# GPT-6 LunaHigh > Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-6-luna-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-6-luna-high. OpenAI Canonical URL: https://benchize.com/models/gpt-6-luna-high Last updated: Thu, 22 Oct 2026 05:40:11 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. OpenAI ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Source | | | --- | --- | --- | --- | --- | --- | --- | | [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 14.46% | — | 53 / 113 | $0.02 | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 14.46 \| percent \| reported \| Higher is better \| \| `cost` \| 0.02 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote false Fallback policy Not reported Reasoning effort high Model configuration GPT-6 Luna (High) thinkingEnabled true ### Reported statistics rank 57 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label GPT-6 Luna (High) Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/56` | | | | | | | | [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 93.95% | — | 17 / 144 | — | [nc bench](https://www.nc-bench.com/models) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 93.95 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.86 \| percent \| category \| Higher is better \| \| `language` \| 99.78 \| percent \| category \| Higher is better \| \| `utility` \| 92.68 \| percent \| category \| Higher is better \| \| `reasoning` \| 94.22 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.19 \| percent \| category \| Higher is better \| \| `rule_following` \| 80.63 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.23 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort high Model configuration GPT-6 Luna (Reasoning, High) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-6 Luna (Reasoning, High) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/21` | | | | | | | | [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 1,662.6 | Range 1,617.5–1,710.6 | 60 / 126 | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1662.6 \| rating \| reported \| Higher is better \| \| `overall` \| 77.39 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 75.55 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 77.02 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 74.38 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 80.77 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 89.13 \| source_score \| rubric \| Higher is better \| \| `slop` \| 85.72 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 95.89 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 82.62 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 71.01 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 76.54 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 69.18 \| source_score \| rubric \| Higher is better \| ### Configuration provider codex Reasoning effort high scoreScope 10_task_current sourceConfiguration gpt-6-luna-high thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 1,617.5–1,710.6 interval [1617.5,1710.6] rank 60 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label GPT-6 Luna (high) Evaluated 2026-10-11 Observed 2026-10-22T04:40:14.102Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/59` | | | | | | | | [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 37.26% | — | 80 / 125 | $0.06 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.3726 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.4193 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.0646 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort high sourceVersion v1_1 subset main ### Reported statistics flaggedRate 0.002 sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-6 Luna Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-6%20Luna/high/main` | | | | | | | | [ARC-AGI-3](https://benchize.com/benchmarks/arc-prize%3Av3_Semi_Private.md) | 0.18% | — | 53 / 65 | 255.98usd | [arc prize · v3](https://arcprize.org/media/data/leaderboard/v3.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0018024216987988248 \| score_fraction \| v3_Semi_Private \| Higher is better \| \| `total_cost` \| 255.97928910000002 \| usd \| v3_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v3_Semi_Private harness standard modelGroup openai-gpt-6-luna modelType CoT Reasoning effort high sourceModelVersion openai-gpt-6-luna-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v3.json) Source arc prize Original model label GPT-6 Luna (High) Source version v3 Observed 2026-10-22T05:20:04.578Z Evidence SHA-256 `3ce335487296bb2dcf4ba9546c5a2a02b1907db5b08887cd9ff4429fed824916` Source locator `/evaluations/41` | | | | | | | | [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 51.3% | — | 82 / 125 | $0.05 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.513 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.5689 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.0532 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort high sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0.0013 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-6 Luna Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-6%20Luna/high/extended` | | | | | | | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 31.39% | — | 119 / 243 | 0.02usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.3138888888888889 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.02336191 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup openai-gpt-6-luna modelType CoT Reasoning effort high sourceModelVersion openai-gpt-6-luna-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-6 Luna (High) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/234` | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 70.33% | — | 131 / 245 | 0.0095usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.7033333333333333 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.009497197 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup openai-gpt-6-luna modelType CoT Reasoning effort high sourceModelVersion openai-gpt-6-luna-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-6 Luna (High) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/232` | | | | | | | --- Cite as: GPT-6 LunaHigh — Benchize, https://benchize.com/models/gpt-6-luna-high (retrieved 2026-10-22)