Model comparison
Claude Sonnet 5 vs Nova 2 Lite
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 39.7 on the Noometry Index. Nova 2 Lite costs 4.7× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Claude Sonnet 5 scores higher in 9 categories and Nova 2 Lite in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 37.5.
- Nova 2 Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
Side by side
| Claude Sonnet 5 | Nova 2 Lite | |
|---|---|---|
| Provider | Anthropic | Amazon |
| Noometry Index | 54.6 | 39.7 |
| Released | 2026-06-29 | 2025-12-01 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 128K | 64K |
| Input $ / M tokens | $2 | $0.30 |
| Output $ / M tokens | $10 | $2.50 |
| Results tracked | 51 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), Nova 2 Lite: 40.7 (#134)
| Benchmark | Claude Sonnet 5 | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1483 | 1385 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |
| ALE-Bench | 1,463 | — |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.8 (#18), Nova 2 Lite: 24.1 (#121)
| Benchmark | Claude Sonnet 5 | Nova 2 Lite |
|---|---|---|
| APEX-Agents | 54.5% | — |
| Berkeley Function Calling Leaderboard | — | 27.1% |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), Nova 2 Lite: 27.5 (#118)
| Benchmark | Claude Sonnet 5 | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1364 |
| SimpleBench | 60.6% | — |
| NYT Connections (extended) | 75.1% | — |
| CritPt | 16.9% | — |
| Chess Puzzles | 35% | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 92.5% | — |
| LMCA | 50% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| Epoch Capabilities Index | 156.21 | — |
| ForecastBench | 61.1 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), Nova 2 Lite: 37.5 (#156)
| Benchmark | Claude Sonnet 5 | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1467 | 1359 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 94.7% | — |
| ProofBench | 77% | — |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.6 (#47), Nova 2 Lite: 43.0 (#94)
| Benchmark | Claude Sonnet 5 | Nova 2 Lite |
|---|---|---|
| LMArena Expert | 1490 | 1358 |
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 33.7% | — |
| Vectara Hallucination Rate | — | 5.1% |
Multimodal Not comparable
Claude Sonnet 5: 42.4 (#31), Nova 2 Lite: —
| Benchmark | Claude Sonnet 5 | Nova 2 Lite |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Claude Sonnet 5 leads
Claude Sonnet 5: 53.8 (#55), Nova 2 Lite: 47.1 (#153)
| Benchmark | Claude Sonnet 5 | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1431 | 1337 |
| LMArena Chinese | 1477 | 1364 |
| LMArena French | 1460 | 1381 |
| LMArena German | 1440 | 1343 |
| LMArena Japanese | 1422 | 1271 |
| LMArena Korean | 1411 | 1284 |
| LMArena Russian | 1451 | 1343 |
| LMArena Spanish | 1437 | 1373 |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.3 (#41), Nova 2 Lite: 70.5 (#161)
| Benchmark | Claude Sonnet 5 | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1452 | 1335 |
Long Context Claude Sonnet 5 leads
Claude Sonnet 5: 44.8 (#55), Nova 2 Lite: 40.6 (#150)
| Benchmark | Claude Sonnet 5 | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1463 | 1335 |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), Nova 2 Lite: 53.9 (#154)
| Benchmark | Claude Sonnet 5 | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1442 | 1362 |
| LMArena Creative Writing | 1416 | 1291 |
| LMArena Multi-Turn | 1454 | 1338 |
| EQ-Bench Creative Writing | 1794 | — |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than Nova 2 Lite?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 39.7 on the Noometry Index. Nova 2 Lite costs 4.7× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 5 or Nova 2 Lite?
Nova 2 Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or Nova 2 Lite better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 40.7 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Sonnet 5 and Nova 2 Lite share?
17 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Nova 2 Lite has 19.