Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
qwen3-235b-a22b-thinking-2507
parasail
Context262144 tokens
Input Price$0.65 / 1M tokens
Output Price$3 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.65 / 1M tokens | $2 / 1M tokens |
| Output Price | $3 / 1M tokens | $8 / 1M tokens |
Capabilities | ||
| Context Window | 262144 tokens | 1047576 tokens |
| Capabilities | tools | tools |
| Input type | text | text, image |
Category Scores | ||
| Overall Average | 47.2 | 56.8 |
| Academia | 45.6 | 54.9 |
| Finance | 45.6 | 55.5 |
| Marketing | 48.0 | 54.4 |
| Maths | 61.4 | 67.5 |
| Programming | 32.1 | 41.9 |
| Science | 61.3 | 66.5 |
| Writing | 36.5 | 39.2 |
| Vision | N/A | 74.8 |
Benchmark Tests | ||
| AIME | 32.7 | 43.7 |
| AA Coding Index | 32.1 | 41.9 |
| AAII | 29.9 | 43.4 |
| AA Math Index | 61.4 | 67.5 |
| GPQA | 61.3 | 66.5 |
| HLE | 4.7 | 4.6 |
| LiveCodeBench | 34.3 | 45.7 |
| MATH-500 | 90.2 | 91.3 |
| MMLU | 87.8 | 90.2 |
| MMLU-Pro | 76.2 | 80.6 |
| MMMU | _ | 74.8 |
| SciCode | 29.9 | 38.1 |
qwen3-235b-a22b-thinking-2507 Advantages
- • Lower input token cost ($0.65 / 1M tokens vs $2 / 1M tokens)
gpt-4.1 Advantages
- • Higher benchmark scores (56.8 vs 47.2)
- • Larger context window (1047576 tokens vs 262144 tokens)