MathematicsActive
Trust Score:
95

FrontierMath

Original, unpublished research-level math problems by expert mathematicians — mostly private to resist contamination. Frontier models solved under 2% at launch.

Launched: Refresh: static
Status Assessment (active):

The strongest active case on the wiki. At launch (Nov 2024) state-of-the-art models solved UNDER 2% — a benchmark frontier systems almost entirely fail. Reasoning models with Python tools have since climbed (OpenAI announced o3 at 25.2% in Dec 2024, tools-on), but that figure is contested — Epoch's own independent reproductions of comparable models came in far lower (~11%). By the June 2026 v2 release Epoch added a harder Tier 4 precisely because Tiers 1–3 progress had become significant, yet the hardest tier remains far from solved. Current figures move fast and are tool/compute-dependent — consult Epoch's live dashboard; this page does not restate unverified third-party numbers. Saturation here would mean research-level, closed-form mathematics is largely automated.

Performance Timeline

Longitudinal progression of model scores against human baselines.

Performance & Historical Trajectory

Empirical score progression across model release dates and evaluation rounds.

Independent Vendor-Reported Human Baseline (2.0%)
ModelScoreDateSource TypeProvenance
o3-mini high (Epoch independent eval, Tiers 1–3, tools-on)11%2025-02-28independentSource ↗
best frontier model (Tiers 1–3, tools-on)2%2024-11-07independentSource ↗

Human Baseline & Difficulty Horizon

Calibrated human reference points, specialist benchmarks, and ceiling thresholds.
Measured Human Score2.0%Domain Expert Baseline
Baseline Protocol & Interpretation

Elite mathematics competition winners and PhD researchers score <2% without computing tools, ~25% with Python.

Metric & Scoring Methodology

Verification protocols, aggregation formulas, and specialized metric variants.
Primary Metric:accuracy — % of problems solved, automated answer verification (%)
Scoring Engine:exact-match

Dataset & Compute Cost

Evaluation volume, public availability, API pricing, and local hardware requirements.
Total Dataset Size338Annotated evaluation items
Public Test SetPublicOpenly mirrored on repositories
Access GatingOpen AccessUnrestricted download
Evaluation LicenseOpen AccessDataset usage and redistribution terms
Frontier API Compute Cost:

$5 – $20 USD for full benchmark evaluation run on frontier APIs.

Recommended Local GPU Setup:

1x NVIDIA RTX 4090 (24GB) or A100 (40GB/80GB) via vLLM / SGLang

Official Dataset & Benchmark Files:Download / View Dataset Repository ↗

How to Run & Reproduce

Standardized evaluation protocols, CLI commands, and reproducible runner templates.
Prompt Regimezero-shot
Reasoning Modedirect
Sampling Temp0
Pass@k Budgetk = 1
Tools & SandboxPure Text
Scoring Verifierexact-match
Option AEleutherAI LM-Evaluation-Harness (Open-Weight Models)
lm_eval --model hf --model_args pretrained=<model_path> --tasks frontiermath --batch_size auto
Option BOpenCompass Evaluation Framework
opencompass --datasets frontiermath --models <model_config>
Python APIDeterministic Inference Loop Snippet
# Standard API Evaluation Loop
from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": prompt}],
    temperature=0.0,
)
Standardized Reporting Requirement:

When publishing results for FrontierMath, always report the exact prompt template, few-shot exemplar ordering, sampling temperature (temperature=0), maximum reasoning budget tokens, and the precise timestamped model snapshot ID.

Contamination & Memorization Analysis

Audit of pretraining exposure risks, memorization vectors, and refresh policies.
Overall Contamination Risk:LOW
Refresh Cadence:

Static fixed snapshot

Test Set Exposure:

Public on web / HuggingFace