Model comparison
Llama-3.3-70B-Instruct vs Qwen2.5 7B Instruct
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 29.0 on the Noometry Index.
Last verified . 9 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 9 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 4 categories and Qwen2.5 7B Instruct in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama-3.3-70B-Instruct leads 30.6 to 17.0.
- The biggest single-benchmark swing is BALROG: 23% for Llama-3.3-70B-Instruct and 7.8% for Qwen2.5 7B Instruct.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 per million input/output tokens, against $0.17 / $0.70 for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct accepts more context: 131K tokens versus 128K.
Side by side
| Llama-3.3-70B-Instruct | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.6 | 29.0 |
| Released | 2024-12-06 | 2024-09 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 8K |
| Input $ / M tokens | $0.10 | $0.17 |
| Output $ / M tokens | $0.32 | $0.70 |
| Results tracked | 43 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 7B Instruct leads
Llama-3.3-70B-Instruct: 31.0 (#290), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | 46.9% | 37.6% |
| BigCodeBench Complete | 57.5% | 46.1% |
| SciCode | 26% | — |
| WeirdML | 14.4% | — |
| LiveBench Coding | 36.6% | — |
| LMArena Coding | 1268 | — |
Agentic & Tool Use Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 25.8 (#105), Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | 23% | 7.8% |
| Berkeley Function Calling Leaderboard | 31.9% | — |
Reasoning Too close to call
Llama-3.3-70B-Instruct: 14.1 (#327), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 7B Instruct |
|---|---|---|
| DTBench | 59.5% | 47.7% |
| LMCA | 17.5% | 6.4% |
| Epoch Capabilities Index | 127.33 | 118.51 |
| SimpleBench | 19.9% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 50.8% | — |
| LMArena Hard Prompts | 1257 | — |
| LiveBench Data Analysis | 49.5% | — |
| ForecastBench | 58.6 | — |
| LiveBench | 50.2% | — |
Math Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 15.3 (#298), Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.1% | 2.5% |
| Omni-MATH | — | 29.4% |
| LiveBench Math | 42.2% | — |
| LMArena Math | 1267 | — |
| MATH Level 5 | 41.6% | — |
Knowledge Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 30.6 (#226), Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 47.4% | 35.5% |
| MMLU | 86.3% | 72.9% |
| MMLU-Pro | — | 53.9% |
| Confabulations | 22.8% | — |
| Vectara Hallucination Rate | 4.1% | — |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1225 | — |
Multilingual Not comparable
Llama-3.3-70B-Instruct: 39.9 (#220), Qwen2.5 7B Instruct: —
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1236 | — |
| LMArena Chinese | 1217 | — |
| LMArena French | 1281 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1150 | — |
| LMArena Korean | 1143 | — |
| LMArena Russian | 1252 | — |
| LMArena Spanish | 1270 | — |
Instruction Following Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 71.1 (#157), Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 7B Instruct |
|---|---|---|
| LiveBench Instruction Following | 82.7% | — |
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1242 | — |
Long Context Not comparable
Llama-3.3-70B-Instruct: 26.4 (#295), Qwen2.5 7B Instruct: —
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 7B Instruct |
|---|---|---|
| Fiction.LiveBench | 33.3% | — |
| LMArena Longer Query | 1256 | — |
Writing & Preference Qwen2.5 7B Instruct leads
Llama-3.3-70B-Instruct: 47.6 (#207), Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Llama-3.3-70B-Instruct | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1274 | — |
| LMArena Creative Writing | 1250 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1280 | — |
| LiveBench Language | 39.2% | — |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than Qwen2.5 7B Instruct?
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 29.0 on the Noometry Index.
Which is cheaper, Llama-3.3-70B-Instruct or Qwen2.5 7B Instruct?
Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; Qwen2.5 7B Instruct lists at $0.17 and $0.70.
Is Llama-3.3-70B-Instruct or Qwen2.5 7B Instruct better for coding?
Qwen2.5 7B Instruct scores higher on coding benchmarks: 36.5 versus 31.0 in the Noometry coding category.
Which has the bigger context window?
Qwen2.5 7B Instruct does, with 131K tokens against 128K.
How many benchmarks do Llama-3.3-70B-Instruct and Qwen2.5 7B Instruct share?
9 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Qwen2.5 7B Instruct has 15.