Vibeleaderboard
← Benchmark guide

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

Evaluation groups

Open a group to see its exact protocol and scores. Different configurations remain separate.

Model rankings

Open a group to compare scores within its reported protocol. Positions do not establish statistical significance.

Other reported results

These reports have no model ranking. Open a group for its evidence and the reason positions are withheld.

  • GPT-5.6 Soltier-4-v2-private

    FrontierMath Tier 4 v2 · private · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v2 · effort promax · result date not supplied

  • GPT-6 Astratier-4-v2-private

    FrontierMath Tier 4 v2 · private · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v2 · effort low · result date not supplied

  • GPT-6 Astratier-4-v2-private

    FrontierMath Tier 4 v2 · private · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v2 · effort medium · result date not supplied

  • GPT-6 Astratier-4-v2-private

    FrontierMath Tier 4 v2 · private · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v2 · no reasoning · result date not supplied

  • Claude Opus 4tier-4-2025-07-01-public

    FrontierMath Tier 4 2025-07-01 · public · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v1 · effort 27K · result date not supplied

  • Claude Opus 4.6tier-4-2025-07-01-public

    FrontierMath Tier 4 2025-07-01 · public · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v1 · effort 32K · result date not supplied

  • Claude Opus 4.6tier-4-2025-07-01-public

    FrontierMath Tier 4 2025-07-01 · public · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v1 · effort 64K · result date not supplied

  • Claude Sonnet 4tier-4-2025-07-01-public

    FrontierMath Tier 4 2025-07-01 · public · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v1 · effort 59K · result date not supplied

  • Claude Sonnet 4.6tier-4-2025-07-01-public

    FrontierMath Tier 4 2025-07-01 · public · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v1 · effort 16K · result date not supplied

  • GPT-5.2tier-4-2025-07-01-public

    FrontierMath Tier 4 2025-07-01 · public · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v1 · effort low · result date not supplied

  • Claude Opus 4.6tier-4-2025-07-01-private

    FrontierMath Tier 4 2025-07-01 · private · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v1 · effort 64K · superseded by FrontierMath Tier 4 v2 · private · result date n…

    Epoch AI run · task v1 · effort 64K · superseded by FrontierMath Tier 4 v2 · private · result date not supplied

  • GPT-5.2tier-4-2025-07-01-private

    FrontierMath Tier 4 2025-07-01 · private · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v1 · effort low · superseded by FrontierMath Tier 4 v2 · private · result date n…

    Epoch AI run · task v1 · effort low · superseded by FrontierMath Tier 4 v2 · private · result date not supplied

  • GPT-5.5erdos

    FrontierMath Erdős · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · effort xhigh · result date not supplied

  • Claude Opus 4.12025-02-28-public

    FrontierMath 2025-02-28 · public · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v1 · effort 27K · result date not supplied

  • Claude Opus 4.62025-02-28-public

    FrontierMath 2025-02-28 · public · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v1 · effort 64K · result date not supplied

  • Claude Opus 4.72025-02-28-public

    FrontierMath 2025-02-28 · public · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v1 · effort xhigh · result date not supplied

  • Claude Opus 4.62025-02-28-private

    FrontierMath 2025-02-28 · private · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v1 · effort 64K · superseded by FrontierMath Tiers 1–3 v2 · private · result dat…

    Epoch AI run · task v1 · effort 64K · superseded by FrontierMath Tiers 1–3 v2 · private · result date not supplied

  • Claude Sonnet 4.52025-02-28-private

    FrontierMath 2025-02-28 · private · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v1 · effort 59K · superseded by FrontierMath Tiers 1–3 v2 · private · result dat…

    Epoch AI run · task v1 · effort 59K · superseded by FrontierMath Tiers 1–3 v2 · private · result date not supplied

  • GPT-5.12025-02-28-private

    FrontierMath 2025-02-28 · private · Epoch AI Benchmarking Hub

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Epoch AI run · task v1 · no reasoning · superseded by FrontierMath Tiers 1–3 v2 · private · result d…

    Epoch AI run · task v1 · no reasoning · superseded by FrontierMath Tiers 1–3 v2 · private · result date not supplied

FrontierMath model results | VibeLeaderboard