Model results

FrontierMath

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Reviewed recommendation and limits

Use the relevant tier and private/public split for difficult mathematical reasoning.

Each tier, release and public/private split separately. Imported groups below may use different protocols; this review does not certify each run. Difficulty is specialized; tier, dataset release, tools and grader must match before comparing scores.

Publisher results Epoch benchmarking methods

← All evaluation groups

FrontierMath Tiers 1–3 v2 · private

Source: Epoch AI Benchmarking Hub
Version: tiers-1-3-v2-private
Measurement date: Not reported
Metric: % · Higher is better
Evaluation scope: Epoch AI run · task v2 · result date not supplied

Exact score ties share a position. Positions do not establish statistical significance. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

#1Qwen3.7 Max
qwen/qwen3.7-max-20260520
64.6%
View modelEvidence independent
#2Gemini 3.1 Pro Preview
google/gemini-3.1-pro-preview-20260219
59.6%
View modelEvidence independent
#3Kimi K2.6
moonshotai/kimi-k2.6-20260420
57.2%
View modelEvidence independent
#4Kimi K2.7 Code
moonshotai/kimi-k2.7-code-20260612
54%
View modelEvidence independent
#5Gemini 3 Flash Preview
google/gemini-3-flash-preview-20251217
51.2%
View modelEvidence independent
#6Qwen3.6 Plus
qwen/qwen3.6-plus-04-02
38.2%
View modelEvidence independent
#7GLM 5.1
z-ai/glm-5.1-20260406
36.8%
View modelEvidence independent
#8Qwen3.6 27B
qwen/qwen3.6-27b-20260422
35.1%
View modelEvidence independent
#9Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17b-20260216
29.5%
View modelEvidence independent
#10Gemini 2.5 Pro
google/gemini-2.5-pro
24.6%
View modelEvidence independent
#11Qwen3.7 Flash
qwen/qwen3.7-flash-20260727
19.3%
View modelEvidence independent
#12Qwen3 Max
qwen/qwen3-max
18.9%
View modelEvidence independent
#13Qwen3.6 35B A3B
qwen/qwen3.6-35b-a3b-20260415
17.5%
View modelEvidence independent
#14Qwen3.6 Flash
qwen/qwen3.6-flash
17.2%
View modelEvidence independent
#15Qwen3.5-Flash
qwen/qwen3.5-flash-20260224
9.5%
View modelEvidence independent
#16GPT-4.1 Mini
openai/gpt-4.1-mini-2025-04-14
6.7%
View modelEvidence independent
#17GPT-4.1
openai/gpt-4.1-2025-04-14
6%
View modelEvidence independent
#18GPT-4o-mini (2024-07-18)
openai/gpt-4o-mini-2024-07-18
0.7%
View modelEvidence independent
#19GPT-4o (2024-08-06)
openai/gpt-4o-2024-08-06
0.4%
View modelEvidence independent