Qwen3.8 Flash (xhigh): benchmark scores, price and ranking

Qwen3.8 Flash (xhigh) from Alibaba ranks #307 of 743 LLMs on the LLMs Tiger aggregate benchmark score (48.9), based on 1 benchmark results captured up to 2026-10-13.

Organisation: Alibaba
Type: Open-weight / local model
Open weights: Yes
Released: 2026-08-26 (source: epoch)
Cheapest API price: $0.113 in / $0.380 out per million tokens (via aihubmix, observed 2026-10-13T20:47Z)
Aggregate rank: #307 of 743 (score 48.9)

Across the 1 benchmark where at least ten models are scored, Qwen3.8 Flash (xhigh) is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $0.113 per million tokens, is lower than that of 78% of the 427 models with a listed price.

Qwen3.8 Flash (xhigh) benchmark results

Qwen3.8 Flash (xhigh) benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
GDP.pdf	16.6%	#19 of 25	Epoch AI Benchmarking Hub	2026-10-13

About Qwen3.8 Flash (xhigh)

Qwen3.8 Flash (xhigh) is an open-weight model that can run on your own hardware from Alibaba. It was released on 2026-08-26, according to Epoch AI. The cheapest API listing we track charges $0.113 per million input tokens and $0.380 per million output tokens, through aihubmix. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.

Where Qwen3.8 Flash (xhigh) stands

On our aggregate score, Qwen3.8 Flash (xhigh) is #307 of 743 ranked models, around the middle of the table. Its score is 48.9; the scale is centred on 50, so it sits 1.1 points below the typical model. That beats 59% of the ranked field. Among the 74 ranked Alibaba models it is #30. The next one up is qwen3.7-max-preview at 49.0. The next one down is ollama/qwen2.5:32b at 48.9.

Qwen3.8 Flash (xhigh), benchmark by benchmark

Qwen3.8 Flash (xhigh) lands below the middle on GDP.pdf: 16.6%, #19 of 25, with 72% of the field scoring higher. GPT-6 Astra (max) leads at 34.2%; the closest result above is Grok 4.6 (xhigh) at 17.2%. It covers economically valuable document tasks. The board median is 22.8%, so Qwen3.8 Flash (xhigh) is 6.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Qwen3.8 Flash (xhigh) costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), DeepSeek V4 Flash 0731 (max) ($0.016, 53.1). Similar scores cost more on GLM-4.5-Air ($0.125) and Qwen2-VL-72B-Instruct ($0.130).

Release history

The Alibaba model released before it was Qwen3.8-27B (XHigh) on 2026-08-14, which scores 48.5.

Reading these numbers

The 1 score on this page comes from 1 source: Epoch AI Benchmarking Hub (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 1 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#304 qwen3.7-max-preview (49.0)
#305 internlm2_5-7b-chat (48.9)
#306 claude-sonnet-4-20250514 (48.9)
#308 Frogmini 14B 2510 (48.9)
#309 Nova Pro (48.9)
#310 ollama/qwen2.5:32b (48.9)