Across 1 comparable benchmark, Qwen3.5-27B has better reported results on 1 and worse on 0.
Limited evidence1 of 1 shared result countedHow we compare
Price basis: Listed rates vs listed rates. The price section below shows the applicable periods.
| Fact | Qwen-72B | Qwen3.5-27B |
|---|---|---|
| Context window | 32K tokens | 1M tokens |
| Input / 1M | — | $0.300 |
| Output / 1M | — | $2.40 |
| Blended (4:1) | — | $0.720 |
| Status | Available | Available |
| Released | November 30, 2023 | February 25, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Published scores, with matching modes where available. Gaps show Qwen-72B relative to Qwen3.5-27B. Reading the results
| Benchmark | Qwen-72B | Qwen3.5-27B | Gap |
|---|---|---|---|
| C-EvalKnowledge Exams · Accuracy | 83.3Historical | 90.5≠Thinking · no tools | −7.2 pts#11 vs #6 of 47 |
Knowledge Exams · Accuracy
A dash means no result is available.
| Benchmark | Qwen-72B | Qwen3.5-27B |
|---|---|---|
| AGIEval | 62.5 | — |
| AIME 2026 | — | 91.7 |
| CritPt | — | 0.9 |
| GPQA Diamond | — | 85.5 |
| GSM8K | 78.9 | — |
| HLE | — | 48.5 |
| MMLU | 77.4 | — |
| MMLU-Pro | — | 86.1 |
| CodeForces | — | 1899 |
| HumanEval | 35.4 | — |
| LiveCodeBench | — | 80.7 |
| MBPP | 52.2 | — |
| SWE-bench Verified | — | 72.4 |
| Terminal Bench 2.0 | — | 41.6 |
| Terminal Bench Hard | — | 32.6 |
| Claw Bench | — | 75.2 |
| OSWorld-Verified | — | 56.2 |
| Pinch Bench | — | 90.0 |
| IF Bench | — | 76.5 |
| Context Arena | — | 73.3 |
| LongBench v2 | — | 60.6 |
| MMMU | — | 82.3 |
| MMMU-Pro | — | 75.0 |
| SimpleVQA | — | 56.0 |
| τ²-Bench | — | 79.0 |
| Vending-Bench 2 | — | 202 |
| BrowseComp | — | 61.0 |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
A blended cost needs a published input and output price on both sides, and one of these two does not have them yet.
Qwen-72B: Listed text rates; pricing tier not confirmed.
Qwen3.5-27B: International pricing. context_length <= 256000 Alibaba Model Studio International (Singapore)
| Price / 1M tokens | Qwen-72B | Qwen3.5-27B | Ratio |
|---|---|---|---|
| Input | — | $0.30 | — |
| Output | — | $2.40 | — |
| Cached input | — | — | — |
| Cache write | — | — | — |
| Blended | — | $0.72 | — |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Benchmark | Qwen-72B | Qwen3.5-27B |
|---|---|---|
| AIME 2026 | Not reported |
| Attribute | Qwen-72B | Qwen3.5-27B |
|---|---|---|
| Availability | Available | Available |
| Provider | Alibaba | Alibaba |
| Model type | Foundation model | Reasoning model |
| First release | November 30, 2023 | February 25, 2026 |
| Context window | 32K tokens | 1M tokens |
| Max output | — | 248K tokens |
| Total parameters | 72B | 27B |
| Active parameters | — | 27B |
| Architecture | Dense | Dense |
| Documented capabilities | Multilingual | Reasoning, Multilingual |
| Input modalities | — | Text, Image, Video |
| Output modalities | — | Text |
| Weights | Open weights | Open weights |
| Licence | Tongyi Qianwen RESEARCH LICENSE AGREEMENT | Qwen License |
| Commercial use | Commercial use allowed | Commercial use allowed |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Qwen-72B or Qwen3.5-27B? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.