AlibabaQwen3.7 Plus
Best configuration ranks #97 of 610 on the BenchLeader Index at 59.7 ±7.1. Last measured 8 Sept 2026. Released 2 Jun 2026.
- Blended price
- $1.13/M
- $0.500 in · $3.00 out
- Output speed
- 56 tok/s
- First answer
- 38 s
- first token 0.80 s
- Context
- 1M
- Overall index60
- Reasoning64
- Coding47
- Agents & tools45
- Maths65
- Knowledge65
- Instruction following75
- Human preference65
- Multimodal64
- Long context63
- Composite62
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 | – | – | 56 tok/s | 38 s | $0.0011 | Maths 51 · Reasoning 60 |
| defaultbest | 59.7 | #97 | 56 tok/s | 38 s | $0.0011 | Agents & tools 45 · Coding 47 · Composite 62 · Human preference 65 · Instruction following 75 · Knowledge 65 · Long context 63 · Maths 65 · Multimodal 64 · Reasoning 64 |
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 | 81.8%#105 | 87.9%#53 | Epoch AI Benchmarking Hub | |
| LMArena Hard Prompts | – | 1473#66 | LMArena | |
| GPQA Diamond (AA)not in index | – | 90.0%#66 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | – | 35.6%#78 | Artificial Analysis |
Coding
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| SciCode | – | 45.5%#84 | SciCode | |
| FrontierCode | – | 10.2%#27 | Cognition | |
| LMArena Coding | – | 1500#62 | LMArena | |
| SciCode (AA)not in index | – | 46.1%#87 | Artificial Analysis |
Agents & tools
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| OSWorld-Verified 2.0 | – | 2.8%#14 | OSWorld | |
| LMArena Agent | – | -5.2#32 | LMArena | |
| Terminal-Bench Hard | – | 47.0%#27 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | – | 93.0%#47 | Artificial Analysis | |
| Terminal-Bench 2.1 (Vals) | – | 52.8%#46 | Vals AI |
Maths
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| FrontierMath Tiers 1–3 | 34.4%#53 | – | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | 80.0%#99 | 93.3%#44 | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| AA-Omniscience | – | 1.1#86 | Artificial Analysis |
Instruction following
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| IFBench | – | 78.0%#14 | Artificial Analysis |
Human preference
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| LMArena Text | – | 1455#59 | LMArena |
Multimodal
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| LMArena Vision | – | 1281#26 | LMArena | |
| MMMU-Pro | – | 80.5%#33 | Artificial Analysis |
Long context
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| AA-LCR | – | 73.0%#132 | Artificial Analysis |
Composite
| Benchmark | no reasoning | default | Source | Trend |
|---|---|---|---|---|
| Epoch Capabilities Indexnot in index | – | 147.4#54 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index | – | 25.8#111 | Artificial Analysis | |
| Vals Indexnot in index | – | 38.6#37 | Vals AI |
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. | 13 tok/s | 0.80 s | $0.320 | $1.28 | 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 at $0.050 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0011 | $0.0010 | 43.1 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0078 | $0.0038 | 48.4 s |
| Code edit | 6,000 / 1,500 | $0.0075 | $0.0055 | 1.1 min |
| Agentic coding session | 60,000 / 4,000 | $0.042 | $0.022 | 1.8 min |
| Structured extraction | 2,000 / 200 | $0.0016 | $0.0009 | 41.3 s |
See also
Data as of 9 Sept 2026. Compare these configurations.