What does FrontierMath-Tiers-1-3-v2-Private measure?

FrontierMath-Tiers-1-3-v2-Private is a knowledge benchmark in the BenchGecko catalog. 87 AI models have been tested on it. Scores range from 0.4 to 100.0 out of 100.

Which model leads on FrontierMath-Tiers-1-3-v2-Private?

Claude Fable 5.2 from Anthropic leads FrontierMath-Tiers-1-3-v2-Private with a score of 100.0. The median score across 87 tested models is 60.6.

Is FrontierMath-Tiers-1-3-v2-Private saturated?

Yes · the top model on FrontierMath-Tiers-1-3-v2-Private 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 FrontierMath-Tiers-1-3-v2-Private predict performance on other benchmarks?

Yes · FrontierMath-Tiers-1-3-v2-Private scores correlate 0.98 with FrontierMath-2025-02-28-Private across 32 shared models. Models that do well on FrontierMath-Tiers-1-3-v2-Private tend to do well on FrontierMath-2025-02-28-Private.

How often is FrontierMath-Tiers-1-3-v2-Private data refreshed?

BenchGecko pulls updates daily. New model scores on FrontierMath-Tiers-1-3-v2-Private appear as soon as they are published by Epoch AI or the model provider.

Benchmark · KnowledgeSettled

FrontierMath-Tiers-1-3-v2-Private

Name: FrontierMath-Tiers-1-3-v2-Private Benchmark
Creator: BenchGecko
License: https://creativecommons.org/licenses/by/4.0/

Updated 2026-11-09

Models tested

Top score

100.0

Claude Fable 5.2

Median

60.6

min 0.4

Top-5 spread

σ 1.7

Settled

The Frontier

Best score over time · one chart, every benchmark

Chart type

Frontier on FrontierMath-Tiers-1-3-v2-Private rose from 15.5 to 100.0 in 23 months · +84.5 points · latest leader Claude Fable 5.2 from Anthropic.

Pink dots = frontier records · 16 totalClick to open model page

Full rankings

87 models tested · sorted by score

#	Model	Score	Price
1	Claude Fable 5.2· Anthropic	100.0	$8.00
2	GPT-6 Astra· OpenAI	98.6	$10.00
3	GPT-6.1 Sol· OpenAI	98.6	$2.00
4	Claude Opus 5.5· Anthropic	96.0	$4.00
5	GPT-6.1 Terra· OpenAI	95.7	$1.00
6	Claude Fable 5.1· Anthropic	94.9	$10.00
7	GPT-6 Sol· OpenAI	94.5	$2.00
8	GPT-5.6 Sol· OpenAI	93.8	$4.00
9	Claude Sonnet 5.5· Anthropic	93.4	$2.00
10	GPT-5.5 Pro· OpenAI	92.3	$30.00
11	Claude Fable 5· Anthropic	91.6	$10.00
12	GPT-5.6 Terra· OpenAI	90.5	$2.00
13	Gemini 4 Argon· Google DeepMind	90.5	$2.00
14	Claude Opus 5· Anthropic	90.1	$5.00
15	GPT-5.5· OpenAI	89.8	$5.00
16	GPT-5.4 Pro· OpenAI	86.8	$30.00
17	GPT-5.6 Luna· OpenAI	86.4	$0.20
18	Claude Opus 4.8· Anthropic	84.2	$5.00
19	GPT-6 Luna· OpenAI	83.1	$0.10
20	GPT-5.4· OpenAI	82.7	$2.50
21	Kimi K3.1 Pro· moonshotai	82.4	$2.00
22	Claude Haiku 5.5· Anthropic	79.0	$0.10
23	Qwen3.8 Max (0902)· Alibaba Qwen	78.7	$2.00
24	GPT-5.2 Pro· OpenAI	77.9	$21.00
25	Kimi K3· moonshotai	76.0	$0.19
26	Gemini 3.7 Flash· Google DeepMind	75.3	$0.75
27	DeepSeek V4.1 Flash 1017· DeepSeek	75.0	$0.01
28	Claude Opus 4.7· Anthropic	73.9	$5.00
29	Muse Spark Open· Meta	73.5	$1.25
30	GLM 5.3· z-ai	72.4	$0.07
31	Gemini 3.8 Flash· Google DeepMind	72.0	$0.82
32	GPT-5.2· OpenAI	71.0	$1.75
33	DeepSeek V4.1 Flash· DeepSeek	70.9	$0.05
34	Grok 4.6· xAI	69.4	$2.00
35	Claude Opus 4.6· Anthropic	69.4	$5.00
36	Claude Sonnet 5· Anthropic	69.1	$2.00
37	Qwen3.7 Max· Alibaba Qwen	68.0	$1.48
38	DeepSeek V4 Pro 0813· DeepSeek	68.0	$0.11
39	Gemini 3.5 Flash· Google DeepMind	66.1	$1.50
40	Gemini 3.1 Pro Preview· Google DeepMind	62.8	$2.00
41	GLM 5.2· z-ai	62.3	$0.01
42	Gemini 3.6 Flash· Google DeepMind	62.0	$0.75
43	Mistral Large 4· Mistral AI	61.7	$0.70
44	DeepSeek V4 Flash 0731· DeepSeek	60.6	$0.04
45	Kimi K2.6· moonshotai	60.2	$0.65
46	Grok 4.5· xAI	60.2	$2.00
47	GPT-5 Pro· OpenAI	58.7	$15.00
48	GLM 5.3 Flash· z-ai	58.7	$0.04
49	GPT-5· OpenAI	58.4	$1.25
50	Kimi K2.7 Code· moonshotai	56.9	$0.60
51	Grok 4.7· xAI	55.8	$2.00
52	GPT-5.4 Mini· OpenAI	53.9	$0.75
53	Gemini 3 Flash Preview· Google DeepMind	53.9	$0.50
54	GPT-5 Mini· OpenAI	49.1	$0.25
55	DeepSeek V4 Pro· DeepSeek	47.6	$0.88
56	Grok 4.20· xAI	47.3	$1.25
57	GPT-5.4 Nano· OpenAI	47.3	$0.20
58	Grok 4.3· xAI	45.1	$1.25
59	Qwen3.6 Plus· Alibaba Qwen	40.3	$0.33
60	GLM 5.1· z-ai	38.8	$1.33
61	o4 Mini· OpenAI	38.0	$1.10
62	o4 Mini (batch)· OpenAI	38.0	$0.55
63	Qwen3.6 27B· Alibaba Qwen	36.9	$0.32
64	Qwen3.7 Plus· Alibaba Qwen	36.2	$0.32
65	Claude Opus 4.5· Anthropic	36.2	$5.00
66	o3· OpenAI	35.1	$2.00
67	Qwen3.5 397B A17B· Alibaba Qwen	32.9	$0.60
68	Gemini 3.1 Flash Lite· Google DeepMind	29.2	$0.25
69	Gemini 3.5 Flash Lite· Google DeepMind	27.3	$0.30
70	Gemini 2.5 Pro· Google DeepMind	25.9	$1.25
71	Claude Sonnet 4.5· Anthropic	25.1	$3.00
72	Qwen3.6 Flash· Alibaba Qwen	23.6	$0.19
73	Qwen3.6 35B A3B· Alibaba Qwen	21.4	$0.10
74	GPT-5 Nano· OpenAI	21.1	$0.05
75	Qwen3.7 Flash· Alibaba Qwen	20.3	$0.03
76	Qwen3 Max· Alibaba Qwen	19.9	$0.78
77	o3 Mini (batch)· OpenAI	19.6	$0.55
78	o3 Mini· OpenAI	19.6	$1.10
79	Qwen3.5-Flash· Alibaba Qwen	19.2	$0.07
80	o1· OpenAI	15.5	$15.00
81	Claude Opus 4.1· Anthropic	13.3	$15.00
82	GPT-4.1 Mini· OpenAI	7.0	$0.40
83	GPT-4.1· OpenAI	6.3	$2.00
84	GPT-4 Turbo (batch)· OpenAI	0.7	$5.00
85	GPT-4o-mini· OpenAI	0.7	$0.15
86	GPT-4 Turbo· OpenAI	0.7	$10.00
87	GPT-4o (2024-11-20)· OpenAI	0.4	$2.50