QwQ-32B-Preview
QwQ-32B-Preview.
Qwen Released 28 Nov 2024 13
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Nov 2024 QwQ-32B-Preview
Open weights
No Epoch Capabilities Index score yet
- Vectara Hallucination Leaderboard (HHEM) 16.1% #8 /148
- BigCodeBench-Hard 26.7% #33 /96
- LLM-AggreFact 71.8% #6 /6
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 | |
|---|---|---|---|---|
| Vectara Hallucination Leaderboard (HHEM) | 16.1% | #8 of 148 | Official leaderboard | |
| MMLU-Pro | 71% | #84 of 212 | Official leaderboard | |
| SuperGPQA | 43.6% | #31 of 58 | Official leaderboard | |
| LMArena (Elo) | 1,154 | #303 of 333 | Official leaderboard | |
| LLM-AggreFact | 71.8% | #6 of 6 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| U-MATH | 73.1% | #6 of 30 | Official leaderboard | |
| ForecastBench | 62.1 | #35 of 86 | Official leaderboard | |
| AIME 2025 | 33.3% | #48 of 53 | Official leaderboard | |
| HMMT 2025 | 18.3% | #48 of 53 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BigCodeBench | 49.5% | #23 of 69 | Official leaderboard | |
| BigCodeBench-Hard | 26.7% | #33 of 96 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Step Race | 1 | #44 of 59 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveBench | 40.3% | #39 of 48 | Epoch AI |