# GPT-6 LunaExtra high

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-6-luna-xhigh. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-6-luna-xhigh.

OpenAI

Canonical URL: https://benchize.com/models/gpt-6-luna-xhigh
Last updated: Thu, 22 Oct 2026 06:30:09 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) | 41.94% | — | 108 / 243 | 0.03usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.41944444444444445 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.032297893333333334 \| 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 xhigh sourceModelVersion openai-gpt-6-luna-xhigh thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-6 Luna (XHigh) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/233` |  |  |  |  |  |  |
| [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 12.63% | — | 60 / 113 | $0.02 | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 12.63 \| 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 xhigh Model configuration GPT-6 Luna (XHigh) thinkingEnabled true ### Reported statistics rank 65 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label GPT-6 Luna (XHigh) Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/64` |  |  |  |  |  |  |
| [ARC-AGI-3](https://benchize.com/benchmarks/arc-prize%3Av3_Semi_Private.md) | 0.16% | — | 57 / 65 | 262.68usd | [arc prize · v3](https://arcprize.org/media/data/leaderboard/v3.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0016413333960356602 \| score_fraction \| v3_Semi_Private \| Higher is better \| \| `total_cost` \| 262.6844075 \| usd \| v3_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v3_Semi_Private harness standard modelGroup openai-gpt-6-luna modelType CoT Reasoning effort xhigh sourceModelVersion openai-gpt-6-luna-xhigh thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v3.json) Source arc prize Original model label GPT-6 Luna (XHigh) Source version v3 Observed 2026-10-22T05:20:04.578Z Evidence SHA-256 `3ce335487296bb2dcf4ba9546c5a2a02b1907db5b08887cd9ff4429fed824916` Source locator `/evaluations/40` |  |  |  |  |  |  |
| [TapTap Maker heldout](https://benchize.com/benchmarks/taptap-maker%3Aheldout.md) | 57.62% | Range 55.71–59.52% | 17 / 30 | — | [taptap maker](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `l2_pass_rate` \| 0.5762 \| score_fraction \| reported \| Higher is better \| ### Configuration datasetVersion 0.2.3 edition 2026-10-18-v6-voxel harness codex Reasoning effort xhigh reasoningMode Not reported ### Reported statistics Uncertainty Reported interval: 55.71–59.52% interval [0.5571,0.5952] intervalMethod bootstrap-case rank 19 rankInterval [14,23] ### Source [Original source](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) Source taptap maker Original model label gpt-6-luna Observed 2026-10-22T06:30:04.044Z Evidence SHA-256 `ad2d7f1adeae0548a4edc0b5e75d11449b443449ff76533d04bc1fb1b6d7035e` Source locator `/heldout/18` |  |  |  |  |  |  |
| [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 51.43% | — | 79 / 125 | $0.06 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5143 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.5693 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.0576 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort xhigh 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 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-6%20Luna/xhigh/extended` |  |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 73% | — | 126 / 245 | 0.01usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.73 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.012172242 \| 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 xhigh sourceModelVersion openai-gpt-6-luna-xhigh thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-6 Luna (XHigh) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/231` |  |  |  |  |  |  |
| [WeirdML v3](https://benchize.com/benchmarks/weirdml%3Av3.md) | 0.08source score | Range 0.07–0.09 | 15 / 25 | — | [weirdml · b0120fe](https://htihle.github.io/assets/data/weirdml_v3.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.07874124242424242 \| source_score \| reported \| Higher is better \| \| `mean_final_best` \| 0.12022755303030302 \| source_score \| reported \| Higher is better \| ### Configuration budget {"kind":"equivalent_tokens","limit":50000000,"start":500000} harness codex_cli Reasoning effort xhigh sourceConfiguration gpt-6-luna-xhigh-openrouter thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 0.07–0.09 interval [0.06867083602621776,0.08885055018431337] intervalMethod {"assumptions":"Independent fresh runs; approximately normal scores; shared variance prior. Pool fitted within analysis mode, including incomplete models; pool estimation uncertainty is not propagated.","confidence":0.95,"draws":10000,"fixed_tasks":true,"method":"partially_pooled_variance","pool":{"degrees_of_freedom":1533,"fallback":false,"prior_df":4,"variance":0.0026383113392869583},"seed":20260915,"unit":"run"} runCount 90 taskCount 11 ### Source [Original source](https://htihle.github.io/assets/data/weirdml_v3.json) Source weirdml Original model label GPT-6 Luna (xhigh) Source version b0120fe Observed 2026-10-22T04:50:05.075Z Evidence SHA-256 `82c3a8de423b23ca0af9761429299a2f21edb0b819e947fdc863f8b5ea4a49b8` Source locator `/rows/14` |  |  |  |  |  |  |
| [TapTap Maker public](https://benchize.com/benchmarks/taptap-maker%3Apublic.md) | 76.62% | Range 75.69–77.55% | 12 / 30 | $0.06 | [taptap maker](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `l2_pass_rate` \| 0.7662 \| score_fraction \| reported \| Higher is better \| \| `cost_per_case` \| 0.0559 \| USD \| per_case \| Lower is better \| ### Configuration datasetVersion 0.2.3 edition 2026-10-18-v6-voxel harness codex Reasoning effort xhigh reasoningMode model-managed ### Reported statistics Uncertainty Reported interval: 75.69–77.55% interval [0.7569,0.7755] intervalMethod bootstrap-case rank 13 rankInterval [11,20] ### Source [Original source](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) Source taptap maker Original model label gpt-6-luna Observed 2026-10-22T06:30:04.044Z Evidence SHA-256 `ad2d7f1adeae0548a4edc0b5e75d11449b443449ff76533d04bc1fb1b6d7035e` Source locator `/public/12` |  |  |  |  |  |  |
| [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 37.1% | — | 81 / 125 | $0.07 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.371 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.418 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.07 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort xhigh 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 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-6%20Luna/xhigh/main` |  |  |  |  |  |  |

---
Cite as: GPT-6 LunaExtra high — Benchize, https://benchize.com/models/gpt-6-luna-xhigh (retrieved 2026-10-22)