Model comparison
Claude 3.5 Haiku vs Claude Sonnet 4.5
Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 29.2 on the Noometry Index.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Claude Sonnet 4.5 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Sonnet 4.5 leads 48.4 to 18.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku and 77.8% for Claude Sonnet 4.5.
Side by side
| Claude 3.5 Haiku | Claude Sonnet 4.5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 29.2 | 44.1 |
| Released | 2024-10-22 | 2025-09-29 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 64K |
| Input $ / M tokens | — | $3 |
| Output $ / M tokens | — | $15 |
| Results tracked | 49 | 73 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.5 leads
Claude 3.5 Haiku: 32.9 (#265), Claude Sonnet 4.5: 47.3 (#61)
| Benchmark | Claude 3.5 Haiku | Claude Sonnet 4.5 |
|---|---|---|
| SciCode | 27.4% | 44.7% |
| WeirdML | 30.7% | 47.7% |
| LMArena Coding | 1286 | 1489 |
| SWE-bench Verified | — | 71.3% |
| SWE-bench Verified (bash only) | — | 71.4% |
| Aider Polyglot | 28% | — |
| LMArena WebDev | — | 1393 |
| SWE-bench Multilingual | — | 67% |
| GSO | — | 14.7% |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
| ALE-Bench | — | 796.15 |
| AlgoTune | — | 1.52 |
Agentic & Tool Use Claude Sonnet 4.5 leads
Claude 3.5 Haiku: 28.0 (#95), Claude Sonnet 4.5: 38.3 (#32)
| Benchmark | Claude 3.5 Haiku | Claude Sonnet 4.5 |
|---|---|---|
| Terminal-Bench | — | 46.5% |
| Berkeley Function Calling Leaderboard | — | 73.2% |
| 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% |
| BALROG | 19.3% | — |
| LMArena Search | — | 1159 |
| METR Time Horizons | — | 67.4% |
| Vending-Bench 2 | — | 3,839 |
Reasoning Claude Sonnet 4.5 leads
Claude 3.5 Haiku: 17.7 (#290), Claude Sonnet 4.5: 26.9 (#125)
| Benchmark | Claude 3.5 Haiku | Claude Sonnet 4.5 |
|---|---|---|
| CritPt | 0% | 1.1% |
| LMArena Hard Prompts | 1251 | 1462 |
| DTBench | 56.7% | 83.2% |
| Epoch Capabilities Index | 127.15 | 146.84 |
| ARC-AGI-2 | — | 13.6% |
| SimpleBench | — | 54.3% |
| Kagi LLM Benchmark | — | 57.9% |
| NYT Connections (extended) | — | 37.3% |
| ARC-AGI-1 | — | 63.7% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 6% |
| EBR-Bench | — | 2.4% |
| LiveBench Reasoning | 28.1% | — |
| Mystery Game Puzzles | — | 17% |
| LiveBench Data Analysis | 48.5% | — |
| LMCA | — | 38.8% |
| ForecastBench | — | 61.9 |
| LiveBench | 43.5% | — |
Math Claude Sonnet 4.5 leads
Claude 3.5 Haiku: 14.7 (#300), Claude Sonnet 4.5: 32.3 (#216)
| Benchmark | Claude 3.5 Haiku | Claude Sonnet 4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 77.8% |
| Omni-MATH | 22.4% | 55.3% |
| LMArena Math | 1244 | 1449 |
| MATH Level 5 | 46.4% | 97.7% |
| FrontierMath (Feb 2025 set) | 0.3% | 15.2% |
| FrontierMath (Tiers 1-3) | — | 23.9% |
| FrontierMath Tier 4 | — | 2.4% |
| ProofBench | — | 19% |
| LiveBench Math | 35.5% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Claude Sonnet 4.5 leads
Claude 3.5 Haiku: 18.7 (#281), Claude Sonnet 4.5: 48.4 (#76)
| Benchmark | Claude 3.5 Haiku | Claude Sonnet 4.5 |
|---|---|---|
| GPQA Diamond | 38.1% | 82.3% |
| MMLU-Pro | 60.5% | 86.9% |
| GPQA (HELM) | 36.3% | 68.6% |
| LMArena Expert | 1208 | 1482 |
| Humanity's Last Exam | — | 13.7% |
| SimpleQA Verified | — | 30.7% |
| Confabulations | 36.7% | — |
| Vectara Hallucination Rate | — | 12% |
| MMLU | 74.3% | — |
Multimodal Claude Sonnet 4.5 leads
Claude 3.5 Haiku: 26.8 (#117), Claude Sonnet 4.5: 34.8 (#89)
| Benchmark | Claude 3.5 Haiku | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
| VPCT | — | 39.8% |
| LMArena Document | — | 1450 |
Multilingual Claude Sonnet 4.5 leads
Claude 3.5 Haiku: 40.0 (#218), Claude Sonnet 4.5: 53.4 (#69)
| Benchmark | Claude 3.5 Haiku | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Non-English | 1238 | 1425 |
| LMArena Chinese | 1229 | 1459 |
| LMArena French | 1264 | 1458 |
| LMArena German | 1237 | 1427 |
| LMArena Japanese | 1175 | 1390 |
| LMArena Korean | 1173 | 1403 |
| LMArena Russian | 1253 | 1437 |
| LMArena Spanish | 1261 | 1457 |
Instruction Following Claude Sonnet 4.5 leads
Claude 3.5 Haiku: 62.9 (#234), Claude Sonnet 4.5: 75.0 (#78)
| Benchmark | Claude 3.5 Haiku | Claude Sonnet 4.5 |
|---|---|---|
| IFEval | 79.2% | 85% |
| LMArena Instruction Following | 1241 | 1459 |
| LiveBench Instruction Following | 61.9% | — |
Long Context Claude Sonnet 4.5 leads
Claude 3.5 Haiku: 38.3 (#200), Claude Sonnet 4.5: 45.2 (#46)
| Benchmark | Claude 3.5 Haiku | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Longer Query | 1261 | 1476 |
Writing & Preference Claude Sonnet 4.5 leads
Claude 3.5 Haiku: 42.7 (#234), Claude Sonnet 4.5: 66.5 (#34)
| Benchmark | Claude 3.5 Haiku | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Text | 1255 | 1439 |
| LMArena Creative Writing | 1233 | 1442 |
| EQ-Bench Creative Writing | 1146 | 1678 |
| WildBench | 76% | 85.4% |
| LMArena Multi-Turn | 1265 | 1465 |
| Short-Story Creative Writing | 73.5% | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Claude Sonnet 4.5?
Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or Claude Sonnet 4.5 better for coding?
Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Claude Sonnet 4.5 share?
32 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Claude Sonnet 4.5 has 73.