AlibabaQwen3.5 Flash
Best configuration ranks #265 of 610 on the BenchLeader Index at 51.8 ±6.0. Last measured 8 Sept 2026. Released 25 Feb 2026.
- Blended price
- $0.559/M
- $0.172 in · $1.72 out
- Output speed
- 41 tok/s
- First answer
- 0.56 s
- Context
- 1M
- Overall index52
- Reasoning59
- Coding47
- Maths47
- Knowledge50
- Human preference58
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 |
|---|---|---|---|---|---|---|
| no reasoning | – | – | 41 tok/s | 0.56 s | $0.0006 | Maths 37 |
| defaultbest | 51.8 | #265 | 41 tok/s | 0.56 s | $0.0006 | Coding 47 · Human preference 58 · Knowledge 50 · Maths 47 · Reasoning 59 |
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 | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| GPQA Diamond | – | 82.3%#101 | Epoch AI Benchmarking Hub | |
| LMArena Hard Prompts | – | 1416#137 | LMArena | |
| GPQA Diamond (Vals)not in index | – | 82.8%#58 | Vals AI |
Coding
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| LMArena Coding | – | 1437#142 | LMArena | |
| LMArena WebDev | – | 1238#109 | LMArena | |
| LiveCodeBench | – | 83.3%#47 | Vals AI | |
| SWE-bench (Vals)not in index | – | 64.4%#71 | Vals AI |
Maths
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| FrontierMath Tiers 1–3 | 18.3%#80 | 9.5%#91 | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | – | 84.4%#83 | Epoch AI Benchmarking Hub | |
| AIME (Vals) | – | 92.5%#19 | Vals AI |
Knowledge
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| SimpleQA Verified | – | 20.3%#62 | Epoch AI Benchmarking Hub | |
| MMLU-Pro | – | 84.1%#65 | Vals AI | |
| LegalBench | – | 84.3%#32 | Vals AI | |
| CorpFin | – | 63.6%#44 | Vals AI | |
| TaxEval | – | 72.2%#67 | Vals AI |
Human preference
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| LMArena Text | – | 1397#134 | LMArena |
Composite
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| Epoch Capabilities Indexnot in index | – | 144.0#77 | Epoch AI Benchmarking Hub |
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. | 41 tok/s | 0.56 s | $0.065 | $0.260 | 1M | – |
Price history
Listed price per 1M tokens over time, as recorded by OpenRouter for the provider with the longest history.
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 | $0.0006 | – | 7.9 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0031 | – | 15.2 s |
| Code edit | 6,000 / 1,500 | $0.0036 | – | 37.1 s |
| Agentic coding session | 60,000 / 4,000 | $0.017 | – | 1.6 min |
| Structured extraction | 2,000 / 200 | $0.0007 | – | 5.4 s |
See also
Data as of 9 Sept 2026. Compare these configurations.