AlibabaAuto-detectedQwen3.8 Max (0902)
Qwen3.8 Max (0902) is an Alibaba proprietary model, released 1 Sept 2026. Its best configuration (xhigh reasoning effort) ranks #152 of 372 on the BenchLeader Index at 57.1 ±6.7, in the upper half. It scores highest in reasoning (67) and lowest in knowledge (56). At $3.00 per million tokens blended it is among the most expensive ranked models. Output speed of 27 tokens per second puts it in the slowest quarter, with a first token in 1.4 s. It has been measured at 2 reasoning-effort settings; tables show the best-scoring one. Last measured 1 Sept 2026.
- Blended price
- $3.00/M
- $2.00 in · $6.00 out
- Output speed
- 27 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 1.39 s
- Context
- 1M
- Overall index57
- Reasoning67
- Maths61
- Knowledge56
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. “Default” means the publisher did not say which setting was used.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| xhighbest | 57.1 | #152 | 27 tok/s | 1.39 s | $0.0026 | Knowledge 56 · Maths 61 · Reasoning 67 |
| default | – | – | 27 tok/s | 1.39 s | $0.0026 | Coding 77 |
Benchmark results
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 | default | Source |
|---|---|---|---|
| GPQA Diamond | 92.3%#22 | – | Epoch AI Benchmarking Hub |
Coding
| Benchmark | xhigh | default | Source |
|---|---|---|---|
| LMArena WebDev | – | 1685#4 | LMArena |
Maths
| Benchmark | xhigh | default | Source |
|---|---|---|---|
| FrontierMath Tiers 1–3 | 65.6%#23 | – | Epoch AI Benchmarking Hub |
| FrontierMath Tier 4 | 34.1%#24 | – | Epoch AI Benchmarking Hub |
| OTIS Mock AIME | 100.0%#1 | – | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | xhigh | default | Source |
|---|---|---|---|
| SimpleQA Verified | 47.3%#28 | – | Epoch AI Benchmarking Hub |
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. | 27 tok/s | 1.39 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. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0026 | – | 12.5 s |
| Summarise a 30-page report | 12,000 / 600 | $0.028 | – | 23.6 s |
| Code edit | 6,000 / 1,500 | $0.021 | – | 56.9 s |
| Agentic coding session | 60,000 / 4,000 | $0.144 | – | 2.5 min |
| Structured extraction | 2,000 / 200 | $0.0052 | – | 8.8 s |
See also
Data as of 10 Sept 2026. Compare these configurations.