AlibabaQwen3 Coder Next
Qwen3 Coder Next is an Alibaba open-weights model, released 2 Feb 2026. Its best configuration ranks #608 of 785 on the BenchLeader Index at 42.1 ±3.6, in the lower half. The ± is the point: 287 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 long context (48) and lowest in knowledge (33). At $0.483 per million tokens blended it is cheaper than most ranked models. Output speed of 80 tokens per second puts it slower than most, with a first answer in 1.1 s. Last measured 3 Feb 2026.stale: no new result in six months
- Blended price
- $0.483/M
- $0.310 in · $1.00 out
- Output speed
- 80 tok/s
- measured by Artificial Analysis
- First answer
- 1.06 s
- first token 0.76 s
- Context
- 262k
- Full answer
- 7.29 s
- median, reasoning included
- Cost per run
- $0.470
- one full Intelligence Index run
- Released
- 2 Feb 2026
- Overall index42
- Reasoning41
- Coding37
- Agents & tools38
- Knowledge33
- Instruction following39
- Long context48
- Composite40
How its index has moved
9 Sept 2026 to 21 Oct 2026The 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 | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond (AA)not in index | 73.7%#266 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 10.2%#322 | Artificial Analysis | |
| CritPt | 0.0%#315 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| SciCode | 36.2%#183 | SciCode | |
| WeirdML | 34.4%#130 | WeirdML | |
| SciCode (AA)not in index | 36.2%#196 | Artificial Analysis | |
| Terminal-Bench 4.0 (AA)not in index | 0.0%#152 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 38.2%#145 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Terminal-Bench Hard | 18.2%#171 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 79.5%#126 | Artificial Analysis | |
| GDPval-AA v2.1not in index | 0.7%#122 | Artificial Analysis | |
| τ³-Banking (AA) | 5.4%#179 | Artificial Analysis | |
| AutomationBenchnot in index | 1.1%#193 | Artificial Analysis | |
| GDP.pdf (AA)not in index | 2.6%#186 | Artificial Analysis |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -62.4#480 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 16.1%#399 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 6.3%#507 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 35.2%#310 | Artificial Analysis |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 47.0%#330 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 9.2#405 | 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 | 63 tok/s | 0.81 s | $0.120 | $0.800 | 262k | bf16 |
Price history
The price above, per 1M tokens, every day it changed.
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 | – | 4.8 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0043 | – | 8.5 s |
| Code edit | 6,000 / 1,500 | $0.0034 | – | 19.8 s |
| Agentic coding session | 60,000 / 4,000 | $0.023 | – | 50.9 s |
| Structured extraction | 2,000 / 200 | $0.0008 | – | 3.6 s |
More from Alibaba
See also
Questions people ask
- What are Qwen3 Coder Next's benchmark scores?
- As of 24 Oct 2026, Qwen3 Coder Next scores 42.1 ±3.6 on the BenchLeader Index, strongest in long context (48) and weakest in knowledge (33). That rests on 9 independent benchmark results, and every score on this page links to its publisher.
- How does Qwen3 Coder Next rank?
- Qwen3 Coder Next is #608 of 785 ranked configurations on 24 Oct 2026. 287 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Qwen3 Coder Next cost per 1M tokens?
- As of 24 Oct 2026, Qwen3 Coder Next costs $0.310 per 1M input tokens and $1.00 per 1M output tokens, $0.483 blended (three input tokens per output token). The list price last changed on 17 Oct 2026.
- When was Qwen3 Coder Next released?
- Alibaba released Qwen3 Coder Next on 2 Feb 2026.
Data as of 24 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Qwen3 Coder Next: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/qwen3-coder-next.