BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database

Qwen3 4B 2507 Instruct

MODEL RECORD: QWEN-QWEN34B2507INSTRUCT

Organization
Qwen
Family
QWEN34B2507INSTRUCT
Model number
Unknown
Tier
Unknown
Status
ACTIVE
Release date
2025-08-06

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-007QWEN34B2507INSTRUCT-001 Qwen3 4B 2507 Instruct Artificial Analysis Intelligence Index Overall 7.1 Unknown Primary source QWEN-QWEN34B2507INSTRUCT
BR-007QWEN34B2507INSTRUCT-002 Qwen3 4B 2507 Instruct GPQA Diamond Accuracy 51.7% Unknown Primary source QWEN-QWEN34B2507INSTRUCT
BR-007QWEN34B2507INSTRUCT-003 Qwen3 4B 2507 Instruct Humanity's Last Exam No tools Overall 4.7% Unknown Primary source QWEN-QWEN34B2507INSTRUCT
BR-007QWEN34B2507INSTRUCT-004 Qwen3 4B 2507 Instruct SciCode Overall 18.1% Unknown Primary source QWEN-QWEN34B2507INSTRUCT
BR-007QWEN34B2507INSTRUCT-005 Qwen3 4B 2507 Instruct tau2-bench Overall 26.6% Unknown Primary source QWEN-QWEN34B2507INSTRUCT
BR-007QWEN34B2507INSTRUCT-006 Qwen3 4B 2507 Instruct Terminal-Bench Hard Overall 4.5% Unknown Primary source QWEN-QWEN34B2507INSTRUCT
BR-007QWEN34B2507INSTRUCT-007 Qwen3 4B 2507 Instruct CritPt Overall 0% Unknown Primary source QWEN-QWEN34B2507INSTRUCT
BR-007QWEN34B2507INSTRUCT-008 Qwen3 4B 2507 Instruct AA-Omniscience Overall -59.6 Unknown Primary source QWEN-QWEN34B2507INSTRUCT
BR-007QWEN34B2507INSTRUCT-009 Qwen3 4B 2507 Instruct AA-Omniscience Accuracy 10.3% Unknown Primary source QWEN-QWEN34B2507INSTRUCT
BR-007QWEN34B2507INSTRUCT-010 Qwen3 4B 2507 Instruct IFBench Overall 33.5% Unknown Primary source QWEN-QWEN34B2507INSTRUCT
BR-007QWEN34B2507INSTRUCT-011 Qwen3 4B 2507 Instruct AA-LCR Overall 7.3% Unknown Primary source QWEN-QWEN34B2507INSTRUCT