Model comparison
Llama 2-13B vs Llama 4 Maverick
Llama 4 Maverick is the stronger model overall, scoring 30.9 to 29.6 on the Noometry Index.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. Llama 2-13B scores higher in 4 categories and Llama 4 Maverick in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 4 Maverick leads 71.7 to 53.3.
- The biggest single-benchmark swing is DTBench: 42.2% for Llama 2-13B and 61.9% for Llama 4 Maverick.
Side by side
| Llama 2-13B | Llama 4 Maverick | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 29.6 | 30.9 |
| Released | 2023-07-18 | 2025-04-05 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.19 |
| Output $ / M tokens | — | $0.65 |
| Results tracked | 32 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-13B leads
Llama 2-13B: 30.9 (#291), Llama 4 Maverick: 26.6 (#324)
| Benchmark | Llama 2-13B | Llama 4 Maverick |
|---|---|---|
| LMArena Coding | 1062 | 1302 |
| 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 2-13B: —, Llama 4 Maverick: 28.2 (#91)
| Benchmark | Llama 2-13B | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
Reasoning Llama 2-13B leads
Llama 2-13B: 12.8 (#337), Llama 4 Maverick: 10.1 (#342)
| Benchmark | Llama 2-13B | Llama 4 Maverick |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1281 |
| DTBench | 42.2% | 61.9% |
| Epoch Capabilities Index | 106.17 | 132.2 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 27.7% |
| Kagi LLM Benchmark | — | 55.9% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| EnigmaEval | — | 0.6% |
| LMCA | — | 15.9% |
| BIG-Bench Hard | 58.2% | — |
| ForecastBench | — | 57.5 |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math Llama 2-13B leads
Llama 2-13B: 31.1 (#229), Llama 4 Maverick: 26.0 (#262)
| Benchmark | Llama 2-13B | Llama 4 Maverick |
|---|---|---|
| LMArena Math | 1065 | 1299 |
| OTIS Mock AIME 2024-2025 | — | 20.6% |
| Omni-MATH | — | 42.2% |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
| GSM8K | 36.9% | — |
Knowledge Llama 4 Maverick leads
Llama 2-13B: 28.1 (#249), Llama 4 Maverick: 33.4 (#204)
| Benchmark | Llama 2-13B | Llama 4 Maverick |
|---|---|---|
| LMArena Expert | 1030 | 1259 |
| GPQA Diamond | — | 67% |
| Humanity's Last Exam | — | 5.7% |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Llama 4 Maverick: 31.6 (#105)
| Benchmark | Llama 2-13B | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | — | 1142 |
| GeoBench | — | 52% |
| ScienceQA | 55.8% | — |
| SpatialViz-Bench | — | 31.8% |
Multilingual Llama 4 Maverick leads
Llama 2-13B: 26.5 (#279), Llama 4 Maverick: 42.2 (#195)
| Benchmark | Llama 2-13B | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1024 | 1269 |
| LMArena Chinese | 1001 | 1277 |
| LMArena French | 1044 | 1259 |
| LMArena German | 1009 | 1291 |
| LMArena Japanese | 894 | 1207 |
| LMArena Korean | 953 | 1203 |
| LMArena Russian | 1055 | 1286 |
| LMArena Spanish | 1087 | 1293 |
Instruction Following Llama 4 Maverick leads
Llama 2-13B: 53.3 (#287), Llama 4 Maverick: 71.7 (#146)
| Benchmark | Llama 2-13B | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1045 | 1267 |
| IFEval | — | 90.8% |
Long Context Too close to call
Llama 2-13B: 32.3 (#269), Llama 4 Maverick: 31.4 (#279)
| Benchmark | Llama 2-13B | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1064 | 1280 |
| Fiction.LiveBench | — | 46.2% |
Writing & Preference Llama 4 Maverick leads
Llama 2-13B: 29.8 (#289), Llama 4 Maverick: 38.8 (#252)
| Benchmark | Llama 2-13B | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1084 | 1287 |
| LMArena Creative Writing | 1047 | 1267 |
| LMArena Multi-Turn | 1050 | 1289 |
| Short-Story Creative Writing | — | 62% |
| EQ-Bench Creative Writing | — | 860 |
| WildBench | — | 80% |
Frequently asked questions
Is Llama 2-13B better than Llama 4 Maverick?
Llama 4 Maverick is the stronger model overall, scoring 30.9 to 29.6 on the Noometry Index.
Is Llama 2-13B or Llama 4 Maverick better for coding?
Llama 2-13B scores higher on coding benchmarks: 30.9 versus 26.6 in the Noometry coding category.
How many benchmarks do Llama 2-13B and Llama 4 Maverick share?
19 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Llama 4 Maverick has 54.