Model comparison
Qwen3 235B-A22B vs Sonar
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 37.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
PerplexitySummary
- The widest gap is in math, where Qwen3 235B-A22B leads 48.5 to 31.3.
- Sonar is cheaper at $1 / $1 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
- Qwen3 235B-A22B accepts more context: 131K tokens versus 128K.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| Qwen3 235B-A22B | Sonar | |
|---|---|---|
| Provider | Alibaba (Qwen) | Perplexity |
| Noometry Index | 43.2 | 37.8 |
| Released | 2025-04 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 131K | 128K |
| Max output | 16K | 4K |
| Input $ / M tokens | $0.70 | $1 |
| Output $ / M tokens | $2.80 | $1 |
| Results tracked | 49 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Qwen3 235B-A22B: 43.8 (#72), Sonar: 35.1 (#217)
| Benchmark | Qwen3 235B-A22B | Sonar |
|---|---|---|
| Aider Polyglot | 59.6% | — |
| SciCode | 42.4% | — |
| WeirdML | 41% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1445 | — |
Agentic & Tool Use Not comparable
Qwen3 235B-A22B: 33.7 (#48), Sonar: —
| Benchmark | Qwen3 235B-A22B | Sonar |
|---|---|---|
| Berkeley Function Calling Leaderboard | 52.1% | — |
| Vending-Bench 2 | -11.34 | — |
Reasoning Sonar leads
Qwen3 235B-A22B: 15.8 (#302), Sonar: 20.3 (#221)
| Benchmark | Qwen3 235B-A22B | Sonar |
|---|---|---|
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 11% | — |
| CritPt | 0% | — |
| Chess Puzzles | 12% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1433 | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 29.3% | — |
| Epoch Capabilities Index | 143.87 | — |
| ForecastBench | 59.7 | — |
| LiveBench | — | 46.9% |
Math Qwen3 235B-A22B leads
Qwen3 235B-A22B: 48.5 (#51), Sonar: 31.3 (#197)
| Benchmark | Qwen3 235B-A22B | Sonar |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| Omni-MATH | 71.8% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1431 | — |
| MATH Level 5 | 68.9% | — |
| FrontierMath (Feb 2025 set) | 8.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Not comparable
Qwen3 235B-A22B: 49.5 (#67), Sonar: —
| Benchmark | Qwen3 235B-A22B | Sonar |
|---|---|---|
| GPQA Diamond | 80.1% | — |
| SimpleQA Verified | 40.4% | — |
| MMLU-Pro | 84.4% | — |
| Confabulations | 15.6% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 72.7% | — |
| LMArena Expert | 1460 | — |
Multilingual Not comparable
Qwen3 235B-A22B: 52.5 (#84), Sonar: —
| Benchmark | Qwen3 235B-A22B | Sonar |
|---|---|---|
| LMArena Non-English | 1410 | — |
| LMArena Chinese | 1481 | — |
| LMArena French | 1445 | — |
| LMArena German | 1432 | — |
| LMArena Japanese | 1400 | — |
| LMArena Korean | 1391 | — |
| LMArena Russian | 1411 | — |
| LMArena Spanish | 1429 | — |
Instruction Following Qwen3 235B-A22B leads
Qwen3 235B-A22B: 72.8 (#132), Sonar: 71.5 (#146)
| Benchmark | Qwen3 235B-A22B | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| IFEval | 83.5% | — |
| LMArena Instruction Following | 1408 | — |
Long Context Not comparable
Qwen3 235B-A22B: 46.1 (#25), Sonar: —
| Benchmark | Qwen3 235B-A22B | Sonar |
|---|---|---|
| Fiction.LiveBench | 75% | — |
| LMArena Longer Query | 1426 | — |
Writing & Preference Qwen3 235B-A22B leads
Qwen3 235B-A22B: 59.8 (#103), Sonar: 52.6 (#166)
| Benchmark | Qwen3 235B-A22B | Sonar |
|---|---|---|
| LMArena Text | 1419 | — |
| LMArena Creative Writing | 1384 | — |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1366 | — |
| WildBench | 86.6% | — |
| LMArena Multi-Turn | 1432 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Qwen3 235B-A22B better than Sonar?
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 37.8 on the Noometry Index.
Which is cheaper, Qwen3 235B-A22B or Sonar?
Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.
Is Qwen3 235B-A22B or Sonar better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 43.8 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3 235B-A22B does, with 131K tokens against 128K.
How many benchmarks do Qwen3 235B-A22B and Sonar share?
0 benchmarks have published results for both models. Qwen3 235B-A22B has 49 scored results on Noometry and Sonar has 7.