Model comparison
Claude Sonnet 4.5 vs Nova 2 Lite
Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 39.7 on the Noometry Index. Nova 2 Lite costs 7.1× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 7 categories and Nova 2 Lite in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Sonnet 4.5 leads 38.3 to 24.1.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 73.2% for Claude Sonnet 4.5 and 27.1% for Nova 2 Lite.
- Nova 2 Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- Nova 2 Lite accepts more context: 1M tokens versus 200K.
Side by side
| Claude Sonnet 4.5 | Nova 2 Lite | |
|---|---|---|
| Provider | Anthropic | Amazon |
| Noometry Index | 44.1 | 39.7 |
| Released | 2025-09-29 | 2025-12-01 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1M |
| Max output | 64K | 64K |
| Input $ / M tokens | $3 | $0.30 |
| Output $ / M tokens | $15 | $2.50 |
| Results tracked | 73 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 47.3 (#61), Nova 2 Lite: 40.7 (#134)
| Benchmark | Claude Sonnet 4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1489 | 1385 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| LMArena WebDev | 1393 | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| WeirdML | 47.7% | — |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 38.3 (#32), Nova 2 Lite: 24.1 (#121)
| Benchmark | Claude Sonnet 4.5 | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | 73.2% | 27.1% |
| Terminal-Bench | 46.5% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning Too close to call
Claude Sonnet 4.5: 26.9 (#125), Nova 2 Lite: 27.5 (#118)
| Benchmark | Claude Sonnet 4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1462 | 1364 |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| Kagi LLM Benchmark | 57.9% | — |
| NYT Connections (extended) | 37.3% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |
| DTBench | 83.2% | — |
| LMCA | 38.8% | — |
| Epoch Capabilities Index | 146.84 | — |
| ForecastBench | 61.9 | — |
Math Nova 2 Lite leads
Claude Sonnet 4.5: 32.3 (#216), Nova 2 Lite: 37.5 (#156)
| Benchmark | Claude Sonnet 4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1449 | 1359 |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| ProofBench | 19% | — |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 48.4 (#76), Nova 2 Lite: 43.0 (#94)
| Benchmark | Claude Sonnet 4.5 | Nova 2 Lite |
|---|---|---|
| Vectara Hallucination Rate | 12% | 5.1% |
| LMArena Expert | 1482 | 1358 |
| GPQA Diamond | 82.3% | — |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| GPQA (HELM) | 68.6% | — |
Multimodal Not comparable
Claude Sonnet 4.5: 34.8 (#89), Nova 2 Lite: —
| Benchmark | Claude Sonnet 4.5 | Nova 2 Lite |
|---|---|---|
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |
Multilingual Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 53.4 (#69), Nova 2 Lite: 47.1 (#153)
| Benchmark | Claude Sonnet 4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1425 | 1337 |
| LMArena Chinese | 1459 | 1364 |
| LMArena French | 1458 | 1381 |
| LMArena German | 1427 | 1343 |
| LMArena Japanese | 1390 | 1271 |
| LMArena Korean | 1403 | 1284 |
| LMArena Russian | 1437 | 1343 |
| LMArena Spanish | 1457 | 1373 |
Instruction Following Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 75.0 (#78), Nova 2 Lite: 70.5 (#161)
| Benchmark | Claude Sonnet 4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1459 | 1335 |
| IFEval | 85% | — |
Long Context Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 45.2 (#46), Nova 2 Lite: 40.6 (#150)
| Benchmark | Claude Sonnet 4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1476 | 1335 |
Writing & Preference Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 66.5 (#34), Nova 2 Lite: 53.9 (#154)
| Benchmark | Claude Sonnet 4.5 | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1439 | 1362 |
| LMArena Creative Writing | 1442 | 1291 |
| LMArena Multi-Turn | 1465 | 1338 |
| EQ-Bench Creative Writing | 1678 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is Claude Sonnet 4.5 better than Nova 2 Lite?
Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 39.7 on the Noometry Index. Nova 2 Lite costs 7.1× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4.5 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 4.5 lists at $3 and $15.
Is Claude Sonnet 4.5 or Nova 2 Lite better for coding?
Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 40.7 in the Noometry coding category.
Which has the bigger context window?
Nova 2 Lite does, with 1M tokens against 200K.
How many benchmarks do Claude Sonnet 4.5 and Nova 2 Lite share?
19 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Nova 2 Lite has 19.