Skip to main content

Critical Physics Tasks (CritPt)

A display-only Artificial Analysis metric for research-level physics reasoning.

Benchmark score on CritPt — June 2, 2026

BenchLM mirrors the published score view for CritPt. GPT-5.4 Pro leads the public snapshot at 30.0% , followed by GPT-5.5 (27.1%) and Gemini 3 Pro Deep Think (25.7%). BenchLM does not use these results to rank models overall.

118 modelsReasoningCurrentDisplay onlyUpdated June 2, 2026

The published CritPt snapshot is tightly clustered at the top: GPT-5.4 Pro sits at 30.0%, while the third row is only 4.3 points behind. The broader top-10 spread is 17.1 points, so the benchmark still separates strong models even when the leaders cluster.

118 models have been evaluated on CritPt. The benchmark falls in the Reasoning category. This category carries a 17% weight in BenchLM.ai's overall scoring system. CritPt is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About CritPt

Year

2026

Tasks

Research-level physics questions

Format

Accuracy

Difficulty

Research-level physics reasoning

BenchLM stores CritPt as a display-only research physics reasoning row from Artificial Analysis benchmark cards.

BenchLM freshness & provenance

Version

CritPt 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Benchmark score table (118 models)

1
30.0%
2
27.1%
3
25.7%
4
23.4%
5
20.9%
6
17.7%
7
16.9%
8
13.4%
9
13.1%
10
12.9%
11
12.6%
12
12.0%
13
11.6%
14
11.3%
15
10.0%
16
10.0%
17
9.3%
18
9.1%
19
8.7%
20
8.0%
21
8.0%
22
7.1%
23
5.7%
24
5.7%
25
5.7%
26
5.1%
27
4.9%
28
4.6%
29
4.6%
30
4.6%
31
4.0%
32
3.7%
33
3.4%
34
3.1%
35
3.1%
36
2.9%
39
2.8%
40
2.6%
41
2.3%
42
2.0%
43
2.0%
44
2.0%
45
1.7%
46
1.7%
47
1.4%
48
1.4%
49
1.4%
50
1.4%
51
1.4%
52
1.1%
53
1.1%
54
1.1%
55
1.1%
56
1.1%
57
1.1%
58
1.1%
59
0.9%
60
0.9%
61
0.9%
62
0.9%
63
0.9%
64
0.9%
65
0.9%
66
0.6%
67
0.6%
68
0.6%
69
0.6%
70
0.3%
71
0.3%
72
0.3%
73
0.3%
75
0.3%
76
0.3%
77
0.3%
78
0.3%
79
0.0%
80
0.0%
81
0.0%
82
0.0%
83
0.0%
84
0.0%
85
0.0%
86
0.0%
87
0.0%
88
0.0%
89
0.0%
90
0.0%
91
0.0%
92
0.0%
93
0.0%
94
0.0%
95
0.0%
96
0.0%
97
0.0%
98
0.0%
99
0.0%
100
0.0%
101
0.0%
102
0.0%
103
0.0%
104
0.0%
105
0.0%
106
0.0%
108
0.0%
109
0.0%
110
0.0%
111
0.0%
112
0.0%
113
0.0%
114
0.0%
115
0.0%
116
0.0%
117
0.0%
118
0.0%

FAQ

What does CritPt measure?

A display-only Artificial Analysis metric for research-level physics reasoning.

Which model scores highest on CritPt?

GPT-5.4 Pro by OpenAI currently leads with a score of 30.0% on CritPt.

How many models are evaluated on CritPt?

118 AI models have been evaluated on CritPt on BenchLM.

Last updated: June 2, 2026 · BenchLM version CritPt 2026

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.