Which model leads on OTIS Mock AIME 2024-2025?

Claude Fable 5 from Anthropic leads OTIS Mock AIME 2024-2025 with a score of 99.7. The median score across 104 tested models is 56.6.

Is OTIS Mock AIME 2024-2025 saturated?

Yes · the top model on OTIS Mock AIME 2024-2025 has reached 99.7 out of 100, within 5% of the theoretical ceiling. This benchmark is approaching saturation and may be replaced by a harder successor.

Does OTIS Mock AIME 2024-2025 predict performance on other benchmarks?

Yes · OTIS Mock AIME 2024-2025 scores correlate 0.96 with OpenCompass · MMLU-Pro across 10 shared models. Models that do well on OTIS Mock AIME 2024-2025 tend to do well on OpenCompass · MMLU-Pro.

How often is OTIS Mock AIME 2024-2025 data refreshed?

BenchGecko pulls updates daily. New model scores on OTIS Mock AIME 2024-2025 appear as soon as they are published by Epoch AI or the model provider.

Benchmark · MathSettled

OTIS Mock AIME 2024-2025

Name: OTIS Mock AIME 2024-2025 Benchmark
Creator: BenchGecko
License: https://creativecommons.org/licenses/by/4.0/

OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.

Updated 2026-06-12

Models tested

104

Top score

99.7

Claude Fable 5

Median

56.6

min 0.5

Top-5 spread

σ 1.3

Settled

The Frontier

Best score over time · one chart, every benchmark

Chart type

Frontier on OTIS Mock AIME 2024-2025 rose from 73.3 to 99.7 in 18 months · +26.4 points · latest leader Claude Fable 5 from Anthropic.

Pink dots = frontier records · 11 totalClick to open model page

Full rankings

104 models tested · sorted by score

#	Model	Score	Price
1	Claude Fable 5· Anthropic	99.7	$10.00
2	Claude Opus 4.8· Anthropic	98.3	$5.00
3	Claude Opus 4.7· Anthropic	97.8	$5.00
4	Kimi K2.7 Code· moonshotai	96.4	$0.61
5	GPT-5.2· OpenAI	96.1	$1.75
6	Kimi K2.6· moonshotai	96.1	$0.66
7	Gemini 3.1 Pro Preview· Google DeepMind	95.6	$2.00
8	Gemini 3.5 Flash· Google DeepMind	95.5	$1.50
9	GPT-5.4· OpenAI	95.3	$2.50
10	Qwen3.7 Max· Alibaba Qwen	95.0	$1.25
11	Claude Opus 4.6· Anthropic	94.4	$5.00
12	Gemini 3 Flash Preview· Google DeepMind	92.8	$0.50
13	GLM 5.1· z-ai	92.2	$0.97
14	Kimi K2.5· moonshotai	92.2	$0.38
15	Gemini 3 Pro· Google DeepMind	91.4	—
16	GPT-5· OpenAI	91.4	$1.25
17	Qwen3.6 Max Preview· Alibaba Qwen	91.1	$1.04
18	Qwen3.6 Plus· Alibaba Qwen	90.5	$0.33
19	U Muse Spark· Unknown	88.9	—
20	gpt-oss-120b· OpenAI	88.9	$0.04
21	GPT-5.1· OpenAI	88.6	$1.25
22	DeepSeek V3.2· DeepSeek	87.8	$0.21
23	GPT-5.4 Nano· OpenAI	87.8	$0.20
24	GPT-5.4 Mini· OpenAI	87.2	$0.75
25	GPT-5 Mini· OpenAI	86.7	$0.25
26	Qwen3 235B A22B Thinking 2507· Alibaba Qwen	86.7	$0.15
27	Claude Opus 4.5· Anthropic	86.1	$5.00
28	Qwen3.6 Flash· Alibaba Qwen	86.1	$0.19
29	Claude Sonnet 4.6· Anthropic	85.8	$3.00
30	Qwen3.5-Flash· Alibaba Qwen	85.5	$0.07
31	Qwen 3.5 Plus (hosted 397B-A17B)· Alibaba Qwen	85.0	—
32	Gemini 2.5 Pro· Google DeepMind	84.7	$1.25
33	Grok 4· xAI	84.0	—
34	o3· OpenAI	83.9	$2.00
35	GLM 4.7· z-ai	83.3	$0.40
36	Kimi K2 Thinking· moonshotai	83.0	$0.60
37	o4 Mini· OpenAI	81.7	$1.10
38	GPT-5 Nano· OpenAI	81.1	$0.05
39	GLM 5· z-ai	80.0	$0.60
40	Claude Sonnet 4.5· Anthropic	77.8	$3.00
41	Grok-3 mini· xAI	77.8	—
42	o3 Mini· OpenAI	76.9	$1.10
43	o1· OpenAI	73.3	$15.00
44	Qwen3 Max· Alibaba Qwen	73.3	$0.78
45	Gemini 2.5 Flash· Google DeepMind	73.0	$0.30
46	Claude Sonnet 4· Anthropic	71.1	$3.00
47	Claude Opus 4.1· Anthropic	68.9	$15.00
48	Claude Haiku 4.5· Anthropic	66.6	$1.00
49	R1 0528· DeepSeek	66.4	$0.50
50	Claude Opus 4· Anthropic	64.4	$15.00
51	Claude 3.7 Sonnet· Anthropic	57.7	—
52	Gemini 2.0 Flash Thinking (Jan 2025)· Google DeepMind	57.7	—
53	Grok 3· xAI	55.5	—
54	R1· DeepSeek	53.3	$0.70
55	o1-mini· OpenAI	46.9	—
56	GPT-4.1 Mini· OpenAI	44.7	$0.40
57	GPT-4.1· OpenAI	38.3	$2.00
58	GPT-4.5· OpenAI	37.7	—
59	Mistral Medium 3· Mistral AI	32.1	$0.40
60	Gemini 2.0 Flash· Google DeepMind	31.0	$0.10
61	Gemini 2.0 Flash (Dec 2024)· Google DeepMind	31.0	—
62	o1-preview· OpenAI	31.0	—
63	U Magistral Small 1.1· Unknown	29.9	—
64	GPT-4.1 Nano· OpenAI	28.8	$0.10
65	Llama 4 Maverick· Meta	20.5	$0.15
66	Gemma 3 27B· Google DeepMind	19.6	$0.08
67	Gemma 3 27B (free)· Google DeepMind	19.6	$0.00
68	Qwen2.5-Max· Alibaba Qwen	16.0	—
69	DeepSeek V3· DeepSeek	15.8	$0.20
70	Phi 4· Microsoft	13.7	$0.07
71	Grok-2 (Dec 2024)· xAI	11.4	—
72	Llama 3.1 405B· Meta	9.6	—
73	Mistral Large 2407· Mistral AI	8.4	$2.00
74	Qwen2.5 72B Instruct· Alibaba Qwen	8.0	$0.36
75	Llama 4 Scout· Meta	7.7	$0.10
76	Mistral Large 2411· Mistral AI	7.7	$2.00
77	GPT-4o-mini· OpenAI	6.8	$0.15
78	GPT-4o-mini (2024-07-18)· OpenAI	6.8	$0.15
79	Gemini 1.5 Pro (Feb 2024)· Google DeepMind	6.7	—
80	Gemini 1.5 Pro (May 2024)· Google DeepMind	6.7	—
81	Claude 3.5 Sonnet· Anthropic	6.4	—
82	GPT-4o (2024-08-06)· OpenAI	6.3	$2.50
83	GPT-4o (2024-11-20)· OpenAI	6.3	$2.50
84	GPT-4o (2024-05-13)· OpenAI	6.2	$5.00
85	Llama 3.3 70B Instruct (free)· Meta	5.0	$0.00
86	Claude 3 Opus· Anthropic	4.6	—
87	Claude 3.5 Haiku· Anthropic	4.2	—
88	Llama 3 70B Instruct· Meta	4.2	$0.51
89	Llama 3-70B· Meta	4.2	—
90	Gemini 1.5 Flash (May 2024)· Google DeepMind	3.8	—
91	Llama 3.1 70B Instruct· Meta	3.5	$0.40
92	Llama 3.2 90B· Meta	2.5	—
93	Claude 2· Anthropic	2.4	—
94	Claude 3 Sonnet· Anthropic	2.4	—
95	Llama 3.1 8B Instruct· Meta	2.4	$0.02
96	Claude 2.1· Anthropic	1.9	—
97	Mistral Large· Mistral AI	1.9	$2.00
98	Claude 3 Haiku· Anthropic	1.7	$0.25
99	Gemma 2 27B· Google DeepMind	1.3	$0.65
100	Gemini 1.0 Pro· Google DeepMind	1.0	—
101	GPT-4 Turbo· OpenAI	1.0	$10.00
102	Llama 3 8B Instruct· Meta	0.7	$0.14
103	Gemma 2 9B· Google DeepMind	0.5	$0.03
104	GPT-4 (older v0314)· OpenAI	0.5	$30.00