EBEasy BenchmarksLLM model index
Workspace
Overview
Benchmarks
Benchmarks list
Overall Index
Coding
Math
MMLU-Pro
Speed
Value
Models
All models
GPT-5.5 (xhigh)
GPT-5.5 (high)
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
Gemini 3.1 Pro Preview
GPT-5.4 (xhigh)
Artificial Analysis data
Back

Alibaba

Qwen3 30B A3B 2507 Instruct

Qwen3 30B A3B 2507 Instruct is a Alibaba language-model profile in the Easy Benchmarks snapshot. Use this page to compare its measured Artificial Analysis scores, output speed, time to first token, pricing, and relative ranking against other models in the local catalog.

Qwen model releases

Operational Metrics

Output Speed97.9 tok/s
First Token1.21s
Blended Price$0.350/M

Model Metadata

Queryable facts extracted from the upstream model payload.

ReleaseJul 29, 2025
Context Windown/a
Modalitiesn/a
API fields: release_date

Strength: MATH-500

Rank #23 across 201 models.

97.5%

Strength: AIME

Rank #34 across 194 models.

72.7%

Strength Profile

Percentile score by analysis domain.

* Cost is inverted: lower input, output, and blended prices rank higher.

Benchmark Percentiles

Higher bars mean stronger relative placement.

All Benchmarks

MetricDomainValueRank
Artificial Analysis Intelligence Indexoverall15.0#318
Artificial Analysis Coding Indexcoding14.2#254
Artificial Analysis Math Indexmath66.3#104
MMLU-Proreasoning77.7%#146
GPQA
reasoning
65.9%
#238
Humanity's Last Examreasoning6.8%#219
LiveCodeBenchcoding51.5%#144
SciCodecoding, reasoning30.4%#241
MATH-500math97.5%#23
AIMEmath72.7%#34
Output Speedspeed97.9 tok/s#123
Time to First Tokenspeed1.21s#173
Blended Pricecost$0.350/M#94
Input Pricecost$0.200/M#97
Output Pricecost$0.800/M#98
Value Indexcost, overall42.9#110