Alibabaqwen3-coder-next
Best configuration ranks #422 of 610 on the BenchLeader Index at 44.1 ±4.4. Last measured 2 Feb 2026stale: no new result in six months. Released 2 Feb 2026.
- Blended price
- $0.450/M
- $0.200 in · $1.20 out
- Output speed
- 113 tok/s
- First answer
- 1.32 s
- first token 1.83 s
- Context
- 262k
- Overall index44
- Coding36
- Agents & tools49
- Knowledge35
- Instruction following38
- Long context49
- Composite42
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 | default | Source |
|---|---|---|
| GPQA Diamond (AA)not in index | 73.7%#256 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 10.2%#255 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| SciCode | 32.3%#139 | SciCode |
| WeirdML | 34.4%#125 | WeirdML |
| SciCode (AA)not in index | 36.2%#133 | Artificial Analysis |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| Terminal-Bench Hard | 18.2%#166 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 79.5%#122 | Artificial Analysis |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -62.4#404 | Artificial Analysis |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| IFBench | 35.2%#295 | Artificial Analysis |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 47.0%#261 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 10.1#311 | 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 |
|---|---|---|---|---|---|---|
| Parasail | 49 tok/s | 1.06 s | $0.120 | $0.800 | 262k | bf16 |
| Alibaba Cloud Int. | 32 tok/s | 2.46 s | $0.300 | $1.50 | 262k | – |
| StreamLake | 20 tok/s | 3.85 s | $0.180 | $0.900 | 256k | – |
| NovitaAI | 14 tok/s | 1.20 s | $0.200 | $1.50 | 262k | fp8 |
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 | $0.0004 | – | 4.0 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0031 | – | 6.6 s |
| Code edit | 6,000 / 1,500 | $0.0030 | – | 14.5 s |
| Agentic coding session | 60,000 / 4,000 | $0.017 | – | 36.6 s |
| Structured extraction | 2,000 / 200 | $0.0006 | – | 3.1 s |
See also
Data as of 9 Sept 2026. Compare with another model.