Model comparison
Claude 3.7 Sonnet vs Nova 2 Lite
Claude 3.7 Sonnet and Nova 2 Lite score almost the same on the Noometry Index (39.5 vs 39.7), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 4 categories and Nova 2 Lite in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude 3.7 Sonnet leads 34.1 to 24.1.
Side by side
| Claude 3.7 Sonnet | Nova 2 Lite | |
|---|---|---|
| Provider | Anthropic | Amazon |
| Noometry Index | 39.5 | 39.7 |
| Released | 2025-02-24 | 2025-12-01 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 64K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 58 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3.7 Sonnet: 40.6 (#136), Nova 2 Lite: 40.7 (#134)
| Benchmark | Claude 3.7 Sonnet | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1361 | 1385 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 34.1 (#50), Nova 2 Lite: 24.1 (#121)
| Benchmark | Claude 3.7 Sonnet | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Nova 2 Lite leads
Claude 3.7 Sonnet: 18.6 (#277), Nova 2 Lite: 27.5 (#118)
| Benchmark | Claude 3.7 Sonnet | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1364 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| ARC-AGI-1 | 28.6% | — |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| LiveBench Data Analysis | 74% | — |
| Epoch Capabilities Index | 141.16 | — |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Too close to call
Claude 3.7 Sonnet: 37.5 (#153), Nova 2 Lite: 37.5 (#156)
| Benchmark | Claude 3.7 Sonnet | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1337 | 1359 |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Nova 2 Lite leads
Claude 3.7 Sonnet: 39.8 (#130), Nova 2 Lite: 43.0 (#94)
| Benchmark | Claude 3.7 Sonnet | Nova 2 Lite |
|---|---|---|
| LMArena Expert | 1321 | 1358 |
| GPQA Diamond | 79.7% | — |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| Vectara Hallucination Rate | — | 5.1% |
| GPQA (HELM) | 60.8% | — |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.7 (#95), Nova 2 Lite: —
| Benchmark | Claude 3.7 Sonnet | Nova 2 Lite |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Nova 2 Lite leads
Claude 3.7 Sonnet: 44.1 (#179), Nova 2 Lite: 47.1 (#153)
| Benchmark | Claude 3.7 Sonnet | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1296 | 1337 |
| LMArena Chinese | 1299 | 1364 |
| LMArena French | 1303 | 1381 |
| LMArena German | 1301 | 1343 |
| LMArena Japanese | 1267 | 1271 |
| LMArena Korean | 1249 | 1284 |
| LMArena Russian | 1311 | 1343 |
| LMArena Spanish | 1298 | 1373 |
Instruction Following Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 72.9 (#125), Nova 2 Lite: 70.5 (#161)
| Benchmark | Claude 3.7 Sonnet | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1352 | 1335 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Nova 2 Lite: 40.6 (#150)
| Benchmark | Claude 3.7 Sonnet | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1373 | 1335 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Too close to call
Claude 3.7 Sonnet: 54.4 (#150), Nova 2 Lite: 53.9 (#154)
| Benchmark | Claude 3.7 Sonnet | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1314 | 1362 |
| LMArena Creative Writing | 1332 | 1291 |
| LMArena Multi-Turn | 1339 | 1338 |
| Short-Story Creative Writing | 81.1% | — |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Nova 2 Lite?
Claude 3.7 Sonnet and Nova 2 Lite score almost the same on the Noometry Index (39.5 vs 39.7), so choose on price, context window or the category you care about most.
Is Claude 3.7 Sonnet or Nova 2 Lite better for coding?
They score almost the same on coding (40.6 vs 40.7); test both on your own repository before choosing.
How many benchmarks do Claude 3.7 Sonnet and Nova 2 Lite share?
17 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Nova 2 Lite has 19.