Model comparison
Claude 3.5 Haiku vs Claude Opus 4
Claude Opus 4 is the stronger model overall, scoring 43.1 to 29.2 on the Noometry Index.
Last verified . 36 shared benchmarks.
Summary
- They share 36 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Claude Opus 4 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4 leads 42.0 to 14.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku and 64.4% for Claude Opus 4.
Side by side
| Claude 3.5 Haiku | Claude Opus 4 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 29.2 | 43.1 |
| Released | 2024-10-22 | 2025-05-22 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 32K |
| Input $ / M tokens | — | $15 |
| Output $ / M tokens | — | $75 |
| Results tracked | 49 | 56 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude 3.5 Haiku: 32.9 (#265), Claude Opus 4: 47.2 (#62)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4 |
|---|---|---|
| Aider Polyglot | 28% | 72% |
| WeirdML | 30.7% | 43.7% |
| LMArena Coding | 1286 | 1442 |
| SWE-bench Verified | — | 70.7% |
| SWE-bench Verified (bash only) | — | 67.6% |
| SciCode | 27.4% | — |
| GSO | — | 6.9% |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
| AlgoTune | — | 1.33 |
Agentic & Tool Use Claude Opus 4 leads
Claude 3.5 Haiku: 28.0 (#95), Claude Opus 4: 34.8 (#42)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4 |
|---|---|---|
| Cybench | — | 38% |
| DeepResearch Bench | — | 46.8% |
| BALROG | 19.3% | — |
| LMArena Search | — | 1127 |
| METR Time Horizons | — | 63.9% |
Reasoning Claude Opus 4 leads
Claude 3.5 Haiku: 17.7 (#290), Claude Opus 4: 27.3 (#121)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4 |
|---|---|---|
| CritPt | 0% | 0.3% |
| LMArena Hard Prompts | 1251 | 1399 |
| DTBench | 56.7% | 81.6% |
| Epoch Capabilities Index | 127.15 | 142.67 |
| ARC-AGI-2 | — | 8.6% |
| SimpleBench | — | 58.8% |
| Kagi LLM Benchmark | — | 74.3% |
| ARC-AGI-1 | — | 35.7% |
| EnigmaEval | — | 5.6% |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 48.5% | — |
| LMCA | — | 37.4% |
| ForecastBench | — | 61.1 |
| LiveBench | 43.5% | — |
Math Claude Opus 4 leads
Claude 3.5 Haiku: 14.7 (#300), Claude Opus 4: 42.0 (#86)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 64.4% |
| Omni-MATH | 22.4% | 61.6% |
| LMArena Math | 1244 | 1390 |
| MATH Level 5 | 46.4% | 85% |
| FrontierMath (Feb 2025 set) | 0.3% | 4.5% |
| LiveBench Math | 35.5% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Claude Opus 4 leads
Claude 3.5 Haiku: 18.7 (#281), Claude Opus 4: 44.0 (#88)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4 |
|---|---|---|
| GPQA Diamond | 38.1% | 76.3% |
| MMLU-Pro | 60.5% | 87.5% |
| Confabulations | 36.7% | 15.9% |
| GPQA (HELM) | 36.3% | 70.8% |
| LMArena Expert | 1208 | 1386 |
| Humanity's Last Exam | — | 10.7% |
| Vectara Hallucination Rate | — | 12% |
| MMLU | 74.3% | — |
Multimodal Claude Opus 4 leads
Claude 3.5 Haiku: 26.8 (#117), Claude Opus 4: 31.5 (#106)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4 |
|---|---|---|
| LMArena Vision | 1092 | 1192 |
| GeoBench | 34% | 49% |
| VPCT | — | 38% |
Multilingual Claude Opus 4 leads
Claude 3.5 Haiku: 40.0 (#218), Claude Opus 4: 48.8 (#138)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4 |
|---|---|---|
| LMArena Non-English | 1238 | 1362 |
| LMArena Chinese | 1229 | 1386 |
| LMArena French | 1264 | 1372 |
| LMArena German | 1237 | 1391 |
| LMArena Japanese | 1175 | 1331 |
| LMArena Korean | 1173 | 1321 |
| LMArena Russian | 1253 | 1392 |
| LMArena Spanish | 1261 | 1389 |
Instruction Following Claude Opus 4 leads
Claude 3.5 Haiku: 62.9 (#234), Claude Opus 4: 77.1 (#28)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4 |
|---|---|---|
| IFEval | 79.2% | 91.8% |
| LMArena Instruction Following | 1241 | 1406 |
| LiveBench Instruction Following | 61.9% | — |
Long Context Claude Opus 4 leads
Claude 3.5 Haiku: 38.3 (#200), Claude Opus 4: 39.6 (#172)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4 |
|---|---|---|
| LMArena Longer Query | 1261 | 1422 |
| Fiction.LiveBench | — | 61.1% |
Writing & Preference Claude Opus 4 leads
Claude 3.5 Haiku: 42.7 (#234), Claude Opus 4: 61.2 (#89)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4 |
|---|---|---|
| LMArena Text | 1255 | 1377 |
| LMArena Creative Writing | 1233 | 1387 |
| Short-Story Creative Writing | 73.5% | 83.6% |
| EQ-Bench Creative Writing | 1146 | 1580 |
| WildBench | 76% | 85.2% |
| LMArena Multi-Turn | 1265 | 1396 |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Claude Opus 4?
Claude Opus 4 is the stronger model overall, scoring 43.1 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or Claude Opus 4 better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Claude Opus 4 share?
36 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Claude Opus 4 has 56.