 16, 6, 25, 8, ?. Even terms follow one pattern and odd terms another. Find the mi
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✗ FAIL
piq29_hard_prime_plus_position
Let Tₙ = Pₙ + n, where Pₙ is the nth prime number. For example: T₁ = 3, T₂ = 5, T₃ = 8, T₄ = 11. Wha
✓ PASS✓ PASS✗ FAIL✗ FAIL✓ PASS✗ FAIL✗ FAIL
piq30_hard_fraction_pattern
Sequence: 1/3, 2/5, 3/7, 4/9, ?; what is the next term?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq31_letter_two_dimensional
Pattern of pairs: (A, D), (C, F), (E, H), (G, J), ?. Each letter advances two alphabet positions. Wh
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq32_letter_mirror_center
Original letters advance by +2, +3, +4 alphabet positions: A, C, F, ?. Their mirrors are Z, X, U, ?.
✓ PASS✓ PASS✗ FAIL✗ FAIL✓ PASS✗ FAIL✗ FAIL
piq33_mixed_letter_number_function
Pattern: A1, C3, F6, J10, ?; the letter steps increase by +2, then +3, then +4... the numbers increa
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✗ FAIL✗ FAIL
piq34_mixed_two_sequences_interleaved
Sequence: A, 2, C, 6, E, 12, G, ?. Letters advance by 2. The numbers are 1×2, 2×3, 3×4, 4×5. What is
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✗ FAIL✗ FAIL
piq35_mixed_code_pattern
Using A=1, B=2, ..., Z=26, which letter string is encoded by 3, 1, 20, 20, 1?
✓ PASS✗ FAIL✓ PASS✗ FAIL✗ FAIL✗ FAIL✗ FAIL
piq36v2_numeric_grid_offsets
A 3×3 grid starts with 2 at top-left. Moving one cell right adds 3; moving one cell down adds 4. Wha
✓ PASS✗ FAIL✗ FAIL✗ FAIL✗ FAIL✗ FAIL✗ FAIL
piq37v2_matrix_row_products
Each row has the form [a, b, a×b]. The rows are [2, 3, 6], [3, 4, 12], [4, 5, ?]. What is missing?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq38v2_matrix_column_rule
In each column, the bottom number equals the top number plus the middle number. Top row: 2, 4, 6. Mi
✓ PASS✓ PASS✗ FAIL✓ PASS✗ FAIL✗ FAIL✓ PASS
piq39_logic_odd_one_combined
The first three sets have the form {n, n², n³}. Which set does not have that form: {2, 4, 8}, {3, 9,
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq40_logic_symmetric
In each row, the middle number is the square of the difference between the two edge numbers. If a ro
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✗ FAIL
piq41_advanced_numeric_pattern
Sequence: 10, 11, 13, 16, 20, ?; differences are 1, 2, 3, 4,... What is the next term?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq42_advanced_letter_block
Two-letter blocks start at A, C, F, J, with starting-letter increments +2, +3, +4, then +5. Each blo
✓ PASS✗ FAIL✗ FAIL✗ FAIL✗ FAIL✗ FAIL✗ FAIL
piq43_advanced_fraction_sequence
Sequence: 1, 1/2, 1/3, 1/4, ?; what is the next term?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq44_advanced_alternating_ops
Sequence: 5, 8, 12, 17, 23, ?; differences are +3, +4, +5, +6,... What is the next term?
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq45_advanced_letter_number_code
Code: A1, C4, F8, J13, ?; letter increments: +2, +3, +4...; number increments: +3, +4, +5.... What i
✓ PASS✓ PASS✓ PASS✗ FAIL✓ PASS✗ FAIL✗ FAIL
piq46v2_interleaved_growth
Two sequences are interleaved: 2, 10, 4, 20, 8, 40, 16, ?. The first doubles independently, and so d
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq47v2_balanced_rows
Each row has the same sum. The rows are [2, 5, 7], [3, 4, 7], [6, 1, ?]. What is missing?
✓ PASS✗ FAIL✗ FAIL✗ FAIL✗ FAIL✗ FAIL✗ FAIL
piq48v2_diagonal_progression
Read the main diagonal of a 3×3 grid from top-left to bottom-right: 3, 8, 15. The increases are +5 t
✓ PASS✓ PASS✓ PASS✓ PASS✗ FAIL✗ FAIL✗ FAIL
piq49v2_triangular_counts
A dot pattern has 1 dot in figure 1, 3 in figure 2, 6 in figure 3, and 10 in figure 4. Each figure a
✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS✓ PASS
piq50v2_cyclic_symbols
A marker cycles through positions North, East, South, West, then repeats. It is North at step 1. Whe
✓ PASS✓ PASS✗ FAIL✓ PASS✗ FAIL✓ PASS✓ PASS

✓ pass · ✗ fail · ERROR execution/evaluation error · — unavailable. Outcomes are observations for the selected runs, not general capability claims.