Model comparison
Qwen3.8 27B vs Sonar
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 38.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
PerplexitySummary
- The widest gap is in reasoning, where Qwen3.8 27B leads 41.0 to 21.1.
- Qwen3.8 27B is cheaper at $0.04 / $2.30 per million input/output tokens, against $1 / $1 for Sonar.
- Qwen3.8 27B accepts more context: 262K tokens versus 128K.
- Qwen3.8 27B has downloadable open weights; the other is API-only.
Side by side
| Qwen3.8 27B | Sonar | |
|---|---|---|
| Provider | Alibaba (Qwen) | Perplexity |
| Noometry Index | 46.0 | 38.5 |
| Released | 2026-08-14 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 262K | 128K |
| Max output | 33K | 4K |
| Input $ / M tokens | $0.04 | $1 |
| Output $ / M tokens | $2.30 | $1 |
| Results tracked | 31 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Qwen3.8 27B: 50.5 (#44), Sonar: 35.7 (#221)
| Benchmark | Qwen3.8 27B | Sonar |
|---|---|---|
| LMArena WebDev | 1593 | — |
| SciCode | 46.6% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1482 | — |
Agentic & Tool Use Not comparable
Qwen3.8 27B: 32.9 (#57), Sonar: —
| Benchmark | Qwen3.8 27B | Sonar |
|---|---|---|
| APEX-Agents | 47.5% | — |
Reasoning Qwen3.8 27B leads
Qwen3.8 27B: 41.0 (#54), Sonar: 21.1 (#227)
| Benchmark | Qwen3.8 27B | Sonar |
|---|---|---|
| ARC-AGI-2 | 42.4% | — |
| NYT Connections (extended) | 54.5% | — |
| ARC-AGI-1 | 87.5% | — |
| CritPt | 5.4% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1460 | — |
| DTBench | 88% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 41.4% | — |
| Surface Evolver Bench | 45% | — |
| Epoch Capabilities Index | 149.38 | — |
| LiveBench | — | 46.9% |
Math Qwen3.8 27B leads
Qwen3.8 27B: 37.1 (#161), Sonar: 33.7 (#200)
| Benchmark | Qwen3.8 27B | Sonar |
|---|---|---|
| ProofBench | 16% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1456 | — |
Knowledge Not comparable
Qwen3.8 27B: 41.6 (#109), Sonar: —
| Benchmark | Qwen3.8 27B | Sonar |
|---|---|---|
| LMArena Expert | 1482 | — |
Multimodal Not comparable
Qwen3.8 27B: 41.3 (#37), Sonar: —
| Benchmark | Qwen3.8 27B | Sonar |
|---|---|---|
| LMArena Vision | 1271 | — |
Multilingual Not comparable
Qwen3.8 27B: 53.7 (#60), Sonar: —
| Benchmark | Qwen3.8 27B | Sonar |
|---|---|---|
| LMArena Non-English | 1430 | — |
| LMArena Chinese | 1504 | — |
| LMArena French | 1465 | — |
| LMArena German | 1438 | — |
| LMArena Japanese | 1384 | — |
| LMArena Korean | 1393 | — |
| LMArena Russian | 1415 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Qwen3.8 27B leads
Qwen3.8 27B: 75.8 (#53), Sonar: 71.4 (#150)
| Benchmark | Qwen3.8 27B | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1439 | — |
Long Context Not comparable
Qwen3.8 27B: 44.3 (#70), Sonar: —
| Benchmark | Qwen3.8 27B | Sonar |
|---|---|---|
| LMArena Longer Query | 1450 | — |
Writing & Preference Qwen3.8 27B leads
Qwen3.8 27B: 65.8 (#43), Sonar: 52.6 (#167)
| Benchmark | Qwen3.8 27B | Sonar |
|---|---|---|
| LMArena Text | 1441 | — |
| LMArena Creative Writing | 1384 | — |
| EQ-Bench Creative Writing | 1671 | — |
| LMArena Multi-Turn | 1441 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Qwen3.8 27B better than Sonar?
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 38.5 on the Noometry Index.
Which is cheaper, Qwen3.8 27B or Sonar?
Qwen3.8 27B is cheaper. It lists at $0.04 per million input tokens and $2.30 per million output tokens; Sonar lists at $1 and $1.
Is Qwen3.8 27B or Sonar better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 27B does, with 262K tokens against 128K.
How many benchmarks do Qwen3.8 27B and Sonar share?
0 benchmarks have published results for both models. Qwen3.8 27B has 31 scored results on Noometry and Sonar has 7.