Benchmark

FrontierMath Tiers 1-3

Measures: 295 unpublished, expert-written math problems (advanced undergraduate to graduate level) with automatically verifiable answers; a model may use Python under a 1M-token limit and gets 1 point per correct answer on the private set.

Maintainer
Epoch AI (OpenAI-funded; Epoch discloses the conflict of interest)
Introduced
2024
Status
Active
Saturation
Saturated
Typical provenance
Independent
In scoring set
No

PaperOfficial leaderboard

Leaderboard

Independent and third-party results only.

Leaderboard
ModelAccuracyProvenanceSourceEvaluated
GPT-3.5 Turbo0.0%IndependentEpoch AI27 Aug 2026
GPT-4o0.4%IndependentEpoch AI27 Aug 2026
GPT-4 Turbo0.7%IndependentEpoch AI27 Aug 2026
GPT-4o mini0.7%IndependentEpoch AI27 Aug 2026
GPT-5 nano
OpenAI · Minimal effort
1.8%IndependentEpoch AI27 Aug 2026
o3-mini
OpenAI · Low effort
3.9%IndependentEpoch AI27 Aug 2026
GPT-5.4 nano
OpenAI · None effort
4.6%IndependentEpoch AI28 Aug 2026
GPT-4.16.0%IndependentEpoch AI27 Aug 2026
GPT-5 mini
OpenAI · Minimal effort
6.0%IndependentEpoch AI27 Aug 2026
GPT-5 nano
OpenAI · Low effort
6.0%IndependentEpoch AI27 Aug 2026
GPT-4.1 mini6.7%IndependentEpoch AI27 Aug 2026
o1
OpenAI · Low effort
8.4%IndependentEpoch AI27 Aug 2026
Qwen3.5-Flash9.5%IndependentEpoch AI28 Aug 2026
o1
OpenAI · Medium effort
10.2%IndependentEpoch AI27 Aug 2026
o3-mini
OpenAI · Medium effort
10.5%IndependentEpoch AI27 Aug 2026
Claude Opus 4.1
Anthropic · 32K effort
12.6%IndependentEpoch AI11 Jun 2026
o1
OpenAI · High effort
14.7%IndependentEpoch AI28 Aug 2026
o4-mini
OpenAI · Low effort
16.1%IndependentEpoch AI27 Aug 2026
GPT-5.4 mini
OpenAI · None effort
17.2%IndependentEpoch AI28 Aug 2026
Qwen3.6-Flash17.2%IndependentEpoch AI29 Aug 2026
Qwen3.6-35B-A3B17.5%IndependentEpoch AI29 Aug 2026
GPT-5
OpenAI · Minimal effort
18.2%IndependentEpoch AI27 Aug 2026
GPT-5 mini
OpenAI · Low effort
18.2%IndependentEpoch AI27 Aug 2026
Qwen3.5-Flash
Alibaba Group · None effort
18.2%IndependentEpoch AI28 Aug 2026
o3-mini
OpenAI · High effort
18.6%IndependentEpoch AI11 Jun 2026
Qwen3-Max18.9%IndependentEpoch AI30 Aug 2026
o3
OpenAI · Low effort
19.3%IndependentEpoch AI27 Aug 2026
Qwen3.7-Flash
Alibaba Group · None effort
19.3%IndependentEpoch AI29 Aug 2026
Qwen3.7-Flash19.3%IndependentEpoch AI29 Aug 2026
GPT-5 nano
OpenAI · High effort
20.0%IndependentEpoch AI12 Jun 2026
GPT-5.4 nano
OpenAI · Low effort
20.4%IndependentEpoch AI28 Aug 2026
Qwen3.6-35B-A3B
Alibaba Group · None effort
20.4%IndependentEpoch AI30 Aug 2026
Gemini 3.1 Flash-Lite
Google DeepMind · Minimal effort
21.4%IndependentEpoch AI28 Aug 2026
Gemini 3.1 Flash-Lite
Google DeepMind · Low effort
22.5%IndependentEpoch AI30 Aug 2026
Qwen3.6-Flash
Alibaba Group · None effort
22.5%IndependentEpoch AI29 Aug 2026
Claude Sonnet 4.5
Anthropic · 32K effort
23.9%IndependentEpoch AI11 Jun 2026
Gemini 2.5 Pro24.6%IndependentEpoch AI11 Jun 2026
GPT-5.4 mini
OpenAI · Low effort
24.6%IndependentEpoch AI28 Aug 2026
GLM-5.1
Z.ai (Zhipu AI) · None effort
24.9%IndependentEpoch AI28 Aug 2026
Gemini 3.5 Flash-Lite
Google DeepMind · High effort
26.0%IndependentEpoch AI2 Aug 2026
Gemini 3.1 Flash-Lite
Google DeepMind · High effort
27.7%IndependentEpoch AI30 Aug 2026
o4-mini
OpenAI · Medium effort
28.8%IndependentEpoch AI27 Aug 2026
Qwen3.5-397B-A17B29.5%IndependentEpoch AI28 Aug 2026
o3
OpenAI · Medium effort
29.8%IndependentEpoch AI27 Aug 2026
Qwen3.5-397B-A17B
Alibaba Group · None effort
31.2%IndependentEpoch AI30 Aug 2026
Qwen3.6-Plus
Alibaba Group · None effort
32.3%IndependentEpoch AI29 Aug 2026
Inkling
Thinking Machines Lab · Xhigh effort
33.3%IndependentEpoch AI6 Aug 2026
o3
OpenAI · High effort
33.3%IndependentEpoch AI27 Aug 2026
Qwen3.6-27B
Alibaba Group · None effort
34.0%IndependentEpoch AI29 Aug 2026
Claude Opus 4.5
Anthropic · 32K effort
34.4%IndependentEpoch AI11 Jun 2026
Qwen3.7-Plus
Alibaba Group · None effort
34.4%IndependentEpoch AI29 Aug 2026
Qwen3.6-27B35.1%IndependentEpoch AI28 Aug 2026
o4-mini
OpenAI · High effort
36.1%IndependentEpoch AI11 Jun 2026
GLM-5.136.8%IndependentEpoch AI29 Aug 2026
GPT-5
OpenAI · Low effort
37.2%IndependentEpoch AI27 Aug 2026
Qwen3.6-Plus38.2%IndependentEpoch AI30 Aug 2026
GPT-5.6 Luna
OpenAI · None effort
39.6%IndependentEpoch AI29 Aug 2026
GPT-5.6 Luna
OpenAI · Low effort
41.4%IndependentEpoch AI29 Aug 2026
GLM-5.2
Z.ai (Zhipu AI) · None effort
42.5%IndependentEpoch AI29 Aug 2026
Grok 4.3
SpaceXAI (xAI) · High effort
42.8%IndependentEpoch AI17 Jun 2026
GPT-5.4 nano
OpenAI · High effort
44.9%IndependentEpoch AI12 Jun 2026
Grok 4.2044.9%IndependentEpoch AI13 Jul 2026
DeepSeek-V4-Pro
DeepSeek · Max effort
45.3%IndependentEpoch AI17 Jun 2026
Inkling Small
Thinking Machines Lab · Xhigh effort
46.3%IndependentEpoch AI14 Aug 2026
GPT-5 mini
OpenAI · High effort
46.7%IndependentEpoch AI12 Jun 2026
Gemini 3 Flash51.2%IndependentEpoch AI11 Jun 2026
GPT-5.4 mini
OpenAI · Xhigh effort
51.2%IndependentEpoch AI12 Jun 2026
Kimi K2.7 Code54.0%IndependentEpoch AI13 Jun 2026
GLM-5.2
Z.ai (Zhipu AI) · Low effort
54.7%IndependentEpoch AI29 Aug 2026
GPT-5
OpenAI · High effort
55.4%IndependentEpoch AI10 Jun 2026
GLM-5.3-Flash
Z.ai (Zhipu AI) · Max effort
55.8%IndependentEpoch AI27 Aug 2026
GPT-5 Pro
OpenAI · High effort
55.8%IndependentEpoch AI12 Jun 2026
Grok 4.5
SpaceXAI (xAI) · High effort
57.2%IndependentEpoch AI9 Jul 2026
Kimi K2.657.2%IndependentEpoch AI10 Jun 2026
DeepSeek-V4-Flash
DeepSeek · Max effort
57.5%IndependentEpoch AI2 Aug 2026
Gemini 3.6 Flash
Google DeepMind · High effort
58.9%IndependentEpoch AI2 Aug 2026
GLM-5.2
Z.ai (Zhipu AI) · Max effort
59.2%IndependentEpoch AI19 Jun 2026
Gemini 3.1 Pro59.6%IndependentEpoch AI11 Jun 2026
Gemini 3.5 Flash
Google DeepMind · High effort
62.8%IndependentEpoch AI10 Jun 2026
DeepSeek-V4-Pro
DeepSeek · Max effort
64.6%IndependentEpoch AI19 Aug 2026
Qwen3.7-Max64.6%IndependentEpoch AI13 Jun 2026
Claude Sonnet 5
Anthropic · Max effort
65.6%IndependentEpoch AI30 Jun 2026
Qwen3.8-Max
Alibaba Group · Xhigh effort
65.6%IndependentEpoch AI2 Sep 2026
Claude Opus 4.6
Anthropic · Max effort
66.0%IndependentEpoch AI11 Jun 2026
Grok 4.6
SpaceXAI (xAI) · Xhigh effort
66.0%IndependentEpoch AI14 Aug 2026
GPT-5.2
OpenAI · Xhigh effort
67.4%IndependentEpoch AI11 Jun 2026
Gemini 3.8 Flash
Google DeepMind · High effort
68.4%IndependentEpoch AI2 Sep 2026
GLM-5.3
Z.ai (Zhipu AI) · Max effort
68.8%IndependentEpoch AI25 Aug 2026
Claude Opus 4.7
Anthropic · Max effort
70.2%IndependentEpoch AI10 Jun 2026
Gemini 3.7 Flash
Google DeepMind · High effort
71.6%IndependentEpoch AI14 Aug 2026
Kimi K3
Moonshot AI · Max effort
72.2%IndependentEpoch AI17 Jul 2026
GPT-5.2 Pro
OpenAI · Xhigh effort
74.0%IndependentEpoch AI13 Jun 2026
Muse Spark 1.3
Meta · Max effort
74.0%IndependentEpoch AI18 Sep 2026
Muse Spark 1.3
Meta · Xhigh effort
74.4%IndependentEpoch AI16 Sep 2026
Qwen3.8-Max
Alibaba Group · Xhigh effort
74.7%IndependentEpoch AI4 Aug 2026
GPT-5.4
OpenAI · Xhigh effort
78.6%IndependentEpoch AI11 Jun 2026
Claude Opus 4.8
Anthropic · Max effort
80.0%IndependentEpoch AI10 Jun 2026
GPT-5.6 Luna
OpenAI · Max effort
82.1%IndependentEpoch AI9 Jul 2026
GPT-5.4 Pro
OpenAI · Xhigh effort
82.5%IndependentEpoch AI13 Jun 2026
GPT-5.5
OpenAI · Xhigh effort
85.3%IndependentEpoch AI11 Jun 2026
Claude Opus 5
Anthropic · Max effort
85.6%IndependentEpoch AI24 Jul 2026
GPT-5.6 Terra
OpenAI · Max effort
86.0%IndependentEpoch AI9 Jul 2026
Claude Fable 5
Anthropic · Max effort
87.0%IndependentEpoch AI9 Jun 2026
GPT-5.5 Pro
OpenAI · Xhigh effort
87.7%IndependentEpoch AI12 Jun 2026
GPT-5.6 Sol
OpenAI · Max effort
89.1%IndependentEpoch AI9 Jul 2026
Claude Fable 5.1
Anthropic · Max effort
90.2%IndependentEpoch AI1 Sep 2026
Claude Opus 5.5
Anthropic · Max effort
91.2%IndependentEpoch AI22 Sep 2026
GPT-6 Astra
OpenAI · Max effort
93.7%IndependentEpoch AI30 Aug 2026
  • Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks, CC BY 4.0.

Sources

FrontierMath Tiers 1-3: leaderboard and what it measures · supermarket.dev