GPQA DiamondVerified
92.3%
GPQA Diamond (AA run)
Models / Alibaba
Qwen3.8-Flash-Next
Qwen · Released 2026-08-26
Alibaba's 26 Aug 2026 Flash-Next sibling in the Qwen3.8 line. AA hosted list $0.15 / $0.47 per 1M tokens — cheaper and faster than Qwen3.8 27B, below hosted Qwen3.8 Max.
Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.
Composite68
Context262K
Input / 1M$0.15
Output / 1M$0.47
Knowledge cutoffunpublished
Output speed51 t/s
Statussolid
Family profile
Best published score in each covered benchmark family.
77/100 avg
- Reasoning
- 92
- Coding
- 51
- Agentic
- 86
- Long context
- 80
4 tested benchmark families
Benchmark placements
Per-benchmark positions
Where Qwen3.8-Flash-Next places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| Terminal-Bench | Agentic | #12/ 167 | 86 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #25/ 184 | 92 | Artificial Analysis | 2026-09-28 |
| SciCode | Coding | #45/ 97 | 51 | Artificial Analysis | 2026-09-28 |
| AA-LCR | Long context | #47/ 184 | 80 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #52/ 186 | 38 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #120/ 195 | Artificial Analysis | 2026-10-12 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where Qwen3.8-Flash-Next shows up, it's highlighted.
ReasoningQwen3.8-Flash-Next · 92
- 196
- 295
- 395
Math
- 152
- 252
- 350
CodingQwen3.8-Flash-Next · 51
- 174
- 273
- 370
AgenticQwen3.8-Flash-Next · 86
- 191
- 289
- 389
Long contextQwen3.8-Flash-Next · 80
- 189
- 286
- 385
Newest receipts
6 recentLast 120 days
Benchmark rows added to the public ledger for Qwen3.8-Flash-Next in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 51 t/s | Artificial Analysis | 10 |
| AA-LCR | Long context | 79.67% | Artificial Analysis | 24 |
| GPQA Diamond | Reasoning | 92.3% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 38% | Artificial Analysis | 24 |
| SciCode | Coding | 50.6% | Artificial Analysis | 24 |
| Terminal-Bench | Agentic | 86.14% | Artificial Analysis | 24 |
Family coverage
Best score per family
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Price vs. performance
Where Qwen3.8-Flash-Next sits on the scatter
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
AnthropicOpenAIGoogleAlibabaMetaZhipuxAIDeepSeekMiniMaxXiaomiMoonshotOtherMeituanMistralNVIDIACohere
Full benchmark ledger
Every catalog benchmark for Qwen3.8-Flash-Next. Scores link to the original source; gaps mean no public row exists yet.
6 of 13 catalog benchmarks have a sourced row for Qwen3.8-Flash-Next.
Reasoning
Humanity's Last ExamVerified
38%
HLE (AA run)
Coding
SciCodeVerified
50.6%
SciCode (AA run)
Agentic
Terminal-BenchVerified
86.14%
Terminal-Bench v2.1 (AA run)
Long context
AA-LCRVerified
79.67%
AA-LCR (AA run)
Performance
AA output speedVerified
51 t/s
Median output tokens/s (1k prompt, default provider)
Sources
Where the numbers come from
- Qwen3.8-Flash-Next announcement· checked 2026-09-01
- Hugging Face Qwen3.8-Flash-Next· checked 2026-09-01
- Artificial Analysis Qwen3.8-Flash-Next· checked 2026-09-01
Questions this model page answers
Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.
What is Qwen3.8-Flash-Next?
Qwen3.8-Flash-Next is a Alibaba model: Alibaba's 26 Aug 2026 Flash-Next sibling in the Qwen3.8 line. AA hosted list $0.15 / $0.47 per 1M tokens — cheaper and faster than Qwen3.8 27B, below hosted Qwen3.8 Max.
What is Qwen3.8-Flash-Next for?
Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.
What does Qwen3.8-Flash-Next cost?
Qwen3.8-Flash-Next lists $0.15 input and $0.47 output per 1M tokens. Pricing last checked 2026-09-01.
How large is the Qwen3.8-Flash-Next context window?
Qwen3.8-Flash-Next publishes a 262K token context window.
What is the VerdictPal status of Qwen3.8-Flash-Next?
Qwen3.8-Flash-Next carries Solid status on the model atlas.
The Pack · Editorial newsletter
Know when the rules move.
One short email when a university changes its AI rule for theses, or a research tool changes its pricing or privacy terms. No tracking, no third-party analytics. Unsubscribe in one click.