# GPT-6 AstraExtra high

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

OpenAI

Canonical URL: https://benchize.com/models/gpt-6-astra-xhigh
Last updated: Wed, 21 Oct 2026 18:52:20 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

OpenAI

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [FrontierMath Tier 4 v2 (private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tier_4_v2.md) | 97.6% | SE ±2.4 pp | 2 / 38 | — | — | [epoch ai · FrontierMath-Tier-4-v2-Private](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) |  |
| ### 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` |  |  |  |  |  |  |  |
| [DesignArena Agentic web applications](https://benchize.com/benchmarks/designarena%3Awebapps.md) | 1,332elo | SE ±10.31 | 2 / 39 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=webapps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1332 \| elo \| webapps \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality text Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics Uncertainty Standard error: ±10.31 averageGenerationTimeMs Not reported battles 1303 losses 521 standardError 10.3051 winRate 60 wins 782 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=webapps) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:38:00.309Z Evidence SHA-256 `f955787274cf4ac627ada7cd33eaae2e08ef7297db92d3391340fcaa0b44a35f` Source locator `/data/1` |  |  |  |  |  |  |  |
| [DesignArena Image to HTML](https://benchize.com/benchmarks/designarena%3Aimage-to-html.md) | 1,264elo | — | 3 / 35 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=image-to-html) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1264 \| elo \| image-to-html \| Higher is better \| ### Configuration arenaType models category website inputModality image Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 662648 battles 684 losses 289 standardError Not reported winRate 57.8 wins 395 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=image-to-html) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:37:58.959Z Evidence SHA-256 `94f97ebbdd53a8c56f138b620e59b3a9b35c66c3954dcaaa1b2ed4c71518b404` Source locator `/data/2` |  |  |  |  |  |  |  |
| [Terminal-Bench 4](https://benchize.com/benchmarks/harbor%3Aterminal-bench-4.md) | 57.88% | 95% CI 55.16–60.6% | 3 / 17 | — | — | [harbor](https://www.tbench.ai/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 57.88 \| percent \| reported \| Higher is better \| \| `pass_at_2` \| 0.6424 \| score_fraction \| reported \| Higher is better \| \| `pass_at_3` \| 0.6697 \| score_fraction \| reported \| Higher is better \| \| `pass_at_4` \| 0.6848 \| score_fraction \| reported \| Higher is better \| \| `pass_at_5` \| 0.697 \| score_fraction \| reported \| Higher is better \| ### Configuration agent Codex Reasoning effort xhigh sourceSubmission 16db8ad5-84aa-4588-b660-1ce68c0d45e2 ### Reported statistics Uncertainty 95% confidence interval: 55.16–60.6% confidenceHalfWidth95 2.72 sampleSize 330 ### Source [Original source](https://www.tbench.ai/) Source harbor Original model label GPT-6 Astra Evaluated 2026-09-03 Observed 2026-10-21T16:33:12.399Z Evidence SHA-256 `0c2d7608e0711b34acae3e757dc2b8bf58bf1f5f04fec84de6cd02598168712c` Source locator `/rows/5` |  |  |  |  |  |  |  |
| [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,353elo | — | 1 / 65 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1353 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 318590 battles 171 losses 55 standardError Not reported winRate 67.8 wins 116 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/0` |  |  |  |  |  |  |  |
| [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 62.12% | — | 15 / 125 | $2.86 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6212 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.6797 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 2.8602 \| 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 Astra Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-6%20Astra/xhigh/extended` |  |  |  |  |  |  |  |
| [TapTap Maker heldout](https://benchize.com/benchmarks/taptap-maker%3Aheldout.md) | 76.53% | Range 74.87–78.2% | 1 / 26 | — | — | [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` \| 0.7653 \| 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: 74.87–78.2% interval [0.7487,0.782] intervalMethod bootstrap-case rank 1 rankInterval [1,4] ### Source [Original source](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) Source taptap maker Original model label gpt-6-astra Observed 2026-10-21T16:33:19.620Z Evidence SHA-256 `ad2d7f1adeae0548a4edc0b5e75d11449b443449ff76533d04bc1fb1b6d7035e` Source locator `/heldout/0` |  |  |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 98.5% | — | 1 / 213 | 0.35usd per task | — | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.985 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.3470552 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup openai-gpt-6-astra modelType CoT Reasoning effort xhigh sourceModelVersion openai-gpt-6-astra-xhigh thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-6 Astra (XHigh) Source version v1 Observed 2026-10-21T16:34:20.378Z Evidence SHA-256 `302d8267c0522bf450ec1deeac4d060e2cf2fb444ba0a4269014d9535de0bd1f` Source locator `/evaluations/225` |  |  |  |  |  |  |  |
| [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,469elo | — | 3 / 110 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1469 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 598503 battles 1691 losses 419 standardError Not reported winRate 75.2 wins 1272 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/2` |  |  |  |  |  |  |  |
| [DesignArena Image to web application](https://benchize.com/benchmarks/designarena%3Aimage-to-webapp.md) | 1,252elo | SE ±18.09 | 5 / 24 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=image-to-webapp) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1252 \| elo \| image-to-webapp \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality image Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics Uncertainty Standard error: ±18.09 averageGenerationTimeMs Not reported battles 391 losses 180 standardError 18.0925 winRate 54 wins 211 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=image-to-webapp) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:37:59.412Z Evidence SHA-256 `cc4e49fc057d3b786184ff44b697422e2420a174e8a98a80a77aa65021921ab4` Source locator `/data/4` |  |  |  |  |  |  |  |
| [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 50.62% | — | 13 / 125 | $3.28 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5062 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.5575 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 3.2755 \| 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 Astra Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-6%20Astra/xhigh/main` |  |  |  |  |  |  |  |
| [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,396elo | — | 1 / 112 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1396 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 497700 battles 579 losses 198 standardError Not reported winRate 65.8 wins 381 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/0` |  |  |  |  |  |  |  |
| [WeirdML v3](https://benchize.com/benchmarks/weirdml%3Av3.md) | 0.42source score | Range 0.4–0.44 | 1 / 25 | — | — | [weirdml · b0120fe](https://htihle.github.io/assets/data/weirdml_v3.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4222023136363636 \| source_score \| reported \| Higher is better \| \| `mean_final_best` \| 0.5404530212121212 \| source_score \| reported \| Higher is better \| ### Configuration budget {"kind":"equivalent_tokens","limit":50000000,"start":500000} harness codex_cli Reasoning effort xhigh sourceConfiguration gpt-6-astra-xhigh-openrouter thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 0.4–0.44 interval [0.4023541536494142,0.44115944655521194] 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 76 taskCount 11 ### Source [Original source](https://htihle.github.io/assets/data/weirdml_v3.json) Source weirdml Original model label GPT-6 Astra (xhigh) Source version b0120fe Observed 2026-10-21T16:33:04.394Z Evidence SHA-256 `82c3a8de423b23ca0af9761429299a2f21edb0b819e947fdc863f8b5ea4a49b8` Source locator `/rows/0` |  |  |  |  |  |  |  |
| [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,334elo | — | 8 / 99 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1334 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 567548 battles 360 losses 142 standardError Not reported winRate 60.6 wins 218 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/8` |  |  |  |  |  |  |  |
| [ARC-AGI-3](https://benchize.com/benchmarks/arc-prize%3Av3_Semi_Private.md) | 59.34% | — | 2 / 53 | 37,317.39usd | — | [arc prize · v3](https://arcprize.org/media/data/leaderboard/v3.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5934295409146055 \| score_fraction \| v3_Semi_Private \| Higher is better \| \| `total_cost` \| 37317.38768 \| usd \| v3_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v3_Semi_Private harness standard modelGroup openai-gpt-6-astra modelType CoT Reasoning effort xhigh sourceModelVersion openai-gpt-6-astra-xhigh thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v3.json) Source arc prize Original model label GPT-6 Astra (XHigh) Source version v3 Observed 2026-10-21T16:34:21.112Z Evidence SHA-256 `1aaee2199f8c6d9b5a589aab2fd2480a729e9132f8cf8fbf7b49f81dbd5b2c49` Source locator `/evaluations/28` |  |  |  |  |  |  |  |
| [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 38.96% | — | 6 / 113 | $1.5 | — | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 38.96 \| percent \| reported \| Higher is better \| \| `cost` \| 1.5 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote false Fallback policy Not reported Reasoning effort xhigh Model configuration GPT-6 Astra (XHigh) thinkingEnabled true ### Reported statistics rank 6 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label GPT-6 Astra (XHigh) Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/5` |  |  |  |  |  |  |  |
| [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,449elo | — | 4 / 117 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1449 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 637512 battles 2348 losses 641 standardError Not reported winRate 72.7 wins 1707 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/3` |  |  |  |  |  |  |  |
| [DeepSWE](https://benchize.com/benchmarks/deepswe%3Av1.1.md) | 74.12% | Range 71.25–76.98% | 1 / 70 | $4.43 | 1,132.4s | [deepswe](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.7411504424778761 \| score_fraction \| scored_rollout_attempts \| Higher is better \| \| `pass_at_4` \| 0.8053097345132744 \| score_fraction \| tasks_with_one_passing_rollout \| Higher is better \| \| `cost_per_attempt` \| 4.429117203539823 \| USD \| scored_attempt \| Lower is better \| \| `duration` \| 1132.4004424778761 \| seconds \| scored_attempt \| Lower is better \| ### Configuration harness mini-swe-agent Reasoning effort xhigh sourceConfiguration mini_swe_agent_gpt_6_astra_xhigh ### Reported statistics Uncertainty Reported interval: 71.25–76.98% interval [0.7124964807371247,0.7698044042186275] intervalMethod 95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R)) runCount 4 sampleSize 452 taskCount 113 ### Source [Original source](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) Source deepswe Original model label gpt-6-astra Observed 2026-10-21T16:30:23.371Z Evidence SHA-256 `a7c15d66288fd249c020b9931c017b92d1a3b90e480b3ff34974b752bd030019` Source locator `/rows/0` |  |  |  |  |  |  |  |
| [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,329elo | — | 5 / 123 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1329 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 618516 battles 4802 losses 2017 standardError Not reported winRate 58 wins 2785 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/6` |  |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 93.33% | — | 3 / 212 | 0.83usd per task | — | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.9333333333333333 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.8286855833333331 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup openai-gpt-6-astra modelType CoT Reasoning effort xhigh sourceModelVersion openai-gpt-6-astra-xhigh thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-6 Astra (XHigh) Source version v2 Observed 2026-10-21T16:34:20.750Z Evidence SHA-256 `bca68e12cc9a01954ae21b641844c1ecbabe146cb24b87f0f8e9b1db27433c29` Source locator `/evaluations/227` |  |  |  |  |  |  |  |
| [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,379elo | SE ±3.96 | 2 / 116 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1379 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics Uncertainty Standard error: ±3.96 averageGenerationTimeMs 614235 battles 8929 losses 3190 standardError 3.9625 winRate 64.3 wins 5739 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/1` |  |  |  |  |  |  |  |
| [TapTap Maker public](https://benchize.com/benchmarks/taptap-maker%3Apublic.md) | 85.81% | Range 85–86.62% | 1 / 26 | $3.59 | — | [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` \| 0.8581 \| score_fraction \| reported \| Higher is better \| \| `cost_per_case` \| 3.5904 \| 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: 85–86.62% interval [0.85,0.8662] intervalMethod bootstrap-case rank 1 rankInterval [1,4] ### Source [Original source](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) Source taptap maker Original model label gpt-6-astra Observed 2026-10-21T16:33:19.620Z Evidence SHA-256 `ad2d7f1adeae0548a4edc0b5e75d11449b443449ff76533d04bc1fb1b6d7035e` Source locator `/public/0` |  |  |  |  |  |  |  |
| [DesignArena Full-stack application development](https://benchize.com/benchmarks/designarena%3Afullstack.md) | 1,357elo | SE ±15.55 | 1 / 31 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=fullstack) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1357 \| elo \| fullstack \| Higher is better \| ### Configuration arenaType agents category fullstack inputModality Not reported Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics Uncertainty Standard error: ±15.55 averageGenerationTimeMs Not reported battles 553 losses 215 standardError 15.5542 winRate 61.1 wins 338 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=fullstack) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:38:00.857Z Evidence SHA-256 `aa171459dd44cfad57fba8da746c40b27832b57dc731b1198bdb71c73ddd0f97` Source locator `/data/0` |  |  |  |  |  |  |  |
| [DesignArena Godot game development](https://benchize.com/benchmarks/designarena%3Agodot-game-dev.md) | 1,348elo | SE ±21.2 | 1 / 14 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=godot-game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1348 \| elo \| godot-game-dev \| Higher is better \| ### Configuration arenaType agents category agon_godot inputModality Not reported Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics Uncertainty Standard error: ±21.2 averageGenerationTimeMs Not reported battles 328 losses 113 standardError 21.2047 winRate 65.5 wins 215 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=godot-game-dev) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:38:02.075Z Evidence SHA-256 `0aad65341ae5287f97ba93448674c557edad76a4e41056ec30cc32bf05d3a7e3` Source locator `/data/0` |  |  |  |  |  |  |  |
| [DesignArena Agentic presentation generation](https://benchize.com/benchmarks/designarena%3Aagentic-slides.md) | 1,243elo | SE ±12.64 | 5 / 19 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=agentic-slides) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1243 \| elo \| agentic-slides \| Higher is better \| ### Configuration arenaType agents category agon_slides inputModality Not reported Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics Uncertainty Standard error: ±12.64 averageGenerationTimeMs Not reported battles 809 losses 404 standardError 12.6389 winRate 50.1 wins 405 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=agentic-slides) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:38:03.963Z Evidence SHA-256 `b732c5aba2e357cf6034f23084d5f95f8e8882f62b8bf3ee340f0cd5cd773724` Source locator `/data/6` |  |  |  |  |  |  |  |
| [DesignArena SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,431elo | — | 1 / 77 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1431 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 264822 battles 1635 losses 511 standardError Not reported winRate 68.8 wins 1124 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/1` |  |  |  |  |  |  |  |
| [DesignArena Mobile application development](https://benchize.com/benchmarks/designarena%3Amobileapps.md) | 1,314elo | SE ±14.45 | 1 / 33 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=mobileapps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1314 \| elo \| mobileapps \| Higher is better \| ### Configuration arenaType agents category mobileapps inputModality Not reported Reasoning effort xhigh sourceModelVersion gpt-6-astra thinkingEnabled true variationName public ### Reported statistics Uncertainty Standard error: ±14.45 averageGenerationTimeMs Not reported battles 653 losses 231 standardError 14.4519 winRate 64.6 wins 422 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=mobileapps) Source designarena Original model label GPT-6 Astra (xhigh) Source version public Observed 2026-10-21T16:38:02.538Z Evidence SHA-256 `40af33d0e93e729486da375cbe954633e2458af0dd6ca6d9fbdcda90da650f7d` Source locator `/data/0` |  |  |  |  |  |  |  |

---
Cite as: GPT-6 AstraExtra high — Benchize, https://benchize.com/models/gpt-6-astra-xhigh (retrieved 2026-10-21)