Which model leads on OTIS Mock AIME 2024-2025?

Claude Fable 5 from Anthropic leads OTIS Mock AIME 2024-2025 with a score of 100.0. The median score across 159 tested models is 71.1.

Is OTIS Mock AIME 2024-2025 saturated?

Yes · the top model on OTIS Mock AIME 2024-2025 has reached 100.0 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 GPQA diamond across 155 shared models. Models that do well on OTIS Mock AIME 2024-2025 tend to do well on GPQA diamond.

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 2026-09-28

Models tested

159

Top score

100.0

Claude Fable 5

Median

71.1

min 0.5

Top-5 spread

σ 0.0

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 100.0 in 18 months · +26.7 points · latest leader Claude Fable 5 from Anthropic.

Pink dots = frontier records · 12 totalClick to open model page

Full rankings

159 models tested · sorted by score

#	Model	Score	Price
1	Claude Fable 5· Anthropic	100.0	$10.00
2	Claude Fable 5.1· Anthropic	100.0	$10.00
3	Claude Opus 5.5· Anthropic	100.0	$4.00
4	Claude Sonnet 5.5· Anthropic	100.0	$2.00
5	GPT-5.6 Sol· OpenAI	100.0	$2.00
6	GPT-6 Astra· OpenAI	100.0	$10.00
7	GPT-5.6 Terra· OpenAI	99.7	$2.00
8	Qwen3.8 Max (0902)· Alibaba Qwen	99.4	$2.00
9	Grok 4.6· xAI	99.2	$2.00
10	Claude Opus 5· Anthropic	98.9	$5.00
11	Gemini 3.8 Flash· Google DeepMind	98.9	$0.75
12	DeepSeek V4 Pro 0813· DeepSeek	98.6	$0.55
13	Claude Opus 4.8· Anthropic	98.3	$5.00
14	GPT-5.6 Luna· OpenAI	98.3	$0.20
15	Claude Opus 4.7· Anthropic	97.8	$5.00
16	GPT-5.4· OpenAI	97.8	$2.50
17	Grok 4.5· xAI	97.8	$2.00
18	Gemini 3.7 Flash· Google DeepMind	97.2	$0.75
19	Kimi K3· moonshotai	97.2	$0.67
20	DeepSeek V4 Pro· DeepSeek	96.7	$0.21
21	GPT-5.2· OpenAI	96.1	$1.75
22	Kimi K2.6· moonshotai	96.1	$0.95
23	Gemini 3.1 Pro Preview· Google DeepMind	95.6	$2.00
24	Gemini 3 Flash Preview· Google DeepMind	95.5	$0.50
25	Gemini 3.5 Flash· Google DeepMind	95.5	$1.50
26	Kimi K2.7 Code· moonshotai	95.5	$0.61
27	Qwen3.7 Max· Alibaba Qwen	95.5	$1.25
28	Claude Sonnet 5· Anthropic	94.7	$2.00
29	Claude Opus 4.6· Anthropic	94.4	$5.00
30	DeepSeek V4 Flash 0731· DeepSeek	94.4	$0.02
31	Gemini 3.6 Flash· Google DeepMind	94.2	$0.75
32	GLM 5.3 Flash· z-ai	93.9	$0.15
33	GLM 5.1· z-ai	93.3	$0.97
34	Grok 4.3· xAI	93.3	$1.25
35	Qwen3.6 Plus· Alibaba Qwen	93.3	$0.33
36	Qwen3.7 Plus· Alibaba Qwen	93.3	$0.32
37	Grok 4.20· xAI	92.2	$1.25
38	Kimi K2.5· moonshotai	92.2	$0.45
39	Gemini 3 Pro· Google DeepMind	91.4	n/a
40	GPT-5· OpenAI	91.4	$1.25
41	GLM 5.3· z-ai	91.1	$1.40
42	Qwen3.6 27B· Alibaba Qwen	91.1	$0.32
43	Qwen3.6 Max Preview· Alibaba Qwen	91.1	$1.03
44	U Muse Spark· Unknown	88.9	n/a
45	GPT-5.4 Mini· OpenAI	88.9	$0.75
46	gpt-oss-120b· OpenAI	88.9	$0.04
47	Qwen3.5 397B A17B· Alibaba Qwen	88.9	$0.55
48	GPT-5.1· OpenAI	88.6	$1.25
49	DeepSeek V3.2· DeepSeek	87.8	$0.28
50	GPT-5.4 Nano· OpenAI	87.8	$0.20
51	GPT-5 Mini· OpenAI	86.7	$0.25
52	Nemotron 3 Ultra· NVIDIA	86.7	$0.50
53	Qwen 3.5 Plus (hosted 397B-A17B)· Alibaba Qwen	86.7	n/a
54	Qwen3 235B A22B Thinking 2507· Alibaba Qwen	86.7	$0.23
55	Qwen3.6 35B A3B· Alibaba Qwen	86.7	$0.15
56	Qwen3.7 Flash· Alibaba Qwen	86.7	$0.03
57	GLM 5.2· z-ai	86.4	$1.00
58	Claude Opus 4.5· Anthropic	86.1	$5.00
59	Claude Sonnet 4.6· Anthropic	85.8	$3.00
60	Gemini 2.5 Pro· Google DeepMind	84.7	$1.25
61	o3· OpenAI	84.4	$2.00
62	Qwen3.5-Flash· Alibaba Qwen	84.4	$0.07
63	Qwen3.6 Flash· Alibaba Qwen	84.4	$0.19
64	Grok 4· xAI	84.0	n/a
65	GLM 4.7· z-ai	83.3	$0.60
66	Kimi K2 Thinking· moonshotai	83.0	$0.60
67	Gemma 4 26B A4B · Google DeepMind	82.2	$0.07
68	o4 Mini· OpenAI	81.7	$1.10
69	GPT-5 Nano· OpenAI	81.1	$0.05
70	Gemini 3.1 Flash Lite· Google DeepMind	80.0	$0.25
71	GLM 5· z-ai	80.0	$0.60
72	Claude Sonnet 4.5· Anthropic	77.8	$3.00
73	Grok-3 mini· xAI	77.8	n/a
74	o3 Mini· OpenAI	76.9	$1.10
75	Gemma 4 31B· Google DeepMind	73.3	$0.09
76	o1· OpenAI	73.3	$15.00
77	Qwen3 Max· Alibaba Qwen	73.3	$0.78
78	Gemini 2.5 Flash· Google DeepMind	73.0	$0.30
79	Claude Sonnet 4· Anthropic	71.1	$3.00
80	Gemini 3.5 Flash Lite· Google DeepMind	71.1	$0.30
81	MiniMax M3· minimax	71.1	$0.30
82	Qwen3.5-35B-A3B· Alibaba Qwen	70.0	$0.15
83	Claude Opus 4.1· Anthropic	68.9	$15.00
84	Qwen3 32B· Alibaba Qwen	66.9	$0.08
85	Claude Haiku 4.5· Anthropic	66.6	$1.00
86	Qwen3 14B· Alibaba Qwen	66.4	$0.12
87	R1 0528· DeepSeek	66.4	$0.50
88	gpt-oss-20b· OpenAI	65.2	$0.02
89	Claude Opus 4· Anthropic	64.4	$15.00
90	Qwen3 30B A3B· Alibaba Qwen	62.7	$0.12
91	Qwen3.5-9B· Alibaba Qwen	61.6	$0.10
92	QwQ 32B· Alibaba Qwen	59.1	$0.15
93	Claude 3.7 Sonnet· Anthropic	57.7	n/a
94	Gemini 2.0 Flash Thinking (Jan 2025)· Google DeepMind	57.7	n/a
95	Qwen3 8B· Alibaba Qwen	56.1	$0.12
96	DeepSeek R1 Distill Qwen 32B· DeepSeek	55.5	n/a
97	Grok 3· xAI	55.5	n/a
98	R1· DeepSeek	53.3	$0.70
99	DeepSeek R1 Distill Qwen 14B· DeepSeek	50.5	n/a
100	o1-mini· OpenAI	46.9	n/a
101	GPT-4.1 Mini· OpenAI	44.7	$0.40
102	GPT-4.1· OpenAI	38.3	$2.00
103	GPT-4.5· OpenAI	37.7	n/a
104	Mistral Medium 3· Mistral AI	32.1	$0.40
105	Gemini 2.0 Flash· Google DeepMind	31.0	$0.10
106	Gemini 2.0 Flash (Dec 2024)· Google DeepMind	31.0	n/a
107	o1-preview· OpenAI	31.0	n/a
108	Mistral Small 3.2 24B· Mistral AI	30.2	$0.09
109	U Magistral Small 1.1· Unknown	29.9	n/a
110	GPT-4.1 Nano· OpenAI	28.8	$0.10
111	Gemma 3 27B· Google DeepMind	22.4	$0.08
112	Llama 4 Maverick· Meta	20.5	$0.19
113	Gemma 3 27B (free)· Google DeepMind	19.6	$0.00
114	Gemma 3 12B· Google DeepMind	16.6	$0.05
115	Qwen2.5-Max· Alibaba Qwen	16.0	n/a
116	DeepSeek V3· DeepSeek	15.8	$0.26
117	Phi 4· Microsoft	13.7	$0.07
118	Grok-2 (Dec 2024)· xAI	11.4	n/a
119	Llama 3.1 405B· Meta	9.6	n/a
120	Mistral Large 2407· Mistral AI	8.4	$2.00
121	Qwen2.5 72B Instruct· Alibaba Qwen	8.0	$0.36
122	Llama 4 Scout· Meta	7.7	$0.10
123	Mistral Large 2411· Mistral AI	7.7	$2.00
124	Gemma 3 4B· Google DeepMind	7.4	$0.05
125	Qwen2.5 32B Instruct· Alibaba	7.3	n/a
126	GPT-4o-mini· OpenAI	6.8	$0.15
127	GPT-4o-mini (2024-07-18)· OpenAI	6.8	$0.15
128	Gemini 1.5 Pro (Feb 2024)· Google DeepMind	6.7	n/a
129	Gemini 1.5 Pro (May 2024)· Google DeepMind	6.7	n/a
130	Mistral Small 3· Mistral AI	6.6	$0.05
131	Claude 3.5 Sonnet· Anthropic	6.4	n/a
132	GPT-4o (2024-08-06)· OpenAI	6.3	$2.50
133	GPT-4o (2024-11-20)· OpenAI	6.3	$2.50
134	GPT-4o (2024-05-13)· OpenAI	6.2	$5.00
135	Mistral Small 3.1 24B· Mistral AI	5.7	$0.35
136	Llama 3.3 70B Instruct· Meta	5.0	$0.10
137	Llama 3.3 70B Instruct (free)· Meta	5.0	$0.00
138	Claude 3 Opus· Anthropic	4.6	n/a
139	Claude 3.5 Haiku· Anthropic	4.2	n/a
140	Llama 3 70B Instruct· Meta	4.2	$0.51
141	Llama 3-70B· Meta	4.2	n/a
142	Gemini 1.5 Flash (May 2024)· Google DeepMind	3.8	n/a
143	Llama 3.1 70B Instruct· Meta	3.5	$0.40
144	Llama 3.2 90B· Meta	2.5	n/a
145	Claude 2· Anthropic	2.4	n/a
146	Claude 3 Sonnet· Anthropic	2.4	n/a
147	Qwen2.5 7B Instruct· Alibaba Qwen	2.4	$0.10
148	GPT-3.5 Turbo (older v0613)· OpenAI	2.1	$1.00
149	Claude 2.1· Anthropic	1.9	n/a
150	Mistral Large· Mistral AI	1.9	$2.00
151	Claude 3 Haiku· Anthropic	1.7	$0.25
152	Llama 3.1 8B Instruct· Meta	1.6	$0.02
153	Gemma 2 27B· Google DeepMind	1.3	$0.65
154	Gemini 1.0 Pro· Google DeepMind	1.0	n/a
155	GPT-4 Turbo· OpenAI	1.0	$10.00
156	Llama 3 8B Instruct· Meta	0.7	$0.14
157	Gemma 2 9B· Google DeepMind	0.5	$0.03
158	GPT-4 (older v0314)· OpenAI	0.5	$30.00
159	Llama 3.2 1B Instruct· Meta	0.5	$0.03