Qwen3 30B A3B Instruct 2507open
Alibaba
40.9#251 of 427 overall
- Input / output
- US$ 0,10 / US$ 0,30 US$ per 1M tokens
- Context
- 262K tokens
- Release
- 07/29/2025 release date
- Speed
- 0 tok/s first token in 0.00 s
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| Arena text (Elo) weight 2 | 1384 | 40% | LMArena |
| Humanity's Last Exam weight 1 | 10.3 | 52% | Artificial Analysis |
| Terminal-Bench weight 1 | 0.0 | 22% | Artificial Analysis |
| GPQA Diamond | 70.7 | 51% | Artificial Analysis |
| Long-context reasoning | 61.3 | 52% | Artificial Analysis |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Agentic | 36.0 | #113 | Terminal-Bench |
| Reasoning | 50.9 | #208 | Humanity's Last Exam, GPQA Diamond |
| Research | 50.8 | #169 | Long-context reasoning |
| Chat | 45.1 | #118 | Arena text (Elo) |
History
RankingIA score on each collection day (hover to see the rank).
Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.