AlibabaQwen3.8 Max
Qwen3.8 Max is an Alibaba proprietary reasoning model, released 3 Aug 2026. Its best configuration (max reasoning effort) ranks #65 of 775 on the BenchLeader Index at 63.3 ±3.7, in the upper half. The ± is the point: 148 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 reasoning (72) and lowest in agents & tools (58). At $3.00 per million tokens blended it is pricier than most ranked models. Output speed of 40 tokens per second puts it in the slowest quarter, with a first answer in 53.0 s. It has been measured at 3 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 19 Oct 2026.
- Blended price
- $3.00/M
- $2.00 in · $6.00 out
- Output speed
- 40 tok/s
- measured by Artificial Analysis
- First answer
- 53 s
- first token 2.69 s
- Context
- 1M
- Full answer
- 65 s
- median, reasoning included
- Cost per run
- $5.41
- one full Intelligence Index run
- Released
- 3 Aug 2026
- Overall index63
- Reasoning72
- Coding65
- Agents & tools58
- Maths65
- Knowledge63
- Human preference68
- Multimodal66
- Long context65
- Composite63
Versions
Alibaba has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Qwen3.8 Maxmaxthis page | 3 Aug 2026 | 63.3 | #65 |
| Qwen3.6 Maxmax | 20 Apr 2026 | 62.4 | #87 |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| xhigh | 57.1 | #185 | 34 tok/s | 2.69 s | $0.0026 | Knowledge 55 · Maths 63 · Reasoning 67 |
| maxbest | 63.3 | #65 | 40 tok/s | 53 s | $0.0026 | Agents & tools 58 · Coding 65 · Composite 63 · Human preference 68 · Knowledge 63 · Long context 65 · Maths 65 · Multimodal 66 · Reasoning 72 |
| not stated | – | – | 34 tok/s | 2.69 s | $0.0026 | Coding 57 |
How its index has moved
27 Sept 2026 to 20 Oct 2026- max
- xhigh
The 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 | xhigh | max | Source | Trend |
|---|---|---|---|---|
| GPQA Diamond | 92.7%#25 | – | Epoch AI Benchmarking Hub | |
| Arena Hard Prompts | – | 1503#28 | Arena (LMArena) | |
| LiveBench 2.0 Reasoningnot in index | – | 88.2%#22 | LiveBench | |
| LiveBench 1.0 Reasoningnot in index | – | 88.2%#23 | LiveBench | |
| GPQA Diamond (AA)not in index | – | 92.8%#28 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | – | 43.1%#60 | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | – | 93.7%#6 | Vals AI | |
| CritPt | – | 20.0%#61 | Artificial Analysis | |
| MysteryMechanismnot in index | – | 23.9%#17 | Vals AI | |
| Chess Puzzlesnot in index | 46.0%#26 | – | Epoch AI Benchmarking Hub | |
| Mystery Game Puzzlesnot in index | 38.0%#17 | – | Epoch AI Benchmarking Hub | |
| LMCAnot in index | 46.2%#85 | – | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | 92.0%#71 | – | Epoch AI Benchmarking Hub |
Coding
| Benchmark | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|
| SciCode | – | 53.2%#79 | 52.1%#88 | SciCode | |
| Arena Coding | – | 1523#29 | – | Arena (LMArena) | |
| Arena WebDev | – | 1674#11 | – | Arena (LMArena) | |
| LiveBench 2.0 Codingnot in index | – | 60.3%#41 | – | LiveBench | |
| LiveBench 1.0 Codingnot in index | – | 72.9%#55 | – | LiveBench | |
| SciCode (AA)not in index | – | 53.2%#78 | – | Artificial Analysis | |
| LiveCodeBench | – | 87.8%#10 | – | Vals AI | |
| IOI | – | 68.9%#12 | – | Vals AI | |
| SWE-bench (Vals)not in index | – | 85.6%#17 | – | Vals AI | |
| Code Migrationnot in index | – | 24.0%#48 | – | Vals AI | |
| ProgramBenchnot in index | – | 0.0%#32 | – | Vals AI | |
| Vibe Code Bench 1-100not in index | – | 12.8%#22 | – | Vals AI | |
| Vibe Code Bench v1.1not in index | – | 64.7%#48 | – | Vals AI | |
| DeepSWE v1.1not in index | 57.5%#36 | – | – | Epoch AI Benchmarking Hub | |
| FrontierSWEnot in index | 17.8%#18 | – | – | Epoch AI Benchmarking Hub | |
| Terminal-Bench 4.0 (AA)not in index | – | 38.9%#32 | – | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | – | 88.8%#9 | – | Artificial Analysis | |
| Startrise Frontendnot in index | – | 71.3%#16 | 69.8%#19 | Startrise | |
| FrontierCode 1.1 (AA)not in index | – | 43.2%#18 | – | Artificial Analysis |
Agents & tools
Maths
| Benchmark | xhigh | max | Source | Trend |
|---|---|---|---|---|
| FrontierMath Tiers 1–3 | 74.7%#21 | – | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | 46.3%#27 | – | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | 100.0%#1 | – | Epoch AI Benchmarking Hub | |
| ProofBench | – | 58.0%#21 | Vals AI | |
| LiveBench Mathematicsnot in index | – | 91.3%#30 | LiveBench | |
| Arena Maths | – | 1500#18 | Arena (LMArena) |
Knowledge
| Benchmark | xhigh | max | Source | Trend |
|---|---|---|---|---|
| SimpleQA Verified | 47.3%#34 | – | Epoch AI Benchmarking Hub | |
| LiveBench 2.0 Data Analysisnot in index | – | 78.4%#18 | LiveBench | |
| LiveBench Researchnot in index | – | 69.9%#30 | LiveBench | |
| LiveBench 1.0 Data Analysisnot in index | – | 78.4%#24 | LiveBench | |
| AA-Omniscience | – | 12.0#90 | Artificial Analysis | |
| MMLU-Pro | – | 88.6%#18 | Vals AI | |
| LegalBench | – | 83.6%#50 | Vals AI | |
| CorpFin | – | 65.8%#26 | Vals AI | |
| TaxEval | – | 75.5%#17 | Vals AI | |
| Excel Modeling Benchmarknot in index | – | 60.1%#35 | Vals AI | |
| MedCodenot in index | – | 40.7%#60 | Vals AI | |
| MedScribenot in index | – | 85.0%#32 | Vals AI | |
| Public Benefits Benchnot in index | – | 67.1%#15 | Vals AI | |
| GDP.pdfnot in index | 23.2%#23 | – | Epoch AI Benchmarking Hub | |
| AA-Omniscience: accuracynot in index | – | 31.9%#167 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | – | 71.2%#37 | Artificial Analysis |
Instruction following
| Benchmark | max | Source | Trend |
|---|---|---|---|
| LiveBench Languagenot in index | 79.7%#34 | LiveBench | |
| LiveBench Instruction Followingnot in index | 74.1%#13 | LiveBench | |
| Arena Instruction Followingnot in index | 1474#29 | Arena (LMArena) |
Human preference
| Benchmark | max | Source | Trend |
|---|---|---|---|
| Arena Text | 1482#24 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1469#19 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1490#21 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1492#26 | Arena (LMArena) |
Multimodal
| Benchmark | max | Source | Trend |
|---|---|---|---|
| Arena Vision | 1313#10 | Arena (LMArena) | |
| LiveBench Designnot in index | 78.6%#17 | LiveBench | |
| MMMU-Pro | 82.8%#29 | Artificial Analysis | |
| MMMU-Pro (Vals)not in index | 88.0%#12 | Vals AI | |
| MortgageTaxnot in index | 64.0%#48 | Vals AI | |
| SAGEnot in index | 51.3%#14 | Vals AI | |
| AA-3Dnot in index | 948#15 | Artificial Analysis |
Long context
| Benchmark | max | Source | Trend |
|---|---|---|---|
| AA-LCR | 80.3%#70 | Artificial Analysis | |
| MLCRnot in index | 20.0%#29 | Artificial Analysis |
Composite
| Benchmark | max | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 157.4#21 | Epoch AI Benchmarking Hub | |
| LiveBench 2.0 | 64.2%#32 | LiveBench | |
| LiveBench 1.0not in index | 78.5%#17 | LiveBench | |
| AA Intelligence Index v4.3.2 | 45.4#35 | Artificial Analysis | |
| Vals Multimodal Indexnot in index | 65.4%#12 | Vals AI |
Where it wins
Benchmarks where this configuration ranks in the top five of every configuration measured.
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Alibaba Cloud Int. | 38 tok/s | 2.44 s | $2.00 | $6.00 | 1M | – |
| Alibaba Cloud Int. | 32 tok/s | 2.63 s | $2.00 | $6.00 | 1M | – |
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 at $0.222 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0026 | $0.0021 | 1.0 min |
| Summarize a 30-page report | 12,000 / 600 | $0.028 | $0.012 | 1.1 min |
| Code edit | 6,000 / 1,500 | $0.021 | $0.013 | 1.5 min |
| Agentic coding session | 60,000 / 4,000 | $0.144 | $0.064 | 2.5 min |
| Structured extraction | 2,000 / 200 | $0.0052 | $0.0025 | 57.9 s |
More from Alibaba
Compare Qwen3.8 Max with…
- Qwen3.8 Max vs Claude Opus 5.5
- Qwen3.8 Max vs Gemini 4 Argon
- Qwen3.8 Max vs Muse Wonder Full
- Qwen3.8 Max vs GPT-6 Astra
- Qwen3.8 Max vs Claude Fable 5.1
- Qwen3.8 Max vs GPT-6.1 Sol
- Qwen3.8 Max vs Claude Sonnet 5.5
- Qwen3.8 Max vs Claude Fable 5
- Qwen3.8 Max vs Claude Opus 5
- Qwen3.8 Max vs GPT-5.6 Sol
- Qwen3.8 Max vs Muse Wonder
- Qwen3.8 Max vs Muse Spark 1.3
- Qwen3.8 Max vs GPT-6 Sol
- Qwen3.8 Max vs GPT-5.5
- Qwen3.8 Max vs GPT-5.5 Pro
- Qwen3.8 Max vs Kimi K3
- Qwen3.8 Max vs GPT-5.4
- Qwen3.8 Max vs Gemini 3.8 Flash
- Qwen3.8 Max vs Muse Spark
- Qwen3.8 Max vs GPT-5.6 Terra
- Qwen3.8 Max vs MiMo-V2.6-Pro
- Qwen3.8 Max vs Grok 4.6
- Qwen3.8 Max vs Grok 4.7
- Qwen3.8 Max vs GPT-5.3-Codex
- Qwen3.8 Max vs GLM 5.3
- Qwen3.8 Max vs Gemini 3.7 Flash
- Qwen3.8 Max vs GPT-5.4 Pro
- Qwen3.8 Max vs Claude Opus 4.7
- Qwen3.8 Max vs Claude Opus 4.8
- Qwen3.8 Max vs Gemini 3.5 Flash
- Qwen3.8 Max vs Muse Spark 1.2
- Qwen3.8 Max vs Qwen3.8 2.4T A95B
- Qwen3.8 Max vs DeepSeek V4.1 Flash 1017
- Qwen3.8 Max vs Muse Spark 1.1
- Qwen3.8 Max vs Claude Opus 4.6
- Qwen3.8 Max vs GLM 5.3 Flash
- Qwen3.8 Max vs DeepSeek V4 Pro
- Qwen3.8 Max vs GLM 5.2
- Qwen3.8 Max vs Qwen3.6 Max
See also
Data as of 21 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Qwen3.8 Max: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/qwen3-8-max, data as of 21 Oct 2026.