Model comparison
Llama 4 Maverick vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 to 30.9 on the Noometry Index. Llama 4 Maverick costs 2.0× less per token, which makes it the better buy when Qwen Plus'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 4 Maverick scores higher in 3 categories and Qwen Plus in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen Plus leads 28.4 to 10.1.
- The biggest single-benchmark swing is DTBench: 61.9% for Llama 4 Maverick and 81.1% for Qwen Plus.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $0.40 / $1.20 for Qwen Plus.
- Qwen Plus accepts more context: 1M tokens versus 128K.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Maverick | Qwen Plus | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.9 | 37.1 |
| Released | 2025-04-05 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 33K |
| Input $ / M tokens | $0.19 | $0.40 |
| Output $ / M tokens | $0.65 | $1.20 |
| Results tracked | 54 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Llama 4 Maverick: 26.6 (#324), Qwen Plus: 38.9 (#167)
| Benchmark | Llama 4 Maverick | Qwen Plus |
|---|---|---|
| LMArena Coding | 1302 | 1328 |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| SciCode | 33.1% | — |
| WeirdML | 24.5% | — |
| BigCodeBench Instruct | 49.7% | — |
| BigCodeBench Complete | 61.4% | — |
| ALE-Bench | 172.97 | — |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 28.2 (#91), Qwen Plus: —
| Benchmark | Llama 4 Maverick | Qwen Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning Qwen Plus leads
Llama 4 Maverick: 10.1 (#342), Qwen Plus: 28.4 (#107)
| Benchmark | Llama 4 Maverick | Qwen Plus |
|---|---|---|
| Kagi LLM Benchmark | 55.9% | 63.3% |
| LMArena Hard Prompts | 1281 | 1317 |
| DTBench | 61.9% | 81.1% |
| LMCA | 15.9% | 24% |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| NYT Connections (extended) | 8% | — |
| ARC-AGI-1 | 4.4% | — |
| CritPt | 0% | — |
| EnigmaEval | 0.6% | — |
| Epoch Capabilities Index | 132.2 | — |
| ForecastBench | 57.5 | — |
Math Llama 4 Maverick leads
Llama 4 Maverick: 26.0 (#262), Qwen Plus: 23.3 (#271)
| Benchmark | Llama 4 Maverick | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 20.6% | 17.8% |
| LMArena Math | 1299 | 1326 |
| MATH Level 5 | 73% | 65.3% |
| FrontierMath (Feb 2025 set) | 0.7% | 1.7% |
| Omni-MATH | 42.2% | — |
Knowledge Llama 4 Maverick leads
Llama 4 Maverick: 33.4 (#204), Qwen Plus: 27.4 (#251)
| Benchmark | Llama 4 Maverick | Qwen Plus |
|---|---|---|
| GPQA Diamond | 67% | 48.1% |
| LMArena Expert | 1259 | 1328 |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
Multimodal Not comparable
Llama 4 Maverick: 31.6 (#105), Qwen Plus: —
| Benchmark | Llama 4 Maverick | Qwen Plus |
|---|---|---|
| LMArena Vision | 1142 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Qwen Plus leads
Llama 4 Maverick: 42.2 (#195), Qwen Plus: 45.1 (#175)
| Benchmark | Llama 4 Maverick | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1269 | 1310 |
| LMArena Chinese | 1277 | 1347 |
| LMArena Japanese | 1207 | 1251 |
| LMArena Russian | 1286 | 1323 |
| LMArena French | 1259 | — |
| LMArena German | 1291 | — |
| LMArena Korean | 1203 | — |
| LMArena Spanish | 1293 | — |
Instruction Following Llama 4 Maverick leads
Llama 4 Maverick: 71.7 (#146), Qwen Plus: 68.8 (#181)
| Benchmark | Llama 4 Maverick | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1267 | 1303 |
| IFEval | 90.8% | — |
Long Context Qwen Plus leads
Llama 4 Maverick: 31.4 (#279), Qwen Plus: 40.3 (#158)
| Benchmark | Llama 4 Maverick | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1280 | 1324 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Qwen Plus leads
Llama 4 Maverick: 38.8 (#252), Qwen Plus: 52.2 (#176)
| Benchmark | Llama 4 Maverick | Qwen Plus |
|---|---|---|
| LMArena Text | 1287 | 1326 |
| LMArena Creative Writing | 1267 | 1293 |
| LMArena Multi-Turn | 1289 | 1336 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Llama 4 Maverick better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 30.9 on the Noometry Index. Llama 4 Maverick costs 2.0× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Maverick or Qwen Plus?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Qwen Plus lists at $0.40 and $1.20.
Is Llama 4 Maverick or Qwen Plus better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 26.6 in the Noometry coding category.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 128K.
How many benchmarks do Llama 4 Maverick and Qwen Plus share?
20 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Qwen Plus has 20.