Skip to main content

Benchmark profile

American Invitational Mathematics Examination 2023 (AIME 2023)

A 15-question, 3-hour examination where each answer is an integer from 000 to 999. Serves as the intermediate step between AMC 10/12 and the USA Mathematical Olympiad (USAMO).

Data verified

How BenchLM shows AIME 2023 right now

BenchLM is tracking AIME 2023 in the local dataset, but exact-source verification records for these rows are still being attached. To avoid a blank benchmark page, BenchLM shows the current tracked rows below as a display-only reference table.

These tracked rows are useful for inspection and spot-checking, but until exact-source attachments are completed they should not be treated as fully verified public benchmark rows.

105 tracked modelsLocal tracked rowsAwaiting exact-source attachmentsDisplay only

Tracked score on AIME 2023 — July 20, 2026

BenchLM mirrors the published tracked score view for AIME 2023. GPT-5.1-Codex-Max leads the public snapshot at 99% , followed by GPT-5.2-Codex (99%) and GPT-5.3 Codex (99%). BenchLM does not use these results to rank models overall.

105 modelsMathStaleDisplay onlyUpdated July 20, 2026

Tracked score table (105 models)

Score
2
99%
3
99%
4
99%
5
GPT-5.4OpenAI
99%
7
99%
8
GPT-5.1OpenAI
99%
9
GPT-5.2OpenAI
99%
10
99%
11
99%
12
99%
13
99%
14
99%
15
99%
18
97%
20
95%
21
94%
22
94%
23
93%
25
o3-proOpenAI
90%
26
90%
27
o3OpenAI
88%
28
GLM-5Z.AI
88%
29
87%
31
86%
32
Qwen2.5-1MAlibaba
85%
33
85%
34
84%
35
84%
36
84%
37
83%
38
83%
39
81%
40
Mercury 2Inception
81%
41
80%
42
80%
43
79%
44
Kimi K2.5Moonshot AI
77%
45
76%
46
76%
47
Aion-2.0Aion Labs
74%
48
73%
50
73%
51
Seed 1.6ByteDance
72%
52
Seed-2.0-LiteByteDance
71%
53
70%
55
68%
56
68%
57
68%
59
GPT-4oOpenAI
66%
60
66%
62
65%
63
65%
65
64%
66
64%
68
62%
69
Seed-2.0-MiniByteDance
62%
70
Claude 3 OpusAnthropic
61%
71
60%
72
58%
74
56%
75
54%
76
Moonshot v1Moonshot AI
53%
77
52%
78
51%
79
50%
82
47%
84
LFM2-24B-A2BLiquidAI
46%
85
45%
86
DeepSeek-R1DeepSeek
44%
88
Nova ProAmazon
41%
90
39%
92
37%
93
36%
94
35%
96
33%
98
31%
99
30%
100
30%
101
29%
102
28%
104
24%
105
23%

The published AIME 2023 snapshot places GPT-5.1-Codex-Max first at 99%. The third row is 0.0 points behind. The broader top-10 range is 0.0 points, so many of the published results sit in a relatively narrow band.

105 models have been evaluated on AIME 2023. The benchmark falls in the Math category. This category carries a 5% weight in BenchLM.ai's overall scoring system. AIME 2023 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About AIME 2023

Year

2023

Tasks

15 problems

Format

Integer answers 000-999

Difficulty

High school olympiad level

AIME is designed for students who score well on AMC 10/12. Problems require creative problem-solving and mathematical insight beyond standard high school curriculum. Only the top scorers qualify for USAMO.

BenchLM freshness & provenance

Version

AIME 2023 2023

Refresh cadence

Static

Staleness state

Stale

Question availability

Public benchmark set

StaleDisplay 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.

FAQ

What does AIME 2023 measure?

A 15-question, 3-hour examination where each answer is an integer from 000 to 999. Serves as the intermediate step between AMC 10/12 and the USA Mathematical Olympiad (USAMO).

Which model leads the published AIME 2023 snapshot?

GPT-5.1-Codex-Max currently leads the published AIME 2023 snapshot with 99% tracked score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on AIME 2023?

105 AI models are included in BenchLM's mirrored AIME 2023 snapshot, based on the public leaderboard captured on July 20, 2026.

Last updated: July 20, 2026 · mirrored from the public benchmark leaderboard

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.