GPT-5 mini vs Qwen3-Max
| Spec | GPT-5 mini | Qwen3-Max |
|---|---|---|
| Respan Index | 20.0 (#119) | 19.9 (#120) |
| Blended price per 1M | $0.688 | - |
| Context window | 400K | 262K |
| Input / output per 1M | $0.25 / $2 | - |
| Max output | 128K | - |
| Input | text, vision | text |
| Released | 2025-08-07 | 2025-09-23 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | GPT-5 mini | Qwen3-Max |
|---|---|---|
| Coding | 9.3 GPT-5 mini | 5.4 Qwen3-Max |
| Agents | 4.9 GPT-5 mini | 5.8 Qwen3-Max |
| Reasoning | 31.2 GPT-5 mini | 20.3 Qwen3-Max |
| Knowledge & language | 21.6 GPT-5 mini | 48.4 Qwen3-Max |
| Human preference | 43.4 GPT-5 mini | 47.9 Qwen3-Max |
Benchmarks both report
GPT-5 mini leads on 7 of the 10 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GPT-5 mini | Qwen3-Max |
|---|---|---|
| Chess Puzzles (Epoch AI) | 24% | 4% |
| LMArena Elo | 1390 | 1423 |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 46.7% | 18.9% |
| GPQA Diamond | 81.6% | 72.6% |
| MATH Level 5 (Epoch AI) | 97.8% | 97.1% |
| Mystery Game Puzzles (Epoch AI) | 10% | 5% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 86.7% | 73.3% |
| SimpleQA Verified | 21.6% | 48.7% |
| Vending-Bench 2 (Andon Labs) | -31.18 | 71.57 |
| SWE-bench Verified | 71% | 69.6% |
FAQ
Is GPT-5 mini better than Qwen3-Max?
GPT-5 mini scores 20.0 on the Respan Index (#119), ahead of Qwen3-Max at 19.9 (#120). GPT-5 mini leads on 7 of the 10 benchmarks both report.
Which has the larger context window?
GPT-5 mini accepts 400K tokens and Qwen3-Max 262K tokens.