Model comparison
Claude 3.5 Sonnet vs Claude 3 Haiku
Claude 3.5 Sonnet is the stronger model overall, scoring 34.4 to 25.7 on the Noometry Index.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 9 categories and Claude 3 Haiku in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude 3.5 Sonnet leads 53.0 to 29.8.
- The biggest single-benchmark swing is MATH Level 5: 56.9% for Claude 3.5 Sonnet and 14.9% for Claude 3 Haiku.
Side by side
| Claude 3.5 Sonnet | Claude 3 Haiku | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 34.4 | 25.7 |
| Released | 2024-06-20 | 2024-03-07 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 60 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.5 (#145), Claude 3 Haiku: 26.1 (#320)
| Benchmark | Claude 3.5 Sonnet | Claude 3 Haiku |
|---|---|---|
| WeirdML | 40% | 9.8% |
| BigCodeBench Instruct | 46.8% | 39.4% |
| LMArena Coding | 1343 | 1199 |
| BigCodeBench Complete | 58.6% | 50.1% |
| CadEval | 48% | 12% |
| HumanEval+ | 81.7% | 68.9% |
| MBPP+ | 74.3% | 68.8% |
| Aider Polyglot | 51.6% | — |
| GSO | 4.6% | — |
| LiveBench Coding | 67.1% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.1 (#61), Claude 3 Haiku: —
| Benchmark | Claude 3.5 Sonnet | Claude 3 Haiku |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 22.5 (#176), Claude 3 Haiku: 15.7 (#303)
| Benchmark | Claude 3.5 Sonnet | Claude 3 Haiku |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1174 |
| DTBench | 67.8% | 50.1% |
| Epoch Capabilities Index | 133.55 | 118.3 |
| ForecastBench | 60.7 | 53.2 |
| SimpleBench | 41.4% | — |
| Kagi LLM Benchmark | — | 34.2% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 8.8% |
| LiveBench | 59% | — |
| WinoGrande | — | 74.2% |
Math Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 18.0 (#282), Claude 3 Haiku: 9.2 (#313)
| Benchmark | Claude 3.5 Sonnet | Claude 3 Haiku |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 1.8% |
| LMArena Math | 1306 | 1188 |
| MATH Level 5 | 56.9% | 14.9% |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 28.5 (#236), Claude 3 Haiku: 17.3 (#280)
| Benchmark | Claude 3.5 Sonnet | Claude 3 Haiku |
|---|---|---|
| GPQA Diamond | 55.3% | 36.3% |
| Confabulations | 19.9% | 34.2% |
| LMArena Expert | 1264 | 1148 |
| MMLU | 87.3% | 73.8% |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| GPQA (HELM) | 56.5% | — |
Multimodal Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 26.0 (#115), Claude 3 Haiku: 23.1 (#123)
| Benchmark | Claude 3.5 Sonnet | Claude 3 Haiku |
|---|---|---|
| LMArena Vision | 1125 | 950 |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
| ScienceQA | — | 72% |
Multilingual Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 43.4 (#180), Claude 3 Haiku: 36.1 (#238)
| Benchmark | Claude 3.5 Sonnet | Claude 3 Haiku |
|---|---|---|
| LMArena Non-English | 1283 | 1178 |
| LMArena Chinese | 1271 | 1155 |
| LMArena French | 1304 | 1194 |
| LMArena German | 1297 | 1174 |
| LMArena Japanese | 1234 | 1102 |
| LMArena Korean | 1200 | 1108 |
| LMArena Russian | 1305 | 1204 |
| LMArena Spanish | 1289 | 1165 |
Instruction Following Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 69.0 (#177), Claude 3 Haiku: 61.5 (#242)
| Benchmark | Claude 3.5 Sonnet | Claude 3 Haiku |
|---|---|---|
| LMArena Instruction Following | 1297 | 1174 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.9 (#162), Claude 3 Haiku: 36.1 (#232)
| Benchmark | Claude 3.5 Sonnet | Claude 3 Haiku |
|---|---|---|
| LMArena Longer Query | 1311 | 1191 |
Writing & Preference Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 53.0 (#159), Claude 3 Haiku: 29.8 (#286)
| Benchmark | Claude 3.5 Sonnet | Claude 3 Haiku |
|---|---|---|
| LMArena Text | 1298 | 1195 |
| LMArena Creative Writing | 1292 | 1157 |
| EQ-Bench Creative Writing | 1451 | 717 |
| LMArena Multi-Turn | 1326 | 1190 |
| Short-Story Creative Writing | 80.3% | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Claude 3 Haiku?
Claude 3.5 Sonnet is the stronger model overall, scoring 34.4 to 25.7 on the Noometry Index.
Is Claude 3.5 Sonnet or Claude 3 Haiku better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.5 versus 26.1 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Claude 3 Haiku share?
33 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Claude 3 Haiku has 37.