AlibabaQwen3 8B
Best configuration ranks #528 of 610 on the BenchLeader Index at 39.5 ±3.9 (thinking reasoning effort). Released 28 Apr 2025.
- Blended price
- $0.660/M
- $0.180 in · $2.10 out
- Output speed
- 38 tok/s
- First answer
- 56 s
- first token 3.67 s
- Context
- 131k
- Overall index40
- Agents & tools36
- Knowledge33
- Instruction following37
- Long context25
- Composite36
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 | – | – | 39 tok/s | 3.67 s | $0.0001 | Maths 34 · Reasoning 37 |
| thinkingbest | 39.5 | #528 | 38 tok/s | 56 s | $0.0007 | Agents & tools 36 · Composite 36 · Instruction following 37 · Knowledge 33 · Long context 25 |
| default | 38.9 | #540 | 39 tok/s | 3.67 s | $0.0001 | Agents & tools 48 · Coding 20 · Composite 37 · Instruction following 33 · Knowledge 29 · Long context 25 · Maths 49 · Reasoning 43 |
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 | thinking | default | Source |
|---|---|---|---|---|
| GPQA Diamond | 47.5%#208 | – | 56.8%#184 | Epoch AI Benchmarking Hub |
| GPQA Diamond (AA)not in index | – | 58.9%#363 | 45.1%#428 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | – | 3.9%#472 | 1.9%#523 | Artificial Analysis |
Coding
| Benchmark | no reasoning | thinking | default | Source |
|---|---|---|---|---|
| SciCode | – | – | 22.6%#152 | SciCode |
| SciCode (AA)not in index | – | 27.9%#149 | – | Artificial Analysis |
Agents & tools
| Benchmark | no reasoning | thinking | default | Source |
|---|---|---|---|---|
| Terminal-Bench Hard | – | 2.3%#304 | 2.3%#304 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | – | 27.8%#264 | 24.9%#285 | Artificial Analysis |
| BFCL Overall | – | – | 42.6%#31 | Berkeley Function Calling Leaderboard |
Maths
| Benchmark | no reasoning | thinking | default | Source |
|---|---|---|---|---|
| OTIS Mock AIME | 22.2%#201 | – | 56.1%#155 | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | no reasoning | thinking | default | Source |
|---|---|---|---|---|
| AA-Omniscience | – | -64.7#420 | -74.0#447 | Artificial Analysis |
Instruction following
| Benchmark | no reasoning | thinking | default | Source |
|---|---|---|---|---|
| IFBench | – | 33.5%#312 | 28.6%#353 | Artificial Analysis |
Long context
| Benchmark | no reasoning | thinking | default | Source |
|---|---|---|---|---|
| AA-LCR | – | 0.0%#419 | 0.0%#419 | Artificial Analysis |
Composite
| Benchmark | no reasoning | thinking | default | Source |
|---|---|---|---|---|
| Epoch Capabilities Indexnot in index | – | – | 136.2#113 | Epoch AI Benchmarking Hub |
| AA Intelligence Index | – | 5.2#511 | 6.0#461 | Artificial Analysis |
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. | 34 tok/s | 0.81 s | $0.117 | $0.455 | 131k | – |
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 | $0.0007 | – | 1.1 min |
| Summarise a 30-page report | 12,000 / 600 | $0.0034 | – | 1.2 min |
| Code edit | 6,000 / 1,500 | $0.0042 | – | 1.6 min |
| Agentic coding session | 60,000 / 4,000 | $0.019 | – | 2.7 min |
| Structured extraction | 2,000 / 200 | $0.0008 | – | 1.0 min |
See also
Data as of 9 Sept 2026. Compare these configurations.