Qwen3-4B-Thinking-2507
Qwen3-4B-Thinking-2507.
8
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Aug 2025 Qwen3-4B-Thinking-2507
Open weights Small
No Epoch Capabilities Index score yet
- MathArena (Apex, IMO, USAMO) 2.08% #30 /47
- KINA 24.8% #29 /37
- Encyclo-K 33.5% #10 /23
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 | |
|---|---|---|---|---|
| Encyclo-K | 33.5% | #10 of 23 | Official leaderboard | |
| Wer wird Millionär? LLM Benchmark | 238.0 | #58 of 77 | Official leaderboard | |
| KINA | 24.8% | #29 of 37 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MathArena (Apex, IMO, USAMO) | 2.08% | #30 of 47 | Official leaderboard | |
| AIME 2026 | 82.5% | #30 of 31 | Official leaderboard | |
| MathArena Apex Shortlist | 16.5% | #38 of 38 | Official leaderboard | |
| HMMT 2026 | 53% | #31 of 31 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BRIDGE | 47.0 | #18 of 39 | Official leaderboard |