# Llama 3.1-8B vs Qwen3.7 Plus

> Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 23.0 on the Noometry Index. Llama 3.1-8B costs 12× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/llama-3-1-8b-vs-qwen3-7-plus
- Last updated: 2026-10-12
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Llama 3.1-8B scores higher in 1 category and Qwen3.7 Plus in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Plus leads 54.9 to 8.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.7% for Llama 3.1-8B and 93.3% for Qwen3.7 Plus.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- Qwen3.7 Plus accepts more context: 1M tokens versus 128K.
- Llama 3.1-8B has downloadable open weights; the other is API-only.

## Snapshot

| | Llama 3.1-8B | Qwen3.7 Plus |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 23.0 | 45.3 |
| Rank | 352 | 72 |
| Context | 128K | 1M |
| Input $/M | $0.05 | $0.40 |
| Output $/M | $0.08 | $1.60 |
| Weights | Open | Proprietary |

## Coding

- Llama 3.1-8B: 20.2 (#340)
- Qwen3.7 Plus: 36.6 (#206)

| Benchmark | Llama 3.1-8B | Qwen3.7 Plus |
|---|---|---|
| SciCode | 13.2% | 45.5% |
| LMArena Coding | 1195 | 1473 |
| FrontierCode | — | 10.2% |
| WeirdML | 1.7% | — |
| BigCodeBench Instruct | 32.8% | — |
| BigCodeBench Complete | 40.5% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |

## Agentic & Tool Use

- Llama 3.1-8B: 22.5 (#131)
- Qwen3.7 Plus: 21.4 (#138)

| Benchmark | Llama 3.1-8B | Qwen3.7 Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| OSWorld 2.0 | — | 2.8% |
| BALROG | 15.1% | — |

## Reasoning

- Llama 3.1-8B: 14.9 (#321)
- Qwen3.7 Plus: 39.3 (#59)

| Benchmark | Llama 3.1-8B | Qwen3.7 Plus |
|---|---|---|
| CritPt | 0% | 9.1% |
| Chess Puzzles | 0% | 24% |
| LMArena Hard Prompts | 1175 | 1460 |
| DTBench | 50.9% | 84% |
| LMCA | 5.4% | 37.6% |
| Epoch Capabilities Index | 116.57 | 147.37 |
| NYT Connections (extended) | — | 74.8% |
| Mystery Game Puzzles | — | 17% |
| PIQA | 81.2% | — |

## Math

- Llama 3.1-8B: 10.2 (#317)
- Qwen3.7 Plus: 50.5 (#56)

| Benchmark | Llama 3.1-8B | Qwen3.7 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.7% | 93.3% |
| LMArena Math | 1179 | 1466 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| Omni-MATH | 13.7% | — |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |

## Knowledge

- Llama 3.1-8B: 8.0 (#307)
- Qwen3.7 Plus: 54.9 (#51)

| Benchmark | Llama 3.1-8B | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 27% | 87.9% |
| LMArena Expert | 1144 | 1467 |
| MMLU-Pro | 40.6% | — |
| GPQA (HELM) | 24.7% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |

## Multimodal

- Llama 3.1-8B: —
- Qwen3.7 Plus: 41.8 (#33)

| Benchmark | Llama 3.1-8B | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |

## Multilingual

- Llama 3.1-8B: 34.0 (#249)
- Qwen3.7 Plus: 54.8 (#38)

| Benchmark | Llama 3.1-8B | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1148 | 1445 |
| LMArena Chinese | 1151 | 1510 |
| LMArena French | 1177 | 1473 |
| LMArena German | 1144 | 1471 |
| LMArena Japanese | 1061 | 1413 |
| LMArena Korean | 1053 | 1415 |
| LMArena Russian | 1158 | 1457 |
| LMArena Spanish | 1169 | 1457 |

## Instruction Following

- Llama 3.1-8B: 58.9 (#258)
- Qwen3.7 Plus: 75.8 (#52)

| Benchmark | Llama 3.1-8B | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1159 | 1440 |
| IFEval | 74.3% | — |

## Long Context

- Llama 3.1-8B: 35.8 (#238)
- Qwen3.7 Plus: 44.5 (#65)

| Benchmark | Llama 3.1-8B | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1182 | 1455 |

## Writing & Preference

- Llama 3.1-8B: 29.7 (#290)
- Qwen3.7 Plus: 64.3 (#56)

| Benchmark | Llama 3.1-8B | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1187 | 1455 |
| LMArena Creative Writing | 1154 | 1439 |
| LMArena Multi-Turn | 1172 | 1460 |
| EQ-Bench Creative Writing | 713 | — |
| WildBench | 68.7% | — |

## FAQ

### Is Llama 3.1-8B better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 23.0 on the Noometry Index. Llama 3.1-8B costs 12× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.

### Which is cheaper, Llama 3.1-8B or Qwen3.7 Plus?

Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.

### Is Llama 3.1-8B or Qwen3.7 Plus better for coding?

Qwen3.7 Plus scores higher on coding benchmarks: 36.6 versus 20.2 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.7 Plus does, with 1M tokens against 128K.

### How many benchmarks do Llama 3.1-8B and Qwen3.7 Plus share?

25 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Qwen3.7 Plus has 32.