Model comparison
Llama-3.3-70B-Instruct vs Qwen2-72B
Llama-3.3-70B-Instruct and Qwen2-72B score almost the same on the Noometry Index (30.6 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 24 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 6 categories and Qwen2-72B in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 30.2 to 15.3.
- The biggest single-benchmark swing is BigCodeBench Instruct: 46.9% for Llama-3.3-70B-Instruct and 38.5% for Qwen2-72B.
Side by side
| Llama-3.3-70B-Instruct | Qwen2-72B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.6 | 30.0 |
| Released | 2024-12-06 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.32 | — |
| Results tracked | 43 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 31.0 (#290), Qwen2-72B: 29.1 (#310)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2-72B |
|---|---|---|
| WeirdML | 14.4% | 11.3% |
| BigCodeBench Instruct | 46.9% | 38.5% |
| LMArena Coding | 1268 | 1196 |
| BigCodeBench Complete | 57.5% | 54% |
| SciCode | 26% | — |
| LiveBench Coding | 36.6% | — |
Agentic & Tool Use Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 25.8 (#105), Qwen2-72B: 17.0 (#146)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 31.9% | — |
| TheAgentCompany | — | 1.1% |
| BALROG | 23% | — |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Llama-3.3-70B-Instruct: 14.1 (#327), Qwen2-72B: 23.2 (#181)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1191 |
| Epoch Capabilities Index | 127.33 | 125.28 |
| SimpleBench | 19.9% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 50.8% | — |
| DTBench | 59.5% | — |
| LiveBench Data Analysis | 49.5% | — |
| LMCA | 17.5% | — |
| ForecastBench | 58.6 | — |
| LiveBench | 50.2% | — |
Math Qwen2-72B leads
Llama-3.3-70B-Instruct: 15.3 (#298), Qwen2-72B: 30.2 (#236)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2-72B |
|---|---|---|
| LMArena Math | 1267 | 1235 |
| MATH Level 5 | 41.6% | 39.1% |
| OTIS Mock AIME 2024-2025 | 5.1% | — |
| LiveBench Math | 42.2% | — |
Knowledge Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 30.6 (#226), Qwen2-72B: 21.2 (#275)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 47.4% | 40.8% |
| LMArena Expert | 1225 | 1171 |
| MMLU | 86.3% | 82.4% |
| Confabulations | 22.8% | — |
| Vectara Hallucination Rate | 4.1% | — |
Multilingual Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 39.9 (#220), Qwen2-72B: 35.9 (#244)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1236 | 1176 |
| LMArena Chinese | 1217 | 1240 |
| LMArena French | 1281 | 1170 |
| LMArena German | 1251 | 1151 |
| LMArena Japanese | 1150 | 1111 |
| LMArena Korean | 1143 | 1083 |
| LMArena Russian | 1252 | 1169 |
| LMArena Spanish | 1270 | 1169 |
Instruction Following Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 71.1 (#157), Qwen2-72B: 61.7 (#241)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1242 | 1181 |
| LiveBench Instruction Following | 82.7% | — |
Long Context Qwen2-72B leads
Llama-3.3-70B-Instruct: 26.4 (#295), Qwen2-72B: 36.1 (#235)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1256 | 1192 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 47.6 (#207), Qwen2-72B: 40.8 (#241)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2-72B |
|---|---|---|
| LMArena Text | 1274 | 1203 |
| LMArena Creative Writing | 1250 | 1181 |
| LMArena Multi-Turn | 1280 | 1196 |
| LiveBench Language | 39.2% | — |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than Qwen2-72B?
Llama-3.3-70B-Instruct and Qwen2-72B score almost the same on the Noometry Index (30.6 vs 30.0), so choose on price, context window or the category you care about most.
Is Llama-3.3-70B-Instruct or Qwen2-72B better for coding?
Llama-3.3-70B-Instruct scores higher on coding benchmarks: 31.0 versus 29.1 in the Noometry coding category.
How many benchmarks do Llama-3.3-70B-Instruct and Qwen2-72B share?
24 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Qwen2-72B has 26.