Categories

Per-category leaderboards for the MOMENT benchmark.

Bridge Loads14 questions

This category tests bridge load determination and distribution using AASHTO-based criteria. Tasks focus on converting bridge geometry, loading conditions, and design parameters into member forces, reactions, moments, and resistance checks.

Last updated: Aug 5, 2026
RankModelScore
1
anthropic logoClaude Opus 4.7
0.0%
2
anthropic logoClaude Opus 4.8
0.0%
3
google logoGemini 3 Pro Preview
0.0%
4
google logoGemini 3.1 Pro Preview
0.0%
5
openai logoGPT-5.6 Sol High
0.0%
6
openai logoGPT-5.6 Sol XHigh
0.0%
7
anthropic logoClaude Fable 5
0.0%
8
anthropic logoClaude Opus 4.5
0.0%
9
anthropic logoClaude Opus 4.6
0.0%
10
anthropic logoClaude Opus 5
0.0%
11
openai logoGPT-5.5 High
0.0%
12
openai logoGPT-5.5 Low
0.0%
13
openai logoGPT-5.5 Medium
0.0%
14
openai logoGPT-5.5 XHigh
0.0%
15
openai logoGPT-5.6 Sol Medium
0.0%
16
moonshot logoKimi K2.6
0.0%
17
anthropic logoClaude Sonnet 4.5
0.0%
18
anthropic logoClaude Sonnet 4.6
0.0%
19
openai logoGPT-5.4 High
0.0%
20
openai logoGPT-5.4 XHigh
0.0%
21
openai logoGPT-5.6 Luna High
0.0%
22
openai logoGPT-5.6 Luna Medium
0.0%
23
openai logoGPT-5.6 Sol Low
0.0%
24
xai logoGrok 4.1 Fast Reasoning
0.0%
25
openai logoO3
0.0%
26
google logoGemini 3.1 Flash-Lite Preview
0.0%
27
openai logoGPT-5 High
0.0%
28
openai logoGPT-5 Mini Low
0.0%
29
openai logoGPT-5.1 High
0.0%
30
openai logoGPT-5.2 Low
0.0%
31
openai logoGPT-5.3-Codex High
0.0%
32
openai logoGPT-5.3-Codex Medium
0.0%
33
openai logoGPT-5.3-Codex XHigh
0.0%
34
openai logoGPT-5.4 Medium
0.0%
35
openai logoGPT-5.6 Luna Low
0.0%
36
openai logoGPT-5.6 Terra Medium
0.0%
37
openai logoGPT-5.6 Terra XHigh
0.0%
38
xai logoGrok 4.20
0.0%
39
moonshot logoKimi K2.5
0.0%
40
moonshot logoKimi K2.5 Thinking
0.0%
41
openai logoO4 Mini
0.0%
42
qwen logoQwen3.5 35B
0.0%
43
anthropic logoClaude Haiku 4.5
0.0%
44
openai logoGPT-5 Mini High
0.0%
45
openai logoGPT-5 Mini Medium
0.0%
46
openai logoGPT-5.2 Medium
0.0%
47
openai logoGPT-5.2 XHigh
0.0%
48
openai logoGPT-5.4 Low
0.0%
49
openai logoGPT-5.6 Terra High
0.0%
50
xai logoGrok 4.20 Beta Latest
0.0%
51
openai logoO1
0.0%
52
openai logoO3 Mini
0.0%
53
qwen logoQwen3.6 35B A3B
0.0%
54
openai logoGPT-5.2 High
0.0%
55
openai logoGPT-5.3-Codex Low
0.0%
56
openai logoGPT-5.6 Luna XHigh
0.0%
57
openai logoGPT-5.6 Terra Low
0.0%
58
openai logoGPT-5 Mini Minimal
0.0%
59
xai logoGrok 4.1 Fast Non-Reasoning
0.0%
60
openai logoGPT-4.1
0.0%
61
openai logoGPT-OSS 20B
0.0%
62
qwen logoQwen3 32B
0.0%
63
openai logoGPT-4o
0.0%
64
google logoGemma 4 31B
0.0%
65
qwen logoQwen2.5 32B
0.0%
66
google logoGemma 4 26B
0.0%
67
google logoGemma 4 E4B
0.0%
68
google logoGemma 4 E2B
0.0%

Building Loads15 questions

This category tests building-level gravity, wind, and seismic load application. Tasks focus on selecting the controlling code provisions, distributing loads through diaphragms and vertical elements, and identifying governing design effects.

Awaiting published benchmark runs

No published leaderboard entries yet.

Connection Design4 questions

This category tests practical connection design across steel, cold-formed steel, timber, and related details. Tasks focus on load transfer, fastener or weld capacity, detailing choices, and limit states that govern connection adequacy.

Awaiting published benchmark runs

No published leaderboard entries yet.

Engineering Mechanics7 questions

This category tests foundational structural mechanics without relying on code lookup. Tasks focus on equilibrium, force resolution, section properties, reactions, and shear or moment behavior from text-only geometry.

Last updated: Aug 5, 2026
RankModelScore
1
anthropic logoClaude Fable 5
0.0%
2
anthropic logoClaude Haiku 4.5
0.0%
3
anthropic logoClaude Opus 4.5
0.0%
4
anthropic logoClaude Opus 4.6
0.0%
5
anthropic logoClaude Opus 4.7
0.0%
6
anthropic logoClaude Opus 4.8
0.0%
7
anthropic logoClaude Opus 5
0.0%
8
anthropic logoClaude Sonnet 4.5
0.0%
9
google logoGemini 3 Pro Preview
0.0%
10
google logoGemini 3.1 Flash-Lite Preview
0.0%
11
google logoGemini 3.1 Pro Preview
0.0%
12
openai logoGPT-5 High
0.0%
13
openai logoGPT-5 Mini High
0.0%
14
openai logoGPT-5 Mini Medium
0.0%
15
openai logoGPT-5.2 High
0.0%
16
openai logoGPT-5.2 Low
0.0%
17
openai logoGPT-5.2 XHigh
0.0%
18
openai logoGPT-5.3-Codex High
0.0%
19
openai logoGPT-5.3-Codex Low
0.0%
20
openai logoGPT-5.3-Codex Medium
0.0%
21
openai logoGPT-5.3-Codex XHigh
0.0%
22
openai logoGPT-5.4 High
0.0%
23
openai logoGPT-5.4 XHigh
0.0%
24
openai logoGPT-5.5 High
0.0%
25
openai logoGPT-5.5 Medium
0.0%
26
openai logoGPT-5.5 XHigh
0.0%
27
openai logoGPT-5.6 Luna High
0.0%
28
openai logoGPT-5.6 Luna Medium
0.0%
29
openai logoGPT-5.6 Sol Low
0.0%
30
openai logoGPT-5.6 Sol Medium
0.0%
31
openai logoGPT-5.6 Sol XHigh
0.0%
32
openai logoGPT-5.6 Terra High
0.0%
33
openai logoGPT-5.6 Terra Low
0.0%
34
openai logoGPT-5.6 Terra Medium
0.0%
35
openai logoGPT-5.6 Terra XHigh
0.0%
36
xai logoGrok 4.1 Fast Reasoning
0.0%
37
xai logoGrok 4.20
0.0%
38
moonshot logoKimi K2.5 Thinking
0.0%
39
moonshot logoKimi K2.6
0.0%
40
openai logoO1
0.0%
41
openai logoO3
0.0%
42
openai logoO3 Mini
0.0%
43
openai logoO4 Mini
0.0%
44
qwen logoQwen3.5 35B
0.0%
45
qwen logoQwen3.6 35B A3B
0.0%
46
anthropic logoClaude Sonnet 4.6
0.0%
47
openai logoGPT-5 Mini Low
0.0%
48
openai logoGPT-5.2 Medium
0.0%
49
openai logoGPT-5.4 Low
0.0%
50
openai logoGPT-5.4 Medium
0.0%
51
openai logoGPT-5.5 Low
0.0%
52
openai logoGPT-5.6 Luna Low
0.0%
53
openai logoGPT-5.6 Luna XHigh
0.0%
54
openai logoGPT-5.6 Sol High
0.0%
55
moonshot logoKimi K2.5
0.0%
56
openai logoGPT-5 Mini Minimal
0.0%
57
google logoGemma 4 E4B
0.0%
58
openai logoGPT-5.1 High
0.0%
59
openai logoGPT-OSS 20B
0.0%
60
openai logoGPT-4.1
0.0%
61
xai logoGrok 4.1 Fast Non-Reasoning
0.0%
62
xai logoGrok 4.20 Beta Latest
0.0%
63
qwen logoQwen3 32B
0.0%
64
google logoGemma 4 31B
0.0%
65
google logoGemma 4 26B
0.0%
66
openai logoGPT-4o
0.0%
67
qwen logoQwen2.5 32B
0.0%
68
google logoGemma 4 E2B
0.0%

Environmental Loads4 questions

This category tests environmental load calculations for wind, snow, and ice effects. Tasks focus on applying stated site, exposure, geometry, and occupancy parameters to determine localized pressures or line loads.

Awaiting published benchmark runs

No published leaderboard entries yet.

Foundation Design5 questions

This category tests foundation and geotechnical load transfer checks. Tasks focus on bearing, pile capacity, pile group behavior, footing moments, and construction inspection requirements from stated soil and foundation conditions.

Awaiting published benchmark runs

No published leaderboard entries yet.

Member Design Concrete11 questions

This category tests concrete member design and detailing. Tasks focus on strength, serviceability, anchorage, shear, moment magnification, strut-and-tie behavior, and reinforcement requirements using stated section and material data.

Last updated: Aug 5, 2026
RankModelScore
1
moonshot logoKimi K2.5 Thinking
0.0%
2
anthropic logoClaude Fable 5
0.0%
3
anthropic logoClaude Opus 4.5
0.0%
4
anthropic logoClaude Opus 4.6
0.0%
5
anthropic logoClaude Opus 4.7
0.0%
6
anthropic logoClaude Opus 4.8
0.0%
7
anthropic logoClaude Opus 5
0.0%
8
anthropic logoClaude Sonnet 4.6
0.0%
9
google logoGemini 3.1 Pro Preview
0.0%
10
openai logoGPT-5 High
0.0%
11
openai logoGPT-5 Mini Medium
0.0%
12
openai logoGPT-5.2 High
0.0%
13
openai logoGPT-5.2 XHigh
0.0%
14
openai logoGPT-5.3-Codex High
0.0%
15
openai logoGPT-5.3-Codex Low
0.0%
16
openai logoGPT-5.3-Codex Medium
0.0%
17
openai logoGPT-5.4 High
0.0%
18
openai logoGPT-5.4 Low
0.0%
19
openai logoGPT-5.4 Medium
0.0%
20
openai logoGPT-5.4 XHigh
0.0%
21
openai logoGPT-5.5 High
0.0%
22
openai logoGPT-5.5 Low
0.0%
23
openai logoGPT-5.5 Medium
0.0%
24
openai logoGPT-5.6 Luna Medium
0.0%
25
openai logoGPT-5.6 Sol High
0.0%
26
openai logoGPT-5.6 Sol Medium
0.0%
27
openai logoGPT-5.6 Sol XHigh
0.0%
28
openai logoGPT-5.6 Terra High
0.0%
29
openai logoGPT-5.6 Terra Medium
0.0%
30
openai logoGPT-5.6 Terra XHigh
0.0%
31
xai logoGrok 4.1 Fast Reasoning
0.0%
32
moonshot logoKimi K2.5
0.0%
33
moonshot logoKimi K2.6
0.0%
34
anthropic logoClaude Sonnet 4.5
0.0%
35
google logoGemini 3 Pro Preview
0.0%
36
google logoGemini 3.1 Flash-Lite Preview
0.0%
37
openai logoGPT-5 Mini High
0.0%
38
openai logoGPT-5.1 High
0.0%
39
openai logoGPT-5.2 Low
0.0%
40
openai logoGPT-5.2 Medium
0.0%
41
openai logoGPT-5.3-Codex XHigh
0.0%
42
openai logoGPT-5.5 XHigh
0.0%
43
openai logoGPT-5.6 Luna High
0.0%
44
openai logoGPT-5.6 Luna Low
0.0%
45
openai logoGPT-5.6 Sol Low
0.0%
46
openai logoGPT-5.6 Terra Low
0.0%
47
openai logoO1
0.0%
48
openai logoO3
0.0%
49
openai logoO3 Mini
0.0%
50
qwen logoQwen3.5 35B
0.0%
51
anthropic logoClaude Haiku 4.5
0.0%
52
openai logoGPT-5.6 Luna XHigh
0.0%
53
xai logoGrok 4.20
0.0%
54
qwen logoQwen3.6 35B A3B
0.0%
55
openai logoGPT-5 Mini Low
0.0%
56
openai logoO4 Mini
0.0%
57
openai logoGPT-4o
0.0%
58
openai logoGPT-5 Mini Minimal
0.0%
59
xai logoGrok 4.20 Beta Latest
0.0%
60
xai logoGrok 4.1 Fast Non-Reasoning
0.0%
61
openai logoGPT-OSS 20B
0.0%
62
google logoGemma 4 31B
0.0%
63
openai logoGPT-4.1
0.0%
64
qwen logoQwen2.5 32B
0.0%
65
google logoGemma 4 26B
0.0%
66
qwen logoQwen3 32B
0.0%
67
google logoGemma 4 E2B
0.0%
68
google logoGemma 4 E4B
0.0%

Member Design Masonry7 questions

This category tests masonry member design and detailing. Tasks focus on CMU walls, lintels, anchors, lap splices, shear wall reinforcement, and out-of-plane behavior under stated TMS-based criteria.

Last updated: Aug 5, 2026
RankModelScore
1
anthropic logoClaude Opus 5
0.0%
2
google logoGemini 3 Pro Preview
0.0%
3
google logoGemini 3.1 Pro Preview
0.0%
4
openai logoGPT-5.4 XHigh
0.0%
5
openai logoGPT-5.5 High
0.0%
6
openai logoGPT-5.5 Medium
0.0%
7
openai logoGPT-5.6 Luna Low
0.0%
8
xai logoGrok 4.20
0.0%
9
anthropic logoClaude Fable 5
0.0%
10
anthropic logoClaude Haiku 4.5
0.0%
11
anthropic logoClaude Opus 4.5
0.0%
12
anthropic logoClaude Opus 4.6
0.0%
13
anthropic logoClaude Opus 4.7
0.0%
14
anthropic logoClaude Opus 4.8
0.0%
15
anthropic logoClaude Sonnet 4.5
0.0%
16
anthropic logoClaude Sonnet 4.6
0.0%
17
google logoGemini 3.1 Flash-Lite Preview
0.0%
18
openai logoGPT-5 High
0.0%
19
openai logoGPT-5 Mini High
0.0%
20
openai logoGPT-5 Mini Medium
0.0%
21
openai logoGPT-5.1 High
0.0%
22
openai logoGPT-5.2 High
0.0%
23
openai logoGPT-5.2 Low
0.0%
24
openai logoGPT-5.2 Medium
0.0%
25
openai logoGPT-5.2 XHigh
0.0%
26
openai logoGPT-5.3-Codex High
0.0%
27
openai logoGPT-5.3-Codex Low
0.0%
28
openai logoGPT-5.3-Codex Medium
0.0%
29
openai logoGPT-5.3-Codex XHigh
0.0%
30
openai logoGPT-5.4 High
0.0%
31
openai logoGPT-5.4 Low
0.0%
32
openai logoGPT-5.4 Medium
0.0%
33
openai logoGPT-5.5 Low
0.0%
34
openai logoGPT-5.5 XHigh
0.0%
35
openai logoGPT-5.6 Luna High
0.0%
36
openai logoGPT-5.6 Luna Medium
0.0%
37
openai logoGPT-5.6 Luna XHigh
0.0%
38
openai logoGPT-5.6 Sol High
0.0%
39
openai logoGPT-5.6 Sol Low
0.0%
40
openai logoGPT-5.6 Sol Medium
0.0%
41
openai logoGPT-5.6 Sol XHigh
0.0%
42
openai logoGPT-5.6 Terra High
0.0%
43
openai logoGPT-5.6 Terra Low
0.0%
44
openai logoGPT-5.6 Terra Medium
0.0%
45
openai logoGPT-5.6 Terra XHigh
0.0%
46
xai logoGrok 4.1 Fast Reasoning
0.0%
47
xai logoGrok 4.20 Beta Latest
0.0%
48
moonshot logoKimi K2.5
0.0%
49
moonshot logoKimi K2.5 Thinking
0.0%
50
moonshot logoKimi K2.6
0.0%
51
openai logoO3
0.0%
52
openai logoO3 Mini
0.0%
53
openai logoO4 Mini
0.0%
54
qwen logoQwen3.5 35B
0.0%
55
openai logoGPT-5 Mini Low
0.0%
56
openai logoGPT-5 Mini Minimal
0.0%
57
xai logoGrok 4.1 Fast Non-Reasoning
0.0%
58
openai logoO1
0.0%
59
openai logoGPT-4o
0.0%
60
openai logoGPT-OSS 20B
0.0%
61
qwen logoQwen2.5 32B
0.0%
62
qwen logoQwen3.6 35B A3B
0.0%
63
qwen logoQwen3 32B
0.0%
64
google logoGemma 4 31B
0.0%
65
openai logoGPT-4.1
0.0%
66
google logoGemma 4 E4B
0.0%
67
google logoGemma 4 26B
0.0%
68
google logoGemma 4 E2B
0.0%

Member Design Steel9 questions

This category tests steel and cold-formed steel member design. Tasks focus on member selection, flexural strength, tensile strength, base plates, seismic detailing, staged construction effects, and governing limit states.

Last updated: Aug 5, 2026
RankModelScore
1
anthropic logoClaude Fable 5
0.0%
2
anthropic logoClaude Opus 4.5
0.0%
3
anthropic logoClaude Opus 4.6
0.0%
4
anthropic logoClaude Opus 4.7
0.0%
5
anthropic logoClaude Opus 4.8
0.0%
6
anthropic logoClaude Opus 5
0.0%
7
google logoGemini 3 Pro Preview
0.0%
8
openai logoGPT-5.3-Codex High
0.0%
9
openai logoGPT-5.3-Codex Low
0.0%
10
openai logoGPT-5.3-Codex Medium
0.0%
11
openai logoGPT-5.3-Codex XHigh
0.0%
12
openai logoGPT-5.4 High
0.0%
13
openai logoGPT-5.4 Low
0.0%
14
openai logoGPT-5.4 XHigh
0.0%
15
openai logoGPT-5.5 High
0.0%
16
openai logoGPT-5.5 Low
0.0%
17
openai logoGPT-5.5 Medium
0.0%
18
openai logoGPT-5.5 XHigh
0.0%
19
openai logoGPT-5.6 Luna High
0.0%
20
openai logoGPT-5.6 Luna Low
0.0%
21
openai logoGPT-5.6 Luna Medium
0.0%
22
openai logoGPT-5.6 Sol High
0.0%
23
openai logoGPT-5.6 Sol Low
0.0%
24
openai logoGPT-5.6 Sol Medium
0.0%
25
openai logoGPT-5.6 Sol XHigh
0.0%
26
openai logoGPT-5.6 Terra Low
0.0%
27
openai logoGPT-5.6 Terra Medium
0.0%
28
openai logoGPT-5.6 Terra XHigh
0.0%
29
xai logoGrok 4.1 Fast Reasoning
0.0%
30
moonshot logoKimi K2.5
0.0%
31
moonshot logoKimi K2.6
0.0%
32
anthropic logoClaude Haiku 4.5
0.0%
33
anthropic logoClaude Sonnet 4.5
0.0%
34
anthropic logoClaude Sonnet 4.6
0.0%
35
google logoGemini 3.1 Flash-Lite Preview
0.0%
36
google logoGemini 3.1 Pro Preview
0.0%
37
openai logoGPT-5 High
0.0%
38
openai logoGPT-5 Mini High
0.0%
39
openai logoGPT-5 Mini Low
0.0%
40
openai logoGPT-5.1 High
0.0%
41
openai logoGPT-5.2 High
0.0%
42
openai logoGPT-5.2 Low
0.0%
43
openai logoGPT-5.2 Medium
0.0%
44
openai logoGPT-5.2 XHigh
0.0%
45
openai logoGPT-5.4 Medium
0.0%
46
openai logoGPT-5.6 Luna XHigh
0.0%
47
openai logoGPT-5.6 Terra High
0.0%
48
xai logoGrok 4.20
0.0%
49
moonshot logoKimi K2.5 Thinking
0.0%
50
openai logoO1
0.0%
51
openai logoO3
0.0%
52
openai logoO3 Mini
0.0%
53
openai logoO4 Mini
0.0%
54
qwen logoQwen3.5 35B
0.0%
55
openai logoGPT-5 Mini Medium
0.0%
56
xai logoGrok 4.20 Beta Latest
0.0%
57
openai logoGPT-5 Mini Minimal
0.0%
58
xai logoGrok 4.1 Fast Non-Reasoning
0.0%
59
qwen logoQwen3.6 35B A3B
0.0%
60
google logoGemma 4 31B
0.0%
61
openai logoGPT-4.1
0.0%
62
openai logoGPT-OSS 20B
0.0%
63
qwen logoQwen2.5 32B
0.0%
64
google logoGemma 4 E4B
0.0%
65
google logoGemma 4 26B
0.0%
66
openai logoGPT-4o
0.0%
67
qwen logoQwen3 32B
0.0%
68
google logoGemma 4 E2B
0.0%

Member Design Timber3 questions

This category tests timber member and diaphragm design. Tasks focus on wood column stability, glulam deflection including load-duration effects, and wood structural panel diaphragm capacity.

Last updated: Aug 5, 2026
RankModelScore
1
anthropic logoClaude Fable 5
0.0%
2
anthropic logoClaude Opus 4.6
0.0%
3
anthropic logoClaude Opus 4.7
0.0%
4
anthropic logoClaude Opus 4.8
0.0%
5
anthropic logoClaude Opus 5
0.0%
6
anthropic logoClaude Sonnet 4.5
0.0%
7
anthropic logoClaude Sonnet 4.6
0.0%
8
google logoGemini 3 Pro Preview
0.0%
9
google logoGemini 3.1 Pro Preview
0.0%
10
openai logoGPT-4.1
0.0%
11
openai logoGPT-5 Mini Minimal
0.0%
12
openai logoGPT-5.2 High
0.0%
13
openai logoGPT-5.5 High
0.0%
14
openai logoGPT-5.5 Low
0.0%
15
openai logoGPT-5.5 Medium
0.0%
16
openai logoGPT-5.5 XHigh
0.0%
17
openai logoGPT-5.6 Sol High
0.0%
18
openai logoGPT-5.6 Sol Low
0.0%
19
openai logoGPT-5.6 Sol XHigh
0.0%
20
moonshot logoKimi K2.5
0.0%
21
moonshot logoKimi K2.6
0.0%
22
openai logoO3 Mini
0.0%
23
qwen logoQwen3.5 35B
0.0%
24
anthropic logoClaude Haiku 4.5
0.0%
25
anthropic logoClaude Opus 4.5
0.0%
26
google logoGemini 3.1 Flash-Lite Preview
0.0%
27
openai logoGPT-4o
0.0%
28
openai logoGPT-5 High
0.0%
29
openai logoGPT-5 Mini High
0.0%
30
openai logoGPT-5 Mini Low
0.0%
31
openai logoGPT-5 Mini Medium
0.0%
32
openai logoGPT-5.1 High
0.0%
33
openai logoGPT-5.2 Low
0.0%
34
openai logoGPT-5.2 Medium
0.0%
35
openai logoGPT-5.2 XHigh
0.0%
36
openai logoGPT-5.3-Codex High
0.0%
37
openai logoGPT-5.3-Codex Low
0.0%
38
openai logoGPT-5.3-Codex Medium
0.0%
39
openai logoGPT-5.3-Codex XHigh
0.0%
40
openai logoGPT-5.4 High
0.0%
41
openai logoGPT-5.4 Low
0.0%
42
openai logoGPT-5.4 Medium
0.0%
43
openai logoGPT-5.4 XHigh
0.0%
44
openai logoGPT-5.6 Luna High
0.0%
45
openai logoGPT-5.6 Luna Low
0.0%
46
openai logoGPT-5.6 Luna Medium
0.0%
47
openai logoGPT-5.6 Sol Medium
0.0%
48
openai logoGPT-5.6 Terra High
0.0%
49
openai logoGPT-5.6 Terra Low
0.0%
50
openai logoGPT-5.6 Terra Medium
0.0%
51
openai logoGPT-5.6 Terra XHigh
0.0%
52
xai logoGrok 4.1 Fast Non-Reasoning
0.0%
53
xai logoGrok 4.1 Fast Reasoning
0.0%
54
xai logoGrok 4.20
0.0%
55
moonshot logoKimi K2.5 Thinking
0.0%
56
openai logoO1
0.0%
57
openai logoO3
0.0%
58
openai logoO4 Mini
0.0%
59
qwen logoQwen3.6 35B A3B
0.0%
60
google logoGemma 4 31B
0.0%
61
openai logoGPT-5.6 Luna XHigh
0.0%
62
openai logoGPT-OSS 20B
0.0%
63
xai logoGrok 4.20 Beta Latest
0.0%
64
qwen logoQwen2.5 32B
0.0%
65
google logoGemma 4 26B
0.0%
66
google logoGemma 4 E2B
0.0%
67
google logoGemma 4 E4B
0.0%
68
qwen logoQwen3 32B
0.0%

Protective Design1 question

This category tests protective design, crowd flow, and related life-safety calculations for buildings, venues, and infrastructure.

Awaiting published benchmark runs

No published leaderboard entries yet.

Retaining Walls4 questions

This category tests lateral earth pressure and retaining wall response. Tasks focus on surcharge effects, seismic active pressure, basement wall reactions, and basic stability checks from stated soil and wall conditions.

Awaiting published benchmark runs

No published leaderboard entries yet.

Structural Analysis7 questions

This category tests structural analysis reasoning from text-only descriptions. Tasks focus on deflected shapes, influence lines, approximate frame analysis, indeterminate beam reactions, moment diagrams, and deformation components.

Awaiting published benchmark runs

No published leaderboard entries yet.