Model comparison
Claude 3.5 Haiku vs Claude 3 Sonnet
Claude 3.5 Haiku and Claude 3 Sonnet score almost the same on the Noometry Index (29.2 vs 29.0), so choose on price, context window or the category you care about most.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 7 categories and Claude 3 Sonnet in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude 3.5 Haiku leads 14.7 to 10.7.
- The biggest single-benchmark swing is MATH Level 5: 46.4% for Claude 3.5 Haiku and 18.2% for Claude 3 Sonnet.
Side by side
| Claude 3.5 Haiku | Claude 3 Sonnet | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 29.2 | 29.0 |
| Released | 2024-10-22 | 2024-02-29 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 49 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Haiku leads
Claude 3.5 Haiku: 32.9 (#265), Claude 3 Sonnet: 29.6 (#302)
| Benchmark | Claude 3.5 Haiku | Claude 3 Sonnet |
|---|---|---|
| WeirdML | 30.7% | 10.2% |
| BigCodeBench Instruct | 46.1% | 42.7% |
| LMArena Coding | 1286 | 1223 |
| BigCodeBench Complete | 59% | 53.8% |
| Aider Polyglot | 28% | — |
| SciCode | 27.4% | — |
| LiveBench Coding | 51.4% | — |
| CadEval | 32% | — |
| HumanEval+ | — | 64% |
| MBPP+ | — | 69.3% |
Agentic & Tool Use Not comparable
Claude 3.5 Haiku: 28.0 (#95), Claude 3 Sonnet: —
| Benchmark | Claude 3.5 Haiku | Claude 3 Sonnet |
|---|---|---|
| BALROG | 19.3% | — |
Reasoning Claude 3 Sonnet leads
Claude 3.5 Haiku: 17.7 (#290), Claude 3 Sonnet: 20.5 (#237)
| Benchmark | Claude 3.5 Haiku | Claude 3 Sonnet |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1197 |
| DTBench | 56.7% | 53.6% |
| Epoch Capabilities Index | 127.15 | 120.7 |
| CritPt | 0% | — |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 48.5% | — |
| LiveBench | 43.5% | — |
| WinoGrande | — | 75.1% |
Math Claude 3.5 Haiku leads
Claude 3.5 Haiku: 14.7 (#300), Claude 3 Sonnet: 10.7 (#310)
| Benchmark | Claude 3.5 Haiku | Claude 3 Sonnet |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 2.5% |
| LMArena Math | 1244 | 1213 |
| MATH Level 5 | 46.4% | 18.2% |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Claude 3 Sonnet leads
Claude 3.5 Haiku: 18.7 (#281), Claude 3 Sonnet: 21.1 (#276)
| Benchmark | Claude 3.5 Haiku | Claude 3 Sonnet |
|---|---|---|
| GPQA Diamond | 38.1% | 40.6% |
| LMArena Expert | 1208 | 1173 |
| MMLU | 74.3% | 75.9% |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
Multimodal Claude 3.5 Haiku leads
Claude 3.5 Haiku: 26.8 (#117), Claude 3 Sonnet: 25.2 (#125)
| Benchmark | Claude 3.5 Haiku | Claude 3 Sonnet |
|---|---|---|
| LMArena Vision | 1092 | 984 |
| GeoBench | 34% | — |
Multilingual Claude 3.5 Haiku leads
Claude 3.5 Haiku: 40.0 (#218), Claude 3 Sonnet: 37.8 (#234)
| Benchmark | Claude 3.5 Haiku | Claude 3 Sonnet |
|---|---|---|
| LMArena Non-English | 1238 | 1205 |
| LMArena Chinese | 1229 | 1189 |
| LMArena French | 1264 | 1229 |
| LMArena German | 1237 | 1204 |
| LMArena Japanese | 1175 | 1131 |
| LMArena Korean | 1173 | 1128 |
| LMArena Russian | 1253 | 1227 |
| LMArena Spanish | 1261 | 1204 |
Instruction Following Too close to call
Claude 3.5 Haiku: 62.9 (#234), Claude 3 Sonnet: 62.8 (#235)
| Benchmark | Claude 3.5 Haiku | Claude 3 Sonnet |
|---|---|---|
| LMArena Instruction Following | 1241 | 1199 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context Claude 3.5 Haiku leads
Claude 3.5 Haiku: 38.3 (#200), Claude 3 Sonnet: 36.7 (#228)
| Benchmark | Claude 3.5 Haiku | Claude 3 Sonnet |
|---|---|---|
| LMArena Longer Query | 1261 | 1211 |
Writing & Preference Too close to call
Claude 3.5 Haiku: 42.7 (#234), Claude 3 Sonnet: 42.1 (#238)
| Benchmark | Claude 3.5 Haiku | Claude 3 Sonnet |
|---|---|---|
| LMArena Text | 1255 | 1218 |
| LMArena Creative Writing | 1233 | 1186 |
| LMArena Multi-Turn | 1265 | 1227 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Claude 3 Sonnet?
Claude 3.5 Haiku and Claude 3 Sonnet score almost the same on the Noometry Index (29.2 vs 29.0), so choose on price, context window or the category you care about most.
Is Claude 3.5 Haiku or Claude 3 Sonnet better for coding?
Claude 3.5 Haiku scores higher on coding benchmarks: 32.9 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Claude 3 Sonnet share?
27 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Claude 3 Sonnet has 30.