# FrontierMath Tier 4 v2 (private) > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tier_4_v2. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tier_4_v2. The corrected v2 private Tier 4 subset of FrontierMath, containing exceptionally difficult research-level mathematics problems. Models may reason with Python and submit automatically checked answer functions; this scope remains separate from Tiers 1–3 and the original Tier 4 set.[Description · epoch.ai](https://epoch.ai/benchmarks/frontiermath-tier-4-v2) Canonical URL: https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tier_4_v2 Last updated: Wed, 21 Oct 2026 18:05:10 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Conquered The corrected v2 private Tier 4 subset of FrontierMath, containing exceptionally difficult research-level mathematics problems. Models may reason with Python and submit automatically checked answer functions; this scope remains separate from Tiers 1–3 and the original Tier 4 set.[Description · epoch.ai](https://epoch.ai/benchmarks/frontiermath-tier-4-v2) Mathematics · Models tested: 38 · Score publishers: [epoch ai](https://epoch.ai/benchmarks/use-this-data) ## Model results | # | Model | Score | ± | | | --- | --- | --- | --- | --- | | 1 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 100% | SE ±0 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 1.0 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 1.0 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion gpt-6.1-sol_max ### Reported statistics Uncertainty Standard error: ±0 pp standardError 0 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-6.1-sol Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-09-29T22:00:34.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/6` | | | | | | 2 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-xhigh.md)Extra high | 97.6% | SE ±2.4 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.976 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.976 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion gpt-6-astra_xhigh ### Reported statistics Uncertainty Standard error: ±2.4 pp standardError 0.024 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-6-astra Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-30T02:22:12.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/21` | | | | | | 2 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 97.6% | SE ±2.4 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.976 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.976 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion gpt-6-astra_max ### Reported statistics Uncertainty Standard error: ±2.4 pp standardError 0.024 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-6-astra Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-30T02:22:12.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/22` | | | | | | 2 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-high.md)High | 97.6% | SE ±2.4 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.976 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.976 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort high sourceModelVersion gpt-6-astra_high ### Reported statistics Uncertainty Standard error: ±2.4 pp standardError 0.024 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-6-astra Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-30T02:22:12.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/20` | | | | | | 5 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-medium.md)Medium | 97.56% | SE ±2.44 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.975609756097561 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.975609756097561 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort medium sourceModelVersion gpt-6-astra_medium ### Reported statistics Uncertainty Standard error: ±2.44 pp standardError 0.024390243902439022 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-6-astra Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-30T02:22:12.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/19` | | | | | | 6 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max | 95% | SE ±4.12 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.95 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.95 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-opus-5-5_max ### Reported statistics Uncertainty Standard error: ±4.12 pp standardError 0.041175470771058854 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label claude-opus-5-5 Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-09-22T18:27:39.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/11` | | | | | | 7 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max | 90.2% | SE ±4.6 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.902 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.902 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-fable-5_max ### Reported statistics Uncertainty Standard error: ±4.6 pp standardError 0.046 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label claude-fable-5 Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-06-09T18:12:35.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/75` | | | | | | 8 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 90% | SE ±5.17 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.9 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.9 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion gpt-6-sol_max ### Reported statistics Uncertainty Standard error: ±5.17 pp standardError 0.051739520574625435 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-6-sol Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-09-22T19:59:24.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/10` | | | | | | 9 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 87.8% | SE ±5.17 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.8780487804878049 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.8780487804878049 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-fable-5-1_max ### Reported statistics Uncertainty Standard error: ±5.17 pp standardError 0.051739520574625435 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label claude-fable-5-1 Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-09-01T18:38:24.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/16` | | | | | | 9 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-low.md)Low | 87.8% | SE ±5.17 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.8780487804878049 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.8780487804878049 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort low sourceModelVersion gpt-6-astra_low ### Reported statistics Uncertainty Standard error: ±5.17 pp standardError 0.051739520574625435 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-6-astra Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-30T02:22:12.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/18` | | | | | | 11 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-off.md)Non-thinking | 82.93% | SE ±5.95 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.8292682926829268 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.8292682926829268 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort none sourceModelVersion gpt-6-astra_none ### Reported statistics Uncertainty Standard error: ±5.95 pp standardError 0.05949419959829497 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-6-astra Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-30T02:22:12.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/17` | | | | | | 11 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-max.md)Max | 82.93% | SE ±5.95 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.8292682926829268 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.8292682926829268 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion gpt-5.6-sol_max ### Reported statistics Uncertainty Standard error: ±5.95 pp standardError 0.05949419959829497 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-5.6-sol Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-07-09T02:45:09.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/41` | | | | | | 13 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-promax.md)Promax | 80.49% | SE ±6.27 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.8048780487804879 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.8048780487804879 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort promax sourceModelVersion gpt-5.6-sol_promax ### Reported statistics Uncertainty Standard error: ±6.27 pp standardError 0.06265967111543964 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-5.6-sol Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-07-09T20:34:41.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/38` | | | | | | 13 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max | 80.49% | SE ±6.27 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.8048780487804879 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.8048780487804879 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-sonnet-5-5_max ### Reported statistics Uncertainty Standard error: ±6.27 pp standardError 0.06265967111543964 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label claude-sonnet-5-5 Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-09-29T15:15:14.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/7` | | | | | | 15 | [GPT-5.5 Pro](https://benchize.com/models/gpt-5-5-pro-xhigh.md)Extra high | 78.05% | SE ±6.54 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.7804878048780488 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.7804878048780488 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion gpt-5.5-pro_xhigh ### Reported statistics Uncertainty Standard error: ±6.54 pp standardError 0.06544589202438408 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-5.5-pro Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-06-12T21:33:12.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/51` | | | | | | 15 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 78.05% | SE ±6.54 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.7804878048780488 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.7804878048780488 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort high sourceModelVersion gemini-4-argon_high ### Reported statistics Uncertainty Standard error: ±6.54 pp standardError 0.06544589202438408 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gemini-4-argon Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-10-13T17:14:57.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/1` | | | | | | 17 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max | 73.17% | SE ±7.01 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.7317073170731707 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.7317073170731707 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-opus-5_max ### Reported statistics Uncertainty Standard error: ±7.01 pp standardError 0.07005564203095158 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label claude-opus-5 Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-07-24T19:54:20.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/35` | | | | | | 18 | [GPT-5.5](https://benchize.com/models/gpt-5-5-xhigh.md)Extra high | 72.5% | SE ±7.15 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.725 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.725 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion gpt-5.5_xhigh ### Reported statistics Uncertainty Standard error: ±7.15 pp standardError 0.07149950690165274 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-5.5 Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-06-11T17:47:36.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/64` | | | | | | 19 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-max.md)Max | 70.73% | SE ±7.19 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.7073170731707317 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.7073170731707317 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion gpt-5.6-terra_max ### Reported statistics Uncertainty Standard error: ±7.19 pp standardError 0.07194088392074452 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-5.6-terra Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-07-09T15:58:30.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/39` | | | | | | 20 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-max.md)Max | 60.98% | SE ±7.71 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6097560975609756 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.6097560975609756 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion gpt-5.6-luna_max ### Reported statistics Uncertainty Standard error: ±7.71 pp standardError 0.07712872341874097 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-5.6-luna Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-07-09T14:18:35.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/40` | | | | | | 21 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 56.1% | SE ±7.85 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5609756097560976 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.5609756097560976 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion gpt-6-luna_max ### Reported statistics Uncertainty Standard error: ±7.85 pp standardError 0.07846686801046543 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gpt-6-luna Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-09-22T22:14:05.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/8` | | | | | | 22 | [Qwen3.8 Max](https://benchize.com/models/qwen3-8-max-xhigh.md)Extra high | 46.34% | SE ±7.88 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4634146341463415 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.4634146341463415 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion qwen3.8-max_xhigh ### Reported statistics Uncertainty Standard error: ±7.88 pp standardError 0.07884502378168105 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label qwen3.8-max Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-04T19:32:51.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/30` | | | | | | 22 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max | 46.34% | SE ±7.88 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4634146341463415 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.4634146341463415 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-haiku-5-5_max ### Reported statistics Uncertainty Standard error: ±7.88 pp standardError 0.07884502378168105 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label claude-haiku-5-5 Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-10-07T20:42:31.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/5` | | | | | | 24 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 36.59% | SE ±7.62 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.36585365853658536 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.36585365853658536 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort high sourceModelVersion gemini-3.7-flash_high ### Reported statistics Uncertainty Standard error: ±7.62 pp standardError 0.07615851217559022 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gemini-3.7-flash Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-14T19:59:58.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/26` | | | | | | 25 | [Qwen3.8 Max (0902)](https://benchize.com/models/qwen3-8-max-0902-xhigh.md)Extra high | 34.15% | SE ±7.5 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.34146341463414637 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.34146341463414637 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion qwen3.8-max-0902_xhigh ### Reported statistics Uncertainty Standard error: ±7.5 pp standardError 0.07497768853141171 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label qwen3.8-max-0902 Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-09-02T18:04:58.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/14` | | | | | | 26 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-max.md)Max | 29.27% | SE ±7.19 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2926829268292683 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.2926829268292683 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion claude-sonnet-5_max ### Reported statistics Uncertainty Standard error: ±7.19 pp standardError 0.07194088392074452 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label claude-sonnet-5 Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-06-30T21:54:08.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/43` | | | | | | 27 | [DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max | 26.83% | SE ±7.01 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2682926829268293 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.2682926829268293 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion deepseek-v4-pro-0813_max ### Reported statistics Uncertainty Standard error: ±7.01 pp standardError 0.07005564203095158 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label deepseek-v4-pro-0813 Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-19T13:35:48.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/25` | | | | | | 27 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 26.83% | SE ±7.01 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2682926829268293 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.2682926829268293 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort high sourceModelVersion gemini-3.5-flash_high ### Reported statistics Uncertainty Standard error: ±7.01 pp standardError 0.07005564203095158 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gemini-3.5-flash Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-06-10T17:32:38.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/73` | | | | | | 27 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-max.md)Max | 26.83% | SE ±7.01 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2682926829268293 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.2682926829268293 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion deepseek-v4.1-flash_max ### Reported statistics Uncertainty Standard error: ±7.01 pp standardError 0.07005564203095158 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label deepseek-v4.1-flash Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-10-08T19:02:32.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/4` | | | | | | 27 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview.md) | 26.83% | SE ±7.01 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2682926829268293 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.2682926829268293 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemini-3.1-pro-preview ### Reported statistics Uncertainty Standard error: ±7.01 pp standardError 0.07005564203095158 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gemini-3.1-pro-preview Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-06-11T23:35:57.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/60` | | | | | | 31 | [DeepSeek V4 Flash 0731](https://benchize.com/models/deepseek-v4-flash-0731-max.md)Max | 24.39% | SE ±6.79 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.24390243902439024 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.24390243902439024 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion deepseek-v4-flash-0731_max ### Reported statistics Uncertainty Standard error: ±6.79 pp standardError 0.06789956540036612 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label deepseek-v4-flash-0731 Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-02T02:15:37.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/32` | | | | | | 32 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 21.95% | SE ±6.54 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.21951219512195122 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.21951219512195122 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort high sourceModelVersion gemini-3.8-flash_high ### Reported statistics Uncertainty Standard error: ±6.54 pp standardError 0.06544589202438408 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gemini-3.8-flash Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-09-02T17:15:36.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/15` | | | | | | 32 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 21.95% | SE ±6.54 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.21951219512195122 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.21951219512195122 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort high sourceModelVersion gemini-3.6-flash_high ### Reported statistics Uncertainty Standard error: ±6.54 pp standardError 0.06544589202438408 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gemini-3.6-flash Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-02T00:36:45.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/34` | | | | | | 34 | [Inkling Small](https://benchize.com/models/inkling-small-xhigh.md)Extra high | 17.07% | SE ±5.95 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.17073170731707318 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.17073170731707318 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion inkling-small_xhigh ### Reported statistics Uncertainty Standard error: ±5.95 pp standardError 0.05949419959829495 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label inkling-small Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-14T19:59:09.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/27` | | | | | | 34 | [Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview.md) | 17.07% | SE ±5.95 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.17073170731707318 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.17073170731707318 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemini-3-flash-preview ### Reported statistics Uncertainty Standard error: ±5.95 pp standardError 0.05949419959829497 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gemini-3-flash-preview Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-06-11T23:44:30.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/59` | | | | | | 36 | [Inkling](https://benchize.com/models/inkling-xhigh.md)Extra high | 4.88% | SE ±3.41 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.04878048780487805 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.04878048780487805 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion Inkling_xhigh ### Reported statistics Uncertainty Standard error: ±3.41 pp standardError 0.03405912205797303 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label Inkling Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-06T20:14:32.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/29` | | | | | | 37 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 0% | SE ±0 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.0 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemini-2.5-pro ### Reported statistics Uncertainty Standard error: ±0 pp standardError 0 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gemini-2.5-pro Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-06-11T23:56:12.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/58` | | | | | | 37 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite-high.md)High | 0% | SE ±0 pp | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.0 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort high sourceModelVersion gemini-3.5-flash-lite_high ### Reported statistics Uncertainty Standard error: ±0 pp standardError 0 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gemini-3.5-flash-lite Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-02T01:20:17.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/33` | | | | | --- Cite as: FrontierMath Tier 4 v2 (private) — Benchize, https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tier_4_v2 (retrieved 2026-10-21)