Model comparison
Llama 3.1-8B vs Qwen3.5-Flash
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 23.0 on the Noometry Index. Llama 3.1-8B costs 3.0× less per token, which makes it the better buy when Qwen3.5-Flash's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Llama 3.1-8B scores higher in 0 categories and Qwen3.5-Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5-Flash leads 43.2 to 8.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.7% for Llama 3.1-8B and 84.4% for Qwen3.5-Flash.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.10 / $0.40 for Qwen3.5-Flash.
- Qwen3.5-Flash 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 | Qwen3.5-Flash | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 23.0 | 42.5 |
| Released | 2024-07-23 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 66K |
| Input $ / M tokens | $0.05 | $0.10 |
| Output $ / M tokens | $0.08 | $0.40 |
| Results tracked | 43 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5-Flash leads
Llama 3.1-8B: 20.2 (#340), Qwen3.5-Flash: 34.2 (#242)
| Benchmark | Llama 3.1-8B | Qwen3.5-Flash |
|---|---|---|
| LMArena Coding | 1195 | 1412 |
| LMArena WebDev | — | 1244 |
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
| BigCodeBench Instruct | 32.8% | — |
| BigCodeBench Complete | 40.5% | — |
| ALE-Bench | — | 221.8 |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Not comparable
Llama 3.1-8B: 22.5 (#131), Qwen3.5-Flash: —
| Benchmark | Llama 3.1-8B | Qwen3.5-Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| BALROG | 15.1% | — |
| Vending-Bench 2 | — | 462.69 |
Reasoning Qwen3.5-Flash leads
Llama 3.1-8B: 14.9 (#321), Qwen3.5-Flash: 33.7 (#72)
| Benchmark | Llama 3.1-8B | Qwen3.5-Flash |
|---|---|---|
| Chess Puzzles | 0% | 21% |
| LMArena Hard Prompts | 1175 | 1403 |
| DTBench | 50.9% | 82.9% |
| LMCA | 5.4% | 29.1% |
| Epoch Capabilities Index | 116.57 | 143.98 |
| CritPt | 0% | — |
| Mystery Game Puzzles | — | 20% |
| PIQA | 81.2% | — |
Math Qwen3.5-Flash leads
Llama 3.1-8B: 10.2 (#317), Qwen3.5-Flash: 37.4 (#158)
| Benchmark | Llama 3.1-8B | Qwen3.5-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.7% | 84.4% |
| LMArena Math | 1179 | 1407 |
| FrontierMath (Tiers 1-3) | — | 18.2% |
| Omni-MATH | 13.7% | — |
| MATH Level 5 | 22.9% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |
| GSM8K | 82.4% | — |
Knowledge Qwen3.5-Flash leads
Llama 3.1-8B: 8.0 (#307), Qwen3.5-Flash: 43.2 (#93)
| Benchmark | Llama 3.1-8B | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 27% | 82.3% |
| LMArena Expert | 1144 | 1407 |
| SimpleQA Verified | — | 20.3% |
| MMLU-Pro | 40.6% | — |
| Vectara Hallucination Rate | — | 10.5% |
| GPQA (HELM) | 24.7% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multilingual Qwen3.5-Flash leads
Llama 3.1-8B: 34.0 (#249), Qwen3.5-Flash: 50.5 (#121)
| Benchmark | Llama 3.1-8B | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1148 | 1385 |
| LMArena Chinese | 1151 | 1446 |
| LMArena French | 1177 | 1412 |
| LMArena German | 1144 | 1390 |
| LMArena Japanese | 1061 | 1368 |
| LMArena Korean | 1053 | 1344 |
| LMArena Russian | 1158 | 1379 |
| LMArena Spanish | 1169 | 1400 |
Instruction Following Qwen3.5-Flash leads
Llama 3.1-8B: 58.9 (#258), Qwen3.5-Flash: 72.6 (#139)
| Benchmark | Llama 3.1-8B | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1159 | 1374 |
| IFEval | 74.3% | — |
Long Context Qwen3.5-Flash leads
Llama 3.1-8B: 35.8 (#238), Qwen3.5-Flash: 42.4 (#124)
| Benchmark | Llama 3.1-8B | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1182 | 1392 |
Writing & Preference Qwen3.5-Flash leads
Llama 3.1-8B: 29.7 (#290), Qwen3.5-Flash: 57.9 (#122)
| Benchmark | Llama 3.1-8B | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1187 | 1397 |
| LMArena Creative Writing | 1154 | 1343 |
| LMArena Multi-Turn | 1172 | 1393 |
| EQ-Bench Creative Writing | 713 | — |
| WildBench | 68.7% | — |
Frequently asked questions
Is Llama 3.1-8B better than Qwen3.5-Flash?
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 23.0 on the Noometry Index. Llama 3.1-8B costs 3.0× less per token, which makes it the better buy when Qwen3.5-Flash's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-8B or Qwen3.5-Flash?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen3.5-Flash lists at $0.10 and $0.40.
Is Llama 3.1-8B or Qwen3.5-Flash better for coding?
Qwen3.5-Flash scores higher on coding benchmarks: 34.2 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5-Flash does, with 1M tokens against 128K.
How many benchmarks do Llama 3.1-8B and Qwen3.5-Flash share?
23 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Qwen3.5-Flash has 32.