Model comparison
Llama-3.3-70B-Instruct vs Qwen2.5 Plus 1127
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.8 to 30.6 on the Noometry Index.
Last verified . 14 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 1 category and Qwen2.5 Plus 1127 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5 Plus 1127 leads 36.1 to 15.3.
- Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.
Side by side
| Llama-3.3-70B-Instruct | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.6 | 38.8 |
| Released | 2024-12-06 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.32 | — |
| Results tracked | 43 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 Plus 1127 leads
Llama-3.3-70B-Instruct: 31.0 (#290), Qwen2.5 Plus 1127: 38.5 (#175)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1268 | 1314 |
| SciCode | 26% | — |
| WeirdML | 14.4% | — |
| BigCodeBench Instruct | 46.9% | — |
| LiveBench Coding | 36.6% | — |
| BigCodeBench Complete | 57.5% | — |
Agentic & Tool Use Not comparable
Llama-3.3-70B-Instruct: 25.8 (#105), Qwen2.5 Plus 1127: —
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 31.9% | — |
| BALROG | 23% | — |
Reasoning Qwen2.5 Plus 1127 leads
Llama-3.3-70B-Instruct: 14.1 (#327), Qwen2.5 Plus 1127: 25.9 (#141)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1299 |
| SimpleBench | 19.9% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 50.8% | — |
| DTBench | 59.5% | — |
| LiveBench Data Analysis | 49.5% | — |
| LMCA | 17.5% | — |
| Epoch Capabilities Index | 127.33 | — |
| ForecastBench | 58.6 | — |
| LiveBench | 50.2% | — |
Math Qwen2.5 Plus 1127 leads
Llama-3.3-70B-Instruct: 15.3 (#298), Qwen2.5 Plus 1127: 36.1 (#174)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1267 | 1298 |
| OTIS Mock AIME 2024-2025 | 5.1% | — |
| LiveBench Math | 42.2% | — |
| MATH Level 5 | 41.6% | — |
Knowledge Qwen2.5 Plus 1127 leads
Llama-3.3-70B-Instruct: 30.6 (#226), Qwen2.5 Plus 1127: 35.5 (#183)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | 1225 | 1289 |
| GPQA Diamond | 47.4% | — |
| Confabulations | 22.8% | — |
| Vectara Hallucination Rate | 4.1% | — |
| MMLU | 86.3% | — |
Multilingual Qwen2.5 Plus 1127 leads
Llama-3.3-70B-Instruct: 39.9 (#220), Qwen2.5 Plus 1127: 41.9 (#201)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1236 | 1265 |
| LMArena Chinese | 1217 | 1314 |
| LMArena German | 1251 | 1231 |
| LMArena Japanese | 1150 | 1207 |
| LMArena Russian | 1252 | 1271 |
| LMArena French | 1281 | — |
| LMArena Korean | 1143 | — |
| LMArena Spanish | 1270 | — |
Instruction Following Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 71.1 (#157), Qwen2.5 Plus 1127: 67.2 (#199)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1242 | 1275 |
| LiveBench Instruction Following | 82.7% | — |
Long Context Qwen2.5 Plus 1127 leads
Llama-3.3-70B-Instruct: 26.4 (#295), Qwen2.5 Plus 1127: 39.2 (#184)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1256 | 1292 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Qwen2.5 Plus 1127 leads
Llama-3.3-70B-Instruct: 47.6 (#207), Qwen2.5 Plus 1127: 49.4 (#192)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1274 | 1299 |
| LMArena Creative Writing | 1250 | 1262 |
| LMArena Multi-Turn | 1280 | 1299 |
| LiveBench Language | 39.2% | — |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than Qwen2.5 Plus 1127?
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.8 to 30.6 on the Noometry Index.
Is Llama-3.3-70B-Instruct or Qwen2.5 Plus 1127 better for coding?
Qwen2.5 Plus 1127 scores higher on coding benchmarks: 38.5 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama-3.3-70B-Instruct and Qwen2.5 Plus 1127 share?
14 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Qwen2.5 Plus 1127 has 14.