Compare / Qwen3 30B A3B Instruct 2507 vs GPT-5 Mini
Qwen3 30B A3B Instruct 2507 vs GPT-5 Mini
21 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Qwen3 30B A3B Instruct 2507 | GPT-5 Mini |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,397 | 1,381 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,319 | 1,324 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,395 | 1,400 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,366 | 1,373 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,383 | 1,390 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,342 | 1,352 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 7.50 | 20.6 |
| Artificial Analysisreported | GPQA Diamond% of questions | 65.9% | 82.8% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 6.9% | 21.5% |
| Artificial Analysisreported | IFBench% of instructions | 33.1% | 75.4% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 26.3% | 72.3% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 6.1% | 33.3% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 10.2% | 71.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 79.9% | 91.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 17.6% | 44.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 30.0% | 27.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 41.4% | 55.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 93.8% | 93.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 88.9% | 69.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 78.4% | 62.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 22.5% | 82.0% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.