Model comparison
Llama 4 Maverick vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.7 to 30.9 on the Noometry Index. Llama 4 Maverick costs 7.9× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 27 benchmarks with published results for both. Llama 4 Maverick scores higher in 0 categories and Qwen3 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 Max leads 62.4 to 38.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 20.6% for Llama 4 Maverick and 73.3% for Qwen3 Max.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Qwen3 Max accepts more context: 262K tokens versus 128K.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Maverick | Qwen3 Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.9 | 43.7 |
| Released | 2025-04-05 | 2025-09-23 |
| Weights | Open | Proprietary |
| Context window | 128K | 262K |
| Max output | 4K | 66K |
| Input $ / M tokens | $0.19 | $1.20 |
| Output $ / M tokens | $0.65 | $6 |
| Results tracked | 54 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
Llama 4 Maverick: 26.6 (#324), Qwen3 Max: 43.0 (#93)
| Benchmark | Llama 4 Maverick | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1302 | 1456 |
| ALE-Bench | 172.97 | 370.45 |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| SciCode | 33.1% | — |
| WeirdML | 24.5% | — |
| BigCodeBench Instruct | 49.7% | — |
| BigCodeBench Complete | 61.4% | — |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 28.2 (#91), Qwen3 Max: —
| Benchmark | Llama 4 Maverick | Qwen3 Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
| Vending-Bench 2 | — | 71.56 |
Reasoning Qwen3 Max leads
Llama 4 Maverick: 10.1 (#342), Qwen3 Max: 22.6 (#190)
| Benchmark | Llama 4 Maverick | Qwen3 Max |
|---|---|---|
| Kagi LLM Benchmark | 55.9% | 72.5% |
| NYT Connections (extended) | 8% | 30.1% |
| LMArena Hard Prompts | 1281 | 1448 |
| DTBench | 61.9% | 82.1% |
| LMCA | 15.9% | 28.3% |
| Epoch Capabilities Index | 132.2 | 142.38 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| ARC-AGI-1 | 4.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 4% |
| EnigmaEval | 0.6% | — |
| Mystery Game Puzzles | — | 5% |
| ForecastBench | 57.5 | — |
Math Qwen3 Max leads
Llama 4 Maverick: 26.0 (#262), Qwen3 Max: 38.7 (#131)
| Benchmark | Llama 4 Maverick | Qwen3 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 20.6% | 73.3% |
| LMArena Math | 1299 | 1446 |
| MATH Level 5 | 73% | 97.1% |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| Omni-MATH | 42.2% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Qwen3 Max leads
Llama 4 Maverick: 33.4 (#204), Qwen3 Max: 48.1 (#78)
| Benchmark | Llama 4 Maverick | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 67% | 72.6% |
| LMArena Expert | 1259 | 1455 |
| Humanity's Last Exam | 5.7% | — |
| SimpleQA Verified | — | 48.7% |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
Multimodal Not comparable
Llama 4 Maverick: 31.6 (#105), Qwen3 Max: —
| Benchmark | Llama 4 Maverick | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1142 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Qwen3 Max leads
Llama 4 Maverick: 42.2 (#195), Qwen3 Max: 53.7 (#62)
| Benchmark | Llama 4 Maverick | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1269 | 1429 |
| LMArena Chinese | 1277 | 1478 |
| LMArena French | 1259 | 1449 |
| LMArena German | 1291 | 1463 |
| LMArena Japanese | 1207 | 1397 |
| LMArena Korean | 1203 | 1399 |
| LMArena Russian | 1286 | 1428 |
| LMArena Spanish | 1293 | 1462 |
Instruction Following Qwen3 Max leads
Llama 4 Maverick: 71.7 (#146), Qwen3 Max: 74.8 (#87)
| Benchmark | Llama 4 Maverick | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1267 | 1419 |
| IFEval | 90.8% | — |
Long Context Qwen3 Max leads
Llama 4 Maverick: 31.4 (#279), Qwen3 Max: 41.6 (#134)
| Benchmark | Llama 4 Maverick | Qwen3 Max |
|---|---|---|
| Fiction.LiveBench | 46.2% | 66.7% |
| LMArena Longer Query | 1280 | 1438 |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
Llama 4 Maverick: 38.8 (#252), Qwen3 Max: 62.4 (#76)
| Benchmark | Llama 4 Maverick | Qwen3 Max |
|---|---|---|
| LMArena Text | 1287 | 1439 |
| LMArena Creative Writing | 1267 | 1402 |
| LMArena Multi-Turn | 1289 | 1446 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Llama 4 Maverick better than Qwen3 Max?
Qwen3 Max is the stronger model overall, scoring 43.7 to 30.9 on the Noometry Index. Llama 4 Maverick costs 7.9× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Maverick or Qwen3 Max?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Qwen3 Max lists at $1.20 and $6.
Is Llama 4 Maverick or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 43.0 versus 26.6 in the Noometry coding category.
Which has the bigger context window?
Qwen3 Max does, with 262K tokens against 128K.
How many benchmarks do Llama 4 Maverick and Qwen3 Max share?
27 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Qwen3 Max has 33.