# GPT-6 LunaMedium > Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-6-luna-medium. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-6-luna-medium. OpenAI Canonical URL: https://benchize.com/models/gpt-6-luna-medium Last updated: Thu, 22 Oct 2026 04:30:12 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 | | | --- | --- | --- | --- | --- | --- | --- | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 18.06% | — | 112 / 212 | 0.01usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.18055555555555555 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.012202668333333333 \| 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 medium sourceModelVersion openai-gpt-6-luna-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-6 Luna (Medium) Source version v2 Observed 2026-10-21T16:34:20.750Z Evidence SHA-256 `bca68e12cc9a01954ae21b641844c1ecbabe146cb24b87f0f8e9b1db27433c29` Source locator `/evaluations/236` | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 61% | — | 119 / 213 | 0.00611usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.61 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.0061084369999999995 \| 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 medium sourceModelVersion openai-gpt-6-luna-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-6 Luna (Medium) Source version v1 Observed 2026-10-21T16:34:20.378Z Evidence SHA-256 `302d8267c0522bf450ec1deeac4d060e2cf2fb444ba0a4269014d9535de0bd1f` Source locator `/evaluations/233` | | | | | | | | [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 50.15% | — | 90 / 125 | $0.04 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5015 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.556 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.043 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort medium sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-6 Luna Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-6%20Luna/medium/extended` | | | | | | | | [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 9.44% | — | 69 / 113 | $0.02 | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 9.44 \| 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 medium Model configuration GPT-6 Luna (Medium) thinkingEnabled true ### Reported statistics rank 78 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label GPT-6 Luna (Medium) Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/77` | | | | | | | | [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 1,628.4 | Range 1,579.7–1,676.1 | 64 / 126 | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1628.4 \| rating \| reported \| Higher is better \| \| `overall` \| 76.96 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 75.54 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 77.06 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 74.91 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 80.47 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 84.78 \| source_score \| rubric \| Higher is better \| \| `slop` \| 85.24 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 94.95 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 82.28 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 71.29 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 76.83 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 68.39 \| source_score \| rubric \| Higher is better \| ### Configuration provider codex Reasoning effort unknown scoreScope 10_task_current sourceConfiguration gpt-6-luna thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 1,579.7–1,676.1 interval [1579.7,1676.1] rank 65 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label GPT-6 Luna (medium) Evaluated 2026-10-11 Observed 2026-10-21T16:32:48.862Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/64` | | | | | | | | [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 35.53% | — | 87 / 125 | $0.05 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.3553 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.4 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.0512 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort medium sourceVersion v1_1 subset main ### Reported statistics flaggedRate 0 sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-6 Luna Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-6%20Luna/medium/main` | | | | | | | | [ARC-AGI-3](https://benchize.com/benchmarks/arc-prize%3Av3_Semi_Private.md) | 0.19% | — | 40 / 53 | 241.28usd | [arc prize · v3](https://arcprize.org/media/data/leaderboard/v3.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0019415284639354709 \| score_fraction \| v3_Semi_Private \| Higher is better \| \| `total_cost` \| 241.2797313 \| usd \| v3_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v3_Semi_Private harness standard modelGroup openai-gpt-6-luna modelType CoT Reasoning effort medium sourceModelVersion openai-gpt-6-luna-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v3.json) Source arc prize Original model label GPT-6 Luna (Medium) Source version v3 Observed 2026-10-21T16:34:21.112Z Evidence SHA-256 `1aaee2199f8c6d9b5a589aab2fd2480a729e9132f8cf8fbf7b49f81dbd5b2c49` Source locator `/evaluations/42` | | | | | | | | [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 92.4% | — | 35 / 144 | — | [nc bench](https://www.nc-bench.com/models) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.4 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.99 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.2 \| percent \| category \| Higher is better \| \| `language` \| 99.78 \| percent \| category \| Higher is better \| \| `utility` \| 91.17 \| percent \| category \| Higher is better \| \| `reasoning` \| 90.5 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.87 \| percent \| category \| Higher is better \| \| `rule_following` \| 73.2 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.53 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration GPT-6 Luna (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-6 Luna (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/42` | | | | | | | --- Cite as: GPT-6 LunaMedium — Benchize, https://benchize.com/models/gpt-6-luna-medium (retrieved 2026-10-22)