Qwen3 30B-A3B Instruct 2507 scores 11.5 on the Respan Index (#134), ahead of GPT-4o mini at 8.8 (#136). Qwen3 30B-A3B Instruct 2507 leads on 4 of the 4 benchmarks both report. GPT-4o mini is 1.3x cheaper per token at list price. Qwen3 30B-A3B Instruct 2507 has the larger context window (262K tokens).
| Benchmark | GPT-4o mini | Qwen3 30B-A3B Instruct 2507 |
|---|---|---|
| Chess Puzzles (Epoch AI) | 0% | 2% |
| GPQA Diamond | 40.2% | 55.6% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 6.9% | 62.2% |
| LMArena Elo | 1318 | 1383 |
Higher is better. Each score links to where it was published.
* Estimated: no published scores in that category. How the Respan Index works