Qwen3 A235 A22B Instruct 2507
Qwen
Highlights
Top benchmark results for qwen/qwen3-a235-a22b-instruct-2507-2025-07-21.
0.57#16
0.70#23
0.42#10
0.84#1
0.78#26
0.55#7
0.89#2
0.75#3
0.52#4
0.93#2
0.83#3
0.54#2
0.63#2
0.44#5
0.71#3
0.95#1
Benchmark table
Detailed scores across tracked benchmarks.
| Benchmark | Category | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|
| Aider-Polyglot | code | 0.57 | - | Yes | Source |
| AIME 2025 | math | 0.70 | - | Yes | Source |
| ARC-AGI-1 | - | 0.42 | NOT confirmed by Arc-AGI | Yes | Source |
| CSimpleQA | - | 0.84 | - | Yes | Source |
| GPQA Diamond | general-knowledge | 0.78 | - | Yes | Source |
| HMMT 2025 | - | 0.55 | - | Yes | Source |
| IFEval | - | 0.89 | - | Yes | Source |
| LiveBench | - | 0.75 | 2024-11-25 | Yes | Source |
| LiveCodeBench V6 | - | 0.52 | - | Yes | Source |
| MMLU Redux | - | 0.93 | - | Yes | Source |
| MMLU-Pro | - | 0.83 | - | Yes | Source |
| Multi‑Programming Language Evaluation | - | 0.88 | - | Yes | Source |
| SimpleQA | - | 0.54 | - | Yes | Source |
| SuperGPQA | - | 0.63 | - | Yes | Source |
| Tau Bench (Airline) | - | 0.44 | - | Yes | Source |
| Tau Bench (Retail) | - | 0.71 | - | Yes | Source |
| ZebraLogic | - | 0.95 | - | Yes | Source |
Benchmark comparisons
Use the selector to switch benchmarks and see how this model stacks up against its closest competitors.
Aider-Polyglot
Compare this model with the leading peers for the selected benchmark.
Benchmark
0.57
Rank #16/34
34 models
Showing 11 models around the selected model (out of 34 total).