Model comparison
Llama 3.1-8B vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.4 to 22.8 on the Noometry Index.
Last verified . 24 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. Llama 3.1-8B scores higher in 0 categories and QwQ-32B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where QwQ-32B leads 37.2 to 8.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.7% for Llama 3.1-8B and 59.2% for QwQ-32B.
Side by side
| Llama 3.1-8B | QwQ-32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 22.8 | 39.4 |
| Released | 2024-07-23 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 43 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding QwQ-32B leads
Llama 3.1-8B: 19.9 (#335), QwQ-32B: 34.9 (#220)
| Benchmark | Llama 3.1-8B | QwQ-32B |
|---|---|---|
| BigCodeBench Instruct | 32.8% | 44.6% |
| LMArena Coding | 1195 | 1333 |
| BigCodeBench Complete | 40.5% | 54.4% |
| Aider Polyglot | — | 20.9% |
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
| LiveBench Coding | — | 72.2% |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Not comparable
Llama 3.1-8B: 22.3 (#123), QwQ-32B: —
| Benchmark | Llama 3.1-8B | QwQ-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| BALROG | 15.1% | — |
Reasoning QwQ-32B leads
Llama 3.1-8B: 14.5 (#316), QwQ-32B: 22.9 (#171)
| Benchmark | Llama 3.1-8B | QwQ-32B |
|---|---|---|
| Chess Puzzles | 0% | 5% |
| LMArena Hard Prompts | 1175 | 1326 |
| Epoch Capabilities Index | 116.48 | 137.6 |
| CritPt | 0% | — |
| LiveBench Reasoning | — | 83.5% |
| DTBench | 50.9% | — |
| LiveBench Data Analysis | — | 65% |
| LMCA | 5.4% | — |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
| PIQA | 81.2% | — |
Math QwQ-32B leads
Llama 3.1-8B: 9.5 (#311), QwQ-32B: 36.2 (#123)
| Benchmark | Llama 3.1-8B | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.7% | 59.2% |
| LMArena Math | 1179 | 1359 |
| Omni-MATH | 13.7% | — |
| LiveBench Math | — | 77.8% |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |
Knowledge QwQ-32B leads
Llama 3.1-8B: 8.0 (#302), QwQ-32B: 37.2 (#150)
| Benchmark | Llama 3.1-8B | QwQ-32B |
|---|---|---|
| GPQA Diamond | 27% | 65.3% |
| LMArena Expert | 1144 | 1323 |
| MMLU-Pro | 40.6% | — |
| Confabulations | — | 15.6% |
| GPQA (HELM) | 24.7% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multilingual QwQ-32B leads
Llama 3.1-8B: 34.2 (#244), QwQ-32B: 45.0 (#171)
| Benchmark | Llama 3.1-8B | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1148 | 1306 |
| LMArena Chinese | 1151 | 1378 |
| LMArena French | 1176 | 1337 |
| LMArena German | 1144 | 1313 |
| LMArena Japanese | 1061 | 1263 |
| LMArena Korean | 1053 | 1278 |
| LMArena Russian | 1158 | 1297 |
| LMArena Spanish | 1169 | 1353 |
Instruction Following QwQ-32B leads
Llama 3.1-8B: 59.1 (#253), QwQ-32B: 72.8 (#131)
| Benchmark | Llama 3.1-8B | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1159 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
| IFEval | 74.3% | — |
Long Context QwQ-32B leads
Llama 3.1-8B: 35.8 (#233), QwQ-32B: 49.0 (#11)
| Benchmark | Llama 3.1-8B | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1182 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference QwQ-32B leads
Llama 3.1-8B: 29.9 (#285), QwQ-32B: 50.9 (#175)
| Benchmark | Llama 3.1-8B | QwQ-32B |
|---|---|---|
| LMArena Text | 1187 | 1329 |
| LMArena Creative Writing | 1154 | 1288 |
| EQ-Bench Creative Writing | 713 | 1257 |
| LMArena Multi-Turn | 1172 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| WildBench | 68.7% | — |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Llama 3.1-8B better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.4 to 22.8 on the Noometry Index.
Is Llama 3.1-8B or QwQ-32B better for coding?
QwQ-32B scores higher on coding benchmarks: 34.9 versus 19.9 in the Noometry coding category.
How many benchmarks do Llama 3.1-8B and QwQ-32B share?
24 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and QwQ-32B has 36.