Model comparison
Claude 3.7 Sonnet vs Llama-3.3-70B-Instruct
Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 30.6 on the Noometry Index.
Last verified . 32 shared benchmarks.
MetaSummary
- They share 32 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 9 categories and Llama-3.3-70B-Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Claude 3.7 Sonnet leads 50.3 to 26.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Claude 3.7 Sonnet and 5.1% for Llama-3.3-70B-Instruct.
- Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | Llama-3.3-70B-Instruct | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 39.5 | 30.6 |
| Released | 2025-02-24 | 2024-12-06 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.32 |
| Results tracked | 58 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 40.6 (#136), Llama-3.3-70B-Instruct: 31.0 (#290)
| Benchmark | Claude 3.7 Sonnet | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Coding | 74.5% | 36.6% |
| LMArena Coding | 1361 | 1268 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| SciCode | — | 26% |
| GSO | 3.8% | — |
| WeirdML | — | 14.4% |
| BigCodeBench Instruct | — | 46.9% |
| BigCodeBench Complete | — | 57.5% |
| CadEval | 54% | — |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 34.1 (#50), Llama-3.3-70B-Instruct: 25.8 (#105)
| Benchmark | Claude 3.7 Sonnet | Llama-3.3-70B-Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 31.9% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| BALROG | — | 23% |
| METR Time Horizons | 60% | — |
Reasoning Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 18.6 (#277), Llama-3.3-70B-Instruct: 14.1 (#327)
| Benchmark | Claude 3.7 Sonnet | Llama-3.3-70B-Instruct |
|---|---|---|
| SimpleBench | 46.4% | 19.9% |
| LiveBench Reasoning | 87.8% | 50.8% |
| LMArena Hard Prompts | 1333 | 1257 |
| LiveBench Data Analysis | 74% | 49.5% |
| Epoch Capabilities Index | 141.16 | 127.33 |
| ForecastBench | 61.8 | 58.6 |
| LiveBench | 76.1% | 50.2% |
| ARC-AGI-2 | 0.9% | — |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 0% |
| EnigmaEval | 4.2% | — |
| DTBench | — | 59.5% |
| LMCA | — | 17.5% |
Math Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 37.5 (#153), Llama-3.3-70B-Instruct: 15.3 (#298)
| Benchmark | Claude 3.7 Sonnet | Llama-3.3-70B-Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 5.1% |
| LiveBench Math | 79% | 42.2% |
| LMArena Math | 1337 | 1267 |
| MATH Level 5 | 91.2% | 41.6% |
| Omni-MATH | 33% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 39.8 (#130), Llama-3.3-70B-Instruct: 30.6 (#226)
| Benchmark | Claude 3.7 Sonnet | Llama-3.3-70B-Instruct |
|---|---|---|
| GPQA Diamond | 79.7% | 47.4% |
| Confabulations | 14.7% | 22.8% |
| LMArena Expert | 1321 | 1225 |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Vectara Hallucination Rate | — | 4.1% |
| GPQA (HELM) | 60.8% | — |
| MMLU | — | 86.3% |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.7 (#95), Llama-3.3-70B-Instruct: —
| Benchmark | Claude 3.7 Sonnet | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 44.1 (#179), Llama-3.3-70B-Instruct: 39.9 (#220)
| Benchmark | Claude 3.7 Sonnet | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | 1296 | 1236 |
| LMArena Chinese | 1299 | 1217 |
| LMArena French | 1303 | 1281 |
| LMArena German | 1301 | 1251 |
| LMArena Japanese | 1267 | 1150 |
| LMArena Korean | 1249 | 1143 |
| LMArena Russian | 1311 | 1252 |
| LMArena Spanish | 1298 | 1270 |
Instruction Following Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 72.9 (#125), Llama-3.3-70B-Instruct: 71.1 (#157)
| Benchmark | Claude 3.7 Sonnet | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Instruction Following | 81.3% | 82.7% |
| LMArena Instruction Following | 1352 | 1242 |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Llama-3.3-70B-Instruct: 26.4 (#295)
| Benchmark | Claude 3.7 Sonnet | Llama-3.3-70B-Instruct |
|---|---|---|
| Fiction.LiveBench | 83.3% | 33.3% |
| LMArena Longer Query | 1373 | 1256 |
Writing & Preference Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 54.4 (#150), Llama-3.3-70B-Instruct: 47.6 (#207)
| Benchmark | Claude 3.7 Sonnet | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | 1314 | 1274 |
| LMArena Creative Writing | 1332 | 1250 |
| LMArena Multi-Turn | 1339 | 1280 |
| LiveBench Language | 59.9% | 39.2% |
| Short-Story Creative Writing | 81.1% | — |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | 81.4% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Llama-3.3-70B-Instruct?
Claude 3.7 Sonnet is the stronger model overall, scoring 39.5 to 30.6 on the Noometry Index.
Is Claude 3.7 Sonnet or Llama-3.3-70B-Instruct better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 40.6 versus 31.0 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Llama-3.3-70B-Instruct share?
32 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Llama-3.3-70B-Instruct has 43.