Model comparison
Claude Sonnet 4 vs Llama 2-13B
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 29.6 on the Noometry Index.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. Claude Sonnet 4 scores higher in 8 categories and Llama 2-13B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Sonnet 4 leads 57.1 to 29.8.
- The biggest single-benchmark swing is DTBench: 77.1% for Claude Sonnet 4 and 42.2% for Llama 2-13B.
- Llama 2-13B has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | Llama 2-13B | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 40.8 | 29.6 |
| Released | 2025-05-22 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 58 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), Llama 2-13B: 30.9 (#291)
| Benchmark | Claude Sonnet 4 | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1414 | 1062 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.5 (#31), Llama 2-13B: —
| Benchmark | Claude Sonnet 4 | Llama 2-13B |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 22.9 (#187), Llama 2-13B: 12.8 (#337)
| Benchmark | Claude Sonnet 4 | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1051 |
| DTBench | 77.1% | 42.2% |
| Epoch Capabilities Index | 141.69 | 106.17 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 0% |
| EnigmaEval | 3.1% | — |
| LMCA | 29% | — |
| BIG-Bench Hard | — | 58.2% |
| ForecastBench | 60.2 | — |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), Llama 2-13B: 31.1 (#229)
| Benchmark | Claude Sonnet 4 | Llama 2-13B |
|---|---|---|
| LMArena Math | 1375 | 1065 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
| GSM8K | — | 36.9% |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), Llama 2-13B: 28.1 (#249)
| Benchmark | Claude Sonnet 4 | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1372 | 1030 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), Llama 2-13B: —
| Benchmark | Claude Sonnet 4 | Llama 2-13B |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
| ScienceQA | — | 55.8% |
Multilingual Claude Sonnet 4 leads
Claude Sonnet 4: 46.7 (#156), Llama 2-13B: 26.5 (#279)
| Benchmark | Claude Sonnet 4 | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1333 | 1024 |
| LMArena Chinese | 1350 | 1001 |
| LMArena French | 1363 | 1044 |
| LMArena German | 1331 | 1009 |
| LMArena Japanese | 1302 | 894 |
| LMArena Korean | 1291 | 953 |
| LMArena Russian | 1355 | 1055 |
| LMArena Spanish | 1357 | 1087 |
Instruction Following Claude Sonnet 4 leads
Claude Sonnet 4: 71.7 (#145), Llama 2-13B: 53.3 (#287)
| Benchmark | Claude Sonnet 4 | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1376 | 1045 |
| IFEval | 84% | — |
Long Context Claude Sonnet 4 leads
Claude Sonnet 4: 33.7 (#259), Llama 2-13B: 32.3 (#269)
| Benchmark | Claude Sonnet 4 | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1398 | 1064 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), Llama 2-13B: 29.8 (#289)
| Benchmark | Claude Sonnet 4 | Llama 2-13B |
|---|---|---|
| LMArena Text | 1351 | 1084 |
| LMArena Creative Writing | 1345 | 1047 |
| LMArena Multi-Turn | 1376 | 1050 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than Llama 2-13B?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 29.6 on the Noometry Index.
Is Claude Sonnet 4 or Llama 2-13B better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 30.9 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4 and Llama 2-13B share?
19 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Llama 2-13B has 32.