# Qwen3.8 27BExtra high

> Source: Benchize (https://benchize.com) — https://benchize.com/models/qwen3-8-27b-xhigh. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/qwen3-8-27b-xhigh.

Alibaba

Canonical URL: https://benchize.com/models/qwen3-8-27b-xhigh
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.

Alibaba

## Benchmarks

| Benchmark | Score | Rank | Cost | Source |  |
| --- | --- | --- | --- | --- | --- |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 87.5% | 87 / 245 | 0.22usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.875 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.21523628600000005 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup alibaba-qwen3-8-27b modelType CoT Reasoning effort xhigh sourceModelVersion alibaba-qwen3-8-27b-xhigh thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Qwen3.8-27B (XHigh) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/258` |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 42.36% | 106 / 243 | 0.45usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4236111111111111 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.4469396510416667 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup alibaba-qwen3-8-27b modelType CoT Reasoning effort xhigh sourceModelVersion alibaba-qwen3-8-27b-xhigh thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Qwen3.8-27B (XHigh) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/260` |  |  |  |  |  |

---
Cite as: Qwen3.8 27BExtra high — Benchize, https://benchize.com/models/qwen3-8-27b-xhigh (retrieved 2026-10-22)