Qwen3 30B A3B 2507 Instruct
AlibabaQwen
Release Date
2025-07-29
Parameters
—
Context Length
262K
Modalities
text
Capability Radar
33
general
29
coding
73
reasoning
42
scienceest.
0
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 274 | 29.0 | AA |
| General Ranking | 340 | 33.0 | AA |
| Math Reasoning | 103 | 75.0 | AA |
| Science | 240 | 44.0 | AA |
Benchmark Scores (LLM Stats)
No benchmark data available
AA Evaluation Indices
Math Index66.3
Intelligence Index15.0
Coding Index14.2
Math 5001.0
Mmlu Pro0.8
Aime0.7
Aime 250.7
Gpqa0.7
Livecodebench0.5
Ifbench0.3
Scicode0.3
Lcr0.2
Tau20.1
Hle0.1
Terminalbench Hard0.1
LLM Stats Category Scores
No category score data available
Pricing
Input Price$0.15 / 1M tokens
Output Price$0.4 / 1M tokens
Blended Price (3:1)$0.213 / 1M tokens
Speed
Tokens/sec106.1 tokens/s
Time to First Token1.04s
Time to Answer1.04s
Available Providers
(LS internal units)No provider data available
External Sources
No external links available