Model comparison
Claude 3.5 Haiku vs Claude Opus 4.1
Claude Opus 4.1 is the stronger model overall, scoring 41.0 to 29.2 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Claude Opus 4.1 in 10 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Opus 4.1 leads 42.0 to 18.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku and 68.9% for Claude Opus 4.1.
Side by side
| Claude 3.5 Haiku | Claude Opus 4.1 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 29.2 | 41.0 |
| Released | 2024-10-22 | 2025-08-05 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 32K |
| Input $ / M tokens | — | $15 |
| Output $ / M tokens | — | $75 |
| Results tracked | 49 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.1 leads
Claude 3.5 Haiku: 32.9 (#265), Claude Opus 4.1: 44.4 (#73)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.1 |
|---|---|---|
| WeirdML | 30.7% | 45.9% |
| LMArena Coding | 1286 | 1479 |
| SWE-bench Verified | — | 73.3% |
| Aider Polyglot | 28% | — |
| LMArena WebDev | — | 1390 |
| SciCode | 27.4% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
| ALE-Bench | — | 674.77 |
| AlgoTune | — | 1.34 |
Agentic & Tool Use Claude Opus 4.1 leads
Claude 3.5 Haiku: 28.0 (#95), Claude Opus 4.1: 35.0 (#41)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.1 |
|---|---|---|
| Terminal-Bench | — | 38% |
| GDPval | — | 43.6% |
| Cybench | — | 42% |
| DeepResearch Bench | — | 48.3% |
| BALROG | 19.3% | — |
| LMArena Search | — | 1148 |
| METR Time Horizons | — | 66.8% |
Reasoning Claude Opus 4.1 leads
Claude 3.5 Haiku: 17.7 (#290), Claude Opus 4.1: 32.2 (#76)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.1 |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1443 |
| DTBench | 56.7% | 80% |
| Epoch Capabilities Index | 127.15 | 144.12 |
| SimpleBench | — | 60% |
| CritPt | 0% | — |
| Chess Puzzles | — | 7% |
| EnigmaEval | — | 7.2% |
| EBR-Bench | — | 7.9% |
| LiveBench Reasoning | 28.1% | — |
| Mystery Game Puzzles | — | 21% |
| LiveBench Data Analysis | 48.5% | — |
| LMCA | — | 37.1% |
| ForecastBench | — | 62 |
| LiveBench | 43.5% | — |
Math Claude Opus 4.1 leads
Claude 3.5 Haiku: 14.7 (#300), Claude Opus 4.1: 22.3 (#277)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 68.9% |
| LMArena Math | 1244 | 1431 |
| FrontierMath (Feb 2025 set) | 0.3% | 7.2% |
| FrontierMath (Tiers 1-3) | — | 12.6% |
| FrontierMath Tier 4 | — | 2.4% |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Claude Opus 4.1 leads
Claude 3.5 Haiku: 18.7 (#281), Claude Opus 4.1: 42.0 (#101)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.1 |
|---|---|---|
| GPQA Diamond | 38.1% | 77.3% |
| Confabulations | 36.7% | 17.1% |
| LMArena Expert | 1208 | 1439 |
| Humanity's Last Exam | — | 11.5% |
| MMLU-Pro | 60.5% | — |
| Vectara Hallucination Rate | — | 11.8% |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |
Multimodal Too close to call
Claude 3.5 Haiku: 26.8 (#117), Claude Opus 4.1: 26.8 (#119)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.1 |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
| VPCT | — | 35% |
Multilingual Claude Opus 4.1 leads
Claude 3.5 Haiku: 40.0 (#218), Claude Opus 4.1: 52.0 (#95)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.1 |
|---|---|---|
| LMArena Non-English | 1238 | 1405 |
| LMArena Chinese | 1229 | 1427 |
| LMArena French | 1264 | 1431 |
| LMArena German | 1237 | 1413 |
| LMArena Japanese | 1175 | 1378 |
| LMArena Korean | 1173 | 1380 |
| LMArena Russian | 1253 | 1422 |
| LMArena Spanish | 1261 | 1448 |
Instruction Following Claude Opus 4.1 leads
Claude 3.5 Haiku: 62.9 (#234), Claude Opus 4.1: 75.6 (#58)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.1 |
|---|---|---|
| LMArena Instruction Following | 1241 | 1435 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context Claude Opus 4.1 leads
Claude 3.5 Haiku: 38.3 (#200), Claude Opus 4.1: 44.5 (#63)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.1 |
|---|---|---|
| LMArena Longer Query | 1261 | 1455 |
Writing & Preference Claude Opus 4.1 leads
Claude 3.5 Haiku: 42.7 (#234), Claude Opus 4.1: 62.4 (#74)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.1 |
|---|---|---|
| LMArena Text | 1255 | 1419 |
| LMArena Creative Writing | 1233 | 1412 |
| Short-Story Creative Writing | 73.5% | 84.7% |
| LMArena Multi-Turn | 1265 | 1444 |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Claude Opus 4.1?
Claude Opus 4.1 is the stronger model overall, scoring 41.0 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or Claude Opus 4.1 better for coding?
Claude Opus 4.1 scores higher on coding benchmarks: 44.4 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Claude Opus 4.1 share?
25 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Claude Opus 4.1 has 48.