qwen3-4b-instruct-2507
qwen3-4b-instruct-2507.
Released August 6th, 2025 Compare with others
15
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Unknown lab Aug 2025
qwen3-4b-instruct-2507
No Epoch Capabilities Index score yet
- GPQA Diamond 45.8% #175 /229
- Encyclo-K 28.6% #14 /23
- AlGhafa 36.5% #35 /39
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ALRAGE | 79.1% | #9 of 39 | Official leaderboard | |
| Encyclo-K | 28.6% | #14 of 23 | Official leaderboard | |
| ArabicMMLU | 31.7% | #31 of 39 | Official leaderboard | |
| Open Arabic LLM Leaderboard v2 | 36.9% | #32 of 39 | Official leaderboard | |
| Wer wird Millionär? LLM Benchmark | 109.0 | #69 of 77 | Official leaderboard | |
| AlGhafa | 36.5% | #35 of 39 | Official leaderboard | |
| ArbMMLU-HT | 23.5% | #36 of 39 | Official leaderboard | |
| ConStory-Bench | 1.69 | #13 of 14 | Official leaderboard | |
| MadinahQA | 25.1% | #37 of 39 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 52.2% | #134 of 212 | Epoch AI run | |
| GPQA Diamond | 45.8% | #175 of 229 | Epoch AI run |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BFCL V4 | 35.7% | #34 of 65 | Official leaderboard |
Professional work
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AraTrust | 40.6% | #33 of 39 | Official leaderboard |