Model comparison
Llama-3.3-70B-Instruct vs Qwen1.5-72B
Llama-3.3-70B-Instruct and Qwen1.5-72B score almost the same on the Noometry Index (30.3 vs 30.3), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 4 categories and Qwen1.5-72B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama-3.3-70B-Instruct leads 30.5 to 11.5.
- The biggest single-benchmark swing is GPQA Diamond: 47.4% for Llama-3.3-70B-Instruct and 28.8% for Qwen1.5-72B.
Side by side
| Llama-3.3-70B-Instruct | Qwen1.5-72B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.3 | 30.3 |
| Released | 2024-12-06 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.32 | — |
| Results tracked | 43 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama-3.3-70B-Instruct: 30.6 (#284), Qwen1.5-72B: 31.4 (#272)
| Benchmark | Llama-3.3-70B-Instruct | Qwen1.5-72B |
|---|---|---|
| BigCodeBench Instruct | 46.9% | 33.2% |
| LMArena Coding | 1268 | 1166 |
| BigCodeBench Complete | 57.5% | 40.3% |
| SciCode | 26% | — |
| WeirdML | 14.4% | — |
| LiveBench Coding | 36.6% | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Agentic & Tool Use Not comparable
Llama-3.3-70B-Instruct: 25.6 (#100), Qwen1.5-72B: —
| Benchmark | Llama-3.3-70B-Instruct | Qwen1.5-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 31.9% | — |
| BALROG | 23% | — |
Reasoning Qwen1.5-72B leads
Llama-3.3-70B-Instruct: 13.7 (#325), Qwen1.5-72B: 21.2 (#201)
| Benchmark | Llama-3.3-70B-Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1148 |
| SimpleBench | 19.9% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 50.8% | — |
| DTBench | 59.5% | — |
| LiveBench Data Analysis | 49.5% | — |
| LMCA | 17.5% | — |
| Epoch Capabilities Index | 127.32 | — |
| ForecastBench | 58.6 | — |
| LiveBench | 50.2% | — |
Math Qwen1.5-72B leads
Llama-3.3-70B-Instruct: 14.3 (#292), Qwen1.5-72B: 30.7 (#205)
| Benchmark | Llama-3.3-70B-Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1268 | 1164 |
| OTIS Mock AIME 2024-2025 | 5.1% | — |
| LiveBench Math | 42.2% | — |
| MATH Level 5 | 41.6% | — |
Knowledge Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 30.5 (#220), Qwen1.5-72B: 11.5 (#295)
| Benchmark | Llama-3.3-70B-Instruct | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | 47.4% | 28.8% |
| LMArena Expert | 1225 | 1136 |
| Confabulations | 22.8% | — |
| Vectara Hallucination Rate | 4.1% | — |
| MMLU | 86.3% | — |
Multilingual Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 40.1 (#215), Qwen1.5-72B: 33.4 (#248)
| Benchmark | Llama-3.3-70B-Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1236 | 1135 |
| LMArena Chinese | 1217 | 1186 |
| LMArena French | 1280 | 1158 |
| LMArena German | 1251 | 1084 |
| LMArena Japanese | 1149 | 1061 |
| LMArena Korean | 1142 | 1049 |
| LMArena Russian | 1252 | 1104 |
| LMArena Spanish | 1269 | 1110 |
Instruction Following Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 71.3 (#152), Qwen1.5-72B: 59.6 (#251)
| Benchmark | Llama-3.3-70B-Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1242 | 1142 |
| LiveBench Instruction Following | 82.7% | — |
Long Context Qwen1.5-72B leads
Llama-3.3-70B-Instruct: 26.4 (#290), Qwen1.5-72B: 35.0 (#238)
| Benchmark | Llama-3.3-70B-Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1256 | 1157 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 47.8 (#203), Qwen1.5-72B: 37.4 (#253)
| Benchmark | Llama-3.3-70B-Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1274 | 1166 |
| LMArena Creative Writing | 1250 | 1137 |
| LMArena Multi-Turn | 1279 | 1160 |
| LiveBench Language | 39.2% | — |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than Qwen1.5-72B?
Llama-3.3-70B-Instruct and Qwen1.5-72B score almost the same on the Noometry Index (30.3 vs 30.3), so choose on price, context window or the category you care about most.
Is Llama-3.3-70B-Instruct or Qwen1.5-72B better for coding?
They score almost the same on coding (30.6 vs 31.4); test both on your own repository before choosing.
How many benchmarks do Llama-3.3-70B-Instruct and Qwen1.5-72B share?
20 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Qwen1.5-72B has 22.