Model comparison
Llama 3.1-8B vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 23.0 on the Noometry Index. Llama 3.1-8B costs 49× less per token, which makes it the better buy when Qwen Max's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Llama 3.1-8B scores higher in 0 categories and Qwen Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen Max leads 30.3 to 8.0.
- The biggest single-benchmark swing is MATH Level 5: 22.9% for Llama 3.1-8B and 67.2% for Qwen Max.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- Llama 3.1-8B accepts more context: 128K tokens versus 33K.
- Llama 3.1-8B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-8B | Qwen Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 23.0 | 34.7 |
| Released | 2024-07-23 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | 128K | 33K |
| Max output | 4K | 8K |
| Input $ / M tokens | $0.05 | $1.60 |
| Output $ / M tokens | $0.08 | $6.40 |
| Results tracked | 43 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Max leads
Llama 3.1-8B: 20.2 (#340), Qwen Max: 30.7 (#292)
| Benchmark | Llama 3.1-8B | Qwen Max |
|---|---|---|
| LMArena Coding | 1195 | 1288 |
| Aider Polyglot | — | 21.8% |
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
| BigCodeBench Instruct | 32.8% | — |
| BigCodeBench Complete | 40.5% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Not comparable
Llama 3.1-8B: 22.5 (#131), Qwen Max: —
| Benchmark | Llama 3.1-8B | Qwen Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| BALROG | 15.1% | — |
Reasoning Qwen Max leads
Llama 3.1-8B: 14.9 (#321), Qwen Max: 25.1 (#151)
| Benchmark | Llama 3.1-8B | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1175 | 1269 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 5.4% | — |
| Epoch Capabilities Index | 116.57 | — |
| PIQA | 81.2% | — |
Math Qwen Max leads
Llama 3.1-8B: 10.2 (#317), Qwen Max: 22.3 (#276)
| Benchmark | Llama 3.1-8B | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.7% | 16.1% |
| LMArena Math | 1179 | 1275 |
| MATH Level 5 | 22.9% | 67.2% |
| Omni-MATH | 13.7% | — |
| FrontierMath (Feb 2025 set) | — | 1% |
| GSM8K | 82.4% | — |
Knowledge Qwen Max leads
Llama 3.1-8B: 8.0 (#307), Qwen Max: 30.3 (#228)
| Benchmark | Llama 3.1-8B | Qwen Max |
|---|---|---|
| GPQA Diamond | 27% | 56.1% |
| LMArena Expert | 1144 | 1248 |
| MMLU-Pro | 40.6% | — |
| GPQA (HELM) | 24.7% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multilingual Qwen Max leads
Llama 3.1-8B: 34.0 (#249), Qwen Max: 41.8 (#202)
| Benchmark | Llama 3.1-8B | Qwen Max |
|---|---|---|
| LMArena Non-English | 1148 | 1263 |
| LMArena Chinese | 1151 | 1254 |
| LMArena French | 1177 | 1330 |
| LMArena German | 1144 | 1254 |
| LMArena Japanese | 1061 | 1205 |
| LMArena Korean | 1053 | 1142 |
| LMArena Russian | 1158 | 1274 |
| LMArena Spanish | 1169 | 1290 |
Instruction Following Qwen Max leads
Llama 3.1-8B: 58.9 (#258), Qwen Max: 66.5 (#208)
| Benchmark | Llama 3.1-8B | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1159 | 1262 |
| IFEval | 74.3% | — |
Long Context Qwen Max leads
Llama 3.1-8B: 35.8 (#238), Qwen Max: 39.4 (#180)
| Benchmark | Llama 3.1-8B | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1182 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Qwen Max leads
Llama 3.1-8B: 29.7 (#290), Qwen Max: 47.8 (#205)
| Benchmark | Llama 3.1-8B | Qwen Max |
|---|---|---|
| LMArena Text | 1187 | 1282 |
| LMArena Creative Writing | 1154 | 1248 |
| LMArena Multi-Turn | 1172 | 1277 |
| EQ-Bench Creative Writing | 713 | — |
| WildBench | 68.7% | — |
Frequently asked questions
Is Llama 3.1-8B better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 23.0 on the Noometry Index. Llama 3.1-8B costs 49× less per token, which makes it the better buy when Qwen Max's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-8B or Qwen Max?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is Llama 3.1-8B or Qwen Max better for coding?
Qwen Max scores higher on coding benchmarks: 30.7 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Llama 3.1-8B does, with 128K tokens against 33K.
How many benchmarks do Llama 3.1-8B and Qwen Max share?
20 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Qwen Max has 23.