Model comparison
Llama 3.1-8B vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 23.0 on the Noometry Index. Llama 3.1-8B costs 52× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Llama 3.1-8B scores higher in 0 categories and Qwen3.8 Max in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 10.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.7% for Llama 3.1-8B and 100% for Qwen3.8 Max.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 128K.
- Llama 3.1-8B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-8B | Qwen3.8 Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 23.0 | 56.8 |
| Released | 2024-07-23 | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.05 | $2 |
| Output $ / M tokens | $0.08 | $6 |
| Results tracked | 43 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Llama 3.1-8B: 20.2 (#340), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Llama 3.1-8B | Qwen3.8 Max |
|---|---|---|
| SciCode | 13.2% | 53.2% |
| LMArena Coding | 1195 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| WeirdML | 1.7% | — |
| BigCodeBench Instruct | 32.8% | — |
| BigCodeBench Complete | 40.5% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Qwen3.8 Max leads
Llama 3.1-8B: 22.5 (#131), Qwen3.8 Max: 45.4 (#14)
| Benchmark | Llama 3.1-8B | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| Berkeley Function Calling Leaderboard | 25.8% | — |
| τ²-bench Banking | — | 55.1% |
| BALROG | 15.1% | — |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Llama 3.1-8B: 14.9 (#321), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Llama 3.1-8B | Qwen3.8 Max |
|---|---|---|
| CritPt | 0% | 20% |
| Chess Puzzles | 0% | 40% |
| LMArena Hard Prompts | 1175 | 1496 |
| DTBench | 50.9% | 92% |
| LMCA | 5.4% | 46.2% |
| Epoch Capabilities Index | 116.57 | 156.41 |
| NYT Connections (extended) | — | 88.3% |
| Mystery Game Puzzles | — | 38% |
| PIQA | 81.2% | — |
Math Qwen3.8 Max leads
Llama 3.1-8B: 10.2 (#317), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Llama 3.1-8B | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.7% | 100% |
| LMArena Math | 1179 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| Omni-MATH | 13.7% | — |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |
Knowledge Qwen3.8 Max leads
Llama 3.1-8B: 8.0 (#307), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Llama 3.1-8B | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 27% | 92.7% |
| LMArena Expert | 1144 | 1507 |
| SimpleQA Verified | — | 47.3% |
| MMLU-Pro | 40.6% | — |
| GPQA (HELM) | 24.7% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multimodal Not comparable
Llama 3.1-8B: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Llama 3.1-8B | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
Llama 3.1-8B: 34.0 (#249), Qwen3.8 Max: 56.7 (#18)
| Benchmark | Llama 3.1-8B | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1148 | 1472 |
| LMArena Chinese | 1151 | 1538 |
| LMArena French | 1177 | 1503 |
| LMArena German | 1144 | 1483 |
| LMArena Japanese | 1061 | 1467 |
| LMArena Korean | 1053 | 1461 |
| LMArena Russian | 1158 | 1481 |
| LMArena Spanish | 1169 | 1492 |
Instruction Following Qwen3.8 Max leads
Llama 3.1-8B: 58.9 (#258), Qwen3.8 Max: 77.6 (#17)
| Benchmark | Llama 3.1-8B | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1159 | 1479 |
| IFEval | 74.3% | — |
Long Context Qwen3.8 Max leads
Llama 3.1-8B: 35.8 (#238), Qwen3.8 Max: 45.6 (#31)
| Benchmark | Llama 3.1-8B | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1182 | 1489 |
Writing & Preference Qwen3.8 Max leads
Llama 3.1-8B: 29.7 (#290), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Llama 3.1-8B | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1187 | 1483 |
| LMArena Creative Writing | 1154 | 1479 |
| LMArena Multi-Turn | 1172 | 1489 |
| EQ-Bench Creative Writing | 713 | — |
| WildBench | 68.7% | — |
Frequently asked questions
Is Llama 3.1-8B better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 23.0 on the Noometry Index. Llama 3.1-8B costs 52× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-8B or Qwen3.8 Max?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is Llama 3.1-8B or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 128K.
How many benchmarks do Llama 3.1-8B and Qwen3.8 Max share?
25 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Qwen3.8 Max has 39.