Model comparison
Llama 4 Maverick vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 30.6 on the Noometry Index. Llama 4 Maverick costs 2.3× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. Llama 4 Maverick scores higher in 1 category and Qwen3.7 Plus in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.7 Plus leads 38.4 to 10.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 20.6% for Llama 4 Maverick and 93.3% for Qwen3.7 Plus.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 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 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Maverick | Qwen3.7 Plus | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.6 | 45.0 |
| Released | 2025-04-05 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.19 | $0.40 |
| Output $ / M tokens | $0.65 | $1.60 |
| Results tracked | 54 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Plus leads
Llama 4 Maverick: 26.3 (#318), Qwen3.7 Plus: 36.1 (#200)
| Benchmark | Llama 4 Maverick | Qwen3.7 Plus |
|---|---|---|
| SciCode | 33.1% | 45.5% |
| LMArena Coding | 1302 | 1473 |
| FrontierCode | — | 10.2% |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| WeirdML | 24.5% | — |
| BigCodeBench Instruct | 49.7% | — |
| BigCodeBench Complete | 61.4% | — |
| ALE-Bench | 172.97 | — |
Agentic & Tool Use Llama 4 Maverick leads
Llama 4 Maverick: 27.9 (#86), Qwen3.7 Plus: 21.2 (#130)
| Benchmark | Llama 4 Maverick | Qwen3.7 Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
Llama 4 Maverick: 10.1 (#337), Qwen3.7 Plus: 38.4 (#54)
| Benchmark | Llama 4 Maverick | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 8% | 74.8% |
| CritPt | 0% | 9.1% |
| LMArena Hard Prompts | 1281 | 1460 |
| DTBench | 61.9% | 84% |
| LMCA | 15.9% | 37.6% |
| Epoch Capabilities Index | 132.2 | 147.39 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| ARC-AGI-1 | 4.4% | — |
| Chess Puzzles | — | 24% |
| EnigmaEval | 0.6% | — |
| Mystery Game Puzzles | — | 17% |
| ForecastBench | 57.5 | — |
Math Qwen3.7 Plus leads
Llama 4 Maverick: 24.6 (#256), Qwen3.7 Plus: 49.3 (#47)
| Benchmark | Llama 4 Maverick | Qwen3.7 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 20.6% | 93.3% |
| LMArena Math | 1299 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| Omni-MATH | 42.2% | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Qwen3.7 Plus leads
Llama 4 Maverick: 33.3 (#196), Qwen3.7 Plus: 54.9 (#46)
| Benchmark | Llama 4 Maverick | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 67% | 87.9% |
| LMArena Expert | 1259 | 1467 |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
Multimodal Qwen3.7 Plus leads
Llama 4 Maverick: 30.9 (#100), Qwen3.7 Plus: 41.2 (#30)
| Benchmark | Llama 4 Maverick | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1141 | 1281 |
| GeoBench | 52% | — |
| LMArena Document | — | 1444 |
| SpatialViz-Bench | 31.8% | — |
Multilingual Qwen3.7 Plus leads
Llama 4 Maverick: 42.4 (#190), Qwen3.7 Plus: 55.0 (#36)
| Benchmark | Llama 4 Maverick | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1269 | 1445 |
| LMArena Chinese | 1277 | 1510 |
| LMArena French | 1258 | 1471 |
| LMArena German | 1291 | 1471 |
| LMArena Japanese | 1207 | 1411 |
| LMArena Korean | 1203 | 1416 |
| LMArena Russian | 1286 | 1457 |
| LMArena Spanish | 1293 | 1453 |
Instruction Following Qwen3.7 Plus leads
Llama 4 Maverick: 71.9 (#140), Qwen3.7 Plus: 75.9 (#49)
| Benchmark | Llama 4 Maverick | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1267 | 1439 |
| IFEval | 90.8% | — |
Long Context Qwen3.7 Plus leads
Llama 4 Maverick: 31.4 (#274), Qwen3.7 Plus: 44.5 (#61)
| Benchmark | Llama 4 Maverick | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1280 | 1454 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Qwen3.7 Plus leads
Llama 4 Maverick: 39.0 (#247), Qwen3.7 Plus: 64.5 (#54)
| Benchmark | Llama 4 Maverick | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1287 | 1454 |
| LMArena Creative Writing | 1266 | 1439 |
| LMArena Multi-Turn | 1289 | 1459 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Llama 4 Maverick better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 30.6 on the Noometry Index. Llama 4 Maverick costs 2.3× 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 4 Maverick or Qwen3.7 Plus?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is Llama 4 Maverick or Qwen3.7 Plus better for coding?
Qwen3.7 Plus scores higher on coding benchmarks: 36.1 versus 26.3 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 4 Maverick and Qwen3.7 Plus share?
26 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Qwen3.7 Plus has 32.