AlibabaQwen3.8-Flash-Next
Qwen3.8-Flash-Next is an Alibaba open-weights reasoning model, released 26 Aug 2026. Its best configuration ranks #115 of 785 on the BenchLeader Index at 60.2 ±6.6, in the upper half. The ± is the point: 263 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in composite (74) and lowest in knowledge (57). At $0.230 per million tokens blended it is cheaper than most ranked models. Output speed of 52 tokens per second puts it in the slowest quarter, with a first answer in 40.9 s. Last measured 22 Oct 2026.
- Blended price
- $0.230/M
- $0.150 in · $0.470 out
- Output speed
- 52 tok/s
- measured by Artificial Analysis
- First answer
- 41 s
- Context
- 256k
- Full answer
- 51 s
- median, reasoning included
- Cost per run
- $0.372
- one full Intelligence Index run
- Released
- 26 Aug 2026
- Overall index60
- Reasoning59
- Coding67
- Agents & tools64
- Knowledge57
- Multimodal63
- Long context65
- Composite74
How its index has moved
9 Sept 2026 to 23 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| LiveBench 1.0 Reasoningnot in index | 87.4%#27 | LiveBench | |
| GPQA Diamond (AA)not in index | 92.3%#36 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 38.0%#101 | Artificial Analysis | |
| CritPt | 11.1%#114 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena WebDev | 1628#19 | Arena (LMArena) | |
| LiveBench 1.0 Codingnot in index | 72.5%#56 | LiveBench | |
| SciCode (AA)not in index | 50.6%#103 | Artificial Analysis | |
| Terminal-Bench 4.0 (AA)not in index | 25.3%#55 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 86.1%#21 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Agent | -3.1#35 | Arena (LMArena) | |
| LiveBench Agentic Codingnot in index | 61.6%#12 | LiveBench | |
| GDPval-AA v2.1not in index | 56.4%#20 | Artificial Analysis | |
| τ³-Banking (AA) | 45.4%#14 | Artificial Analysis | |
| AutomationBenchnot in index | 55.9%#56 | Artificial Analysis | |
| GDP.pdf (AA)not in index | 15.6%#94 | Artificial Analysis |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| LiveBench Mathematicsnot in index | 85.8%#53 | LiveBench |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| LiveBench 1.0 Data Analysisnot in index | 74.2%#39 | LiveBench | |
| AA-Omniscience | -9.7#188 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 24.5%#242 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 54.7%#102 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| LiveBench Languagenot in index | 74.6%#50 | LiveBench | |
| LiveBench Instruction Followingnot in index | 77.1%#5 | LiveBench |
Multimodal
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MMMU-Pro | 79.8%#57 | Artificial Analysis |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 79.7%#88 | Artificial Analysis | |
| MLCRnot in index | 20.6%#43 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| LiveBench 1.0not in index | 76.2%#31 | LiveBench | |
| AA Intelligence Index v4.3.2 | 39.8#64 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0002 | – | 46.7 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0021 | – | 52.5 s |
| Code edit | 6,000 / 1,500 | $0.0016 | – | 1.2 min |
| Agentic coding session | 60,000 / 4,000 | $0.011 | – | 2.0 min |
| Structured extraction | 2,000 / 200 | $0.0004 | – | 44.7 s |
Compare Qwen3.8-Flash-Next with…
- Qwen3.8-Flash-Next vs Claude Opus 5.5
- Qwen3.8-Flash-Next vs Gemini 4 Argon
- Qwen3.8-Flash-Next vs Muse Wonder Full
- Qwen3.8-Flash-Next vs Claude Fable 5.1
- Qwen3.8-Flash-Next vs GPT-6 Astra
- Qwen3.8-Flash-Next vs GPT-6.1 Sol
- Qwen3.8-Flash-Next vs Claude Fable 5
- Qwen3.8-Flash-Next vs Claude Sonnet 5.5
- Qwen3.8-Flash-Next vs Claude Opus 5
- Qwen3.8-Flash-Next vs GPT-5.6 Sol
See also
Questions people ask
- What are Qwen3.8-Flash-Next's benchmark scores?
- As of 24 Oct 2026, Qwen3.8-Flash-Next scores 60.2 ±6.6 on the BenchLeader Index, strongest in composite (74) and weakest in knowledge (57). That rests on 8 independent benchmark results, and every score on this page links to its publisher.
- How does Qwen3.8-Flash-Next rank?
- Qwen3.8-Flash-Next is #115 of 785 ranked configurations on 24 Oct 2026. 263 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Qwen3.8-Flash-Next cost per 1M tokens?
- As of 24 Oct 2026, Qwen3.8-Flash-Next costs $0.150 per 1M input tokens and $0.470 per 1M output tokens, $0.230 blended (three input tokens per output token).
- Is Qwen3.8-Flash-Next better than GPT-5.6 Sol?
- As of 24 Oct 2026, GPT-5.6 Sol (max) leads on quality (68.0 vs 60.2 on the BenchLeader Index), but Qwen3.8-Flash-Next costs 35× less, so it is the better buy unless you need the extra quality. The head-to-head page has the benchmark-by-benchmark detail.
- When was Qwen3.8-Flash-Next released?
- Alibaba released Qwen3.8-Flash-Next on 26 Aug 2026.
Data as of 24 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Qwen3.8-Flash-Next: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/qwen3-8-flash-next.