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 2025-02-28 · public

Source: Epoch AI Benchmarking Hub
Version: 2025-02-28-public
Measurement date: Not reported
Metric: % · Higher is better
Evaluation scope: Epoch AI run · task v1 · 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.

#1Kimi K2.6
moonshotai/kimi-k2.6-20260420
90%
View modelEvidence independent
#2Gemini 3.1 Pro Preview
google/gemini-3.1-pro-preview-20260219
88.9%
View modelEvidence independent
#3GLM 5.1
z-ai/glm-5.1-20260406
80%
View modelEvidence independent
#4Gemini 3 Flash Preview
google/gemini-3-flash-preview-20251217
60%
View modelEvidence independent
#5Qwen3.6 Max Preview
qwen/qwen3.6-max-preview-20260420
50%
View modelEvidence independent
#5Qwen3.6 Plus
qwen/qwen3.6-plus-04-02
50%
View modelEvidence independent
#7Gemini 2.5 Pro
google/gemini-2.5-pro
40%
View modelEvidence independent
#7Kimi K2 Thinking
moonshotai/kimi-k2-thinking-20251106
40%
View modelEvidence independent
#9Gemini 2.5 Pro Preview 06-05
google/gemini-2.5-pro-preview-06-05
30%
View modelEvidence independent
#10Claude Opus 4.5
anthropic/claude-opus-4-5
20%
View modelEvidence independent
#10Qwen3 235B A22B Thinking 2507
qwen/qwen3-235b-a22b-thinking-2507
20%
View modelEvidence independent
#10Qwen3.6 Flash
qwen/qwen3.6-flash
20%
View modelEvidence independent
#13GPT-4.1 Mini
openai/gpt-4.1-mini-2025-04-14
10%
View modelEvidence independent
#13Qwen3.5-Flash
qwen/qwen3.5-flash-20260224
10%
View modelEvidence independent
#15GLM 5
z-ai/glm-5-20260211
2.1%
View modelEvidence independent
#16Claude Opus 4
anthropic/claude-opus-4
0%
View modelEvidence independent
#16Claude Opus 4.1
anthropic/claude-opus-4-1
0%
View modelEvidence independent
#16Claude Sonnet 4
anthropic/claude-sonnet-4
0%
View modelEvidence independent
#16Claude Sonnet 4.5
anthropic/claude-sonnet-4-5
0%
View modelEvidence independent
#16DeepSeek V3
deepseek/deepseek-chat-v3
0%
View modelEvidence independent
#16DeepSeek V3 0324
deepseek/deepseek-chat-v3-0324
0%
View modelEvidence independent
#16GLM 4.5
z-ai/glm-4.5
0%
View modelEvidence independent
#16GLM 4.6
z-ai/glm-4.6
0%
View modelEvidence independent
#16GPT-4.1
openai/gpt-4.1-2025-04-14
0%
View modelEvidence independent
#16GPT-4.1 Nano
openai/gpt-4.1-nano-2025-04-14
0%
View modelEvidence independent
#16GPT-4o (2024-08-06)
openai/gpt-4o-2024-08-06
0%
View modelEvidence independent
#16GPT-4o (2024-11-20)
openai/gpt-4o-2024-11-20
0%
View modelEvidence independent
#16Llama 4 Scout
meta/llama-4-scout-17b-16e-instruct
0%
View modelEvidence independent
#16Qwen-Plus
qwen/qwen-plus-2025-01-25
0%
View modelEvidence independent
#16Qwen3 235B A22B
qwen/qwen3-235b-a22b-04-28
0%
View modelEvidence independent