Model comparison
Claude 3 Haiku vs Claude Opus 4.5
Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 25.9 on the Noometry Index.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Claude Opus 4.5 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Opus 4.5 leads 56.5 to 17.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 86.1% for Claude Opus 4.5.
Side by side
| Claude 3 Haiku | Claude Opus 4.5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 25.9 | 50.5 |
| Released | 2024-03-07 | 2025-11-01 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 64K |
| Input $ / M tokens | — | $5 |
| Output $ / M tokens | — | $25 |
| Results tracked | 37 | 69 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.5 leads
Claude 3 Haiku: 26.4 (#325), Claude Opus 4.5: 54.8 (#27)
| Benchmark | Claude 3 Haiku | Claude Opus 4.5 |
|---|---|---|
| WeirdML | 9.8% | 63.7% |
| LMArena Coding | 1199 | 1504 |
| SWE-bench Verified | — | 76.7% |
| SWE-bench Verified (bash only) | — | 76.8% |
| LMArena WebDev | — | 1494 |
| SWE-bench Multilingual | — | 70.7% |
| GSO | — | 26.5% |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| ALE-Bench | — | 1,025 |
| AlgoTune | — | 1.77 |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Agentic & Tool Use Not comparable
Claude 3 Haiku: —, Claude Opus 4.5: 47.3 (#12)
| Benchmark | Claude 3 Haiku | Claude Opus 4.5 |
|---|---|---|
| Terminal-Bench | — | 63.1% |
| Berkeley Function Calling Leaderboard | — | 77.5% |
| GDPval | — | 45.5% |
| Remote Labor Index | — | 3.8% |
| τ²-bench Airline | — | 84% |
| τ²-bench Banking | — | 24.7% |
| τ²-bench Retail | — | 79.6% |
| τ²-bench Telecom | — | 92.3% |
| Cybench | — | 82% |
| DeepResearch Bench | — | 54.8% |
| OSWorld | — | 66.3% |
| BALROG | — | 43.5% |
| LMArena Search | — | 1180 |
| METR Time Horizons | — | 75% |
| Vending-Bench 2 | — | 4,967 |
Reasoning Claude Opus 4.5 leads
Claude 3 Haiku: 16.3 (#307), Claude Opus 4.5: 42.6 (#51)
| Benchmark | Claude 3 Haiku | Claude Opus 4.5 |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 80.2% |
| LMArena Hard Prompts | 1174 | 1476 |
| DTBench | 50.1% | 89.9% |
| LMCA | 8.8% | 44.5% |
| Epoch Capabilities Index | 118.35 | 150.09 |
| ForecastBench | 53.2 | 60.7 |
| ARC-AGI-2 | — | 37.6% |
| SimpleBench | — | 62% |
| NYT Connections (extended) | — | 52.5% |
| ARC-AGI-1 | — | 80% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 11.9% |
| EBR-Bench | — | 14.3% |
| Mystery Game Puzzles | — | 22% |
| WinoGrande | 74.2% | — |
Math Claude Opus 4.5 leads
Claude 3 Haiku: 9.8 (#319), Claude Opus 4.5: 38.6 (#132)
| Benchmark | Claude 3 Haiku | Claude Opus 4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 86.1% |
| LMArena Math | 1188 | 1463 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| FrontierMath Tier 4 | — | 4.9% |
| ProofBench | — | 36% |
| MATH Level 5 | 14.9% | — |
| FrontierMath (Feb 2025 set) | — | 20.7% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Claude Opus 4.5 leads
Claude 3 Haiku: 17.3 (#285), Claude Opus 4.5: 56.5 (#44)
| Benchmark | Claude 3 Haiku | Claude Opus 4.5 |
|---|---|---|
| GPQA Diamond | 36.3% | 86% |
| LMArena Expert | 1148 | 1487 |
| Humanity's Last Exam | — | 25.2% |
| SimpleQA Verified | — | 45.7% |
| Confabulations | 34.2% | — |
| Vectara Hallucination Rate | — | 10.9% |
| MMLU | 73.8% | — |
Multimodal Claude Opus 4.5 leads
Claude 3 Haiku: 23.6 (#128), Claude Opus 4.5: 31.4 (#107)
| Benchmark | Claude 3 Haiku | Claude Opus 4.5 |
|---|---|---|
| LMArena Vision | 950 | — |
| GeoBench | — | 75% |
| VPCT | — | 40% |
| Furniture Assembly | — | 28.3% |
| LMArena Document | — | 1462 |
| ScienceQA | 72% | — |
Multilingual Claude Opus 4.5 leads
Claude 3 Haiku: 36.0 (#243), Claude Opus 4.5: 54.3 (#47)
| Benchmark | Claude 3 Haiku | Claude Opus 4.5 |
|---|---|---|
| LMArena Non-English | 1178 | 1438 |
| LMArena Chinese | 1155 | 1470 |
| LMArena French | 1195 | 1471 |
| LMArena German | 1174 | 1449 |
| LMArena Japanese | 1102 | 1416 |
| LMArena Korean | 1109 | 1424 |
| LMArena Russian | 1204 | 1447 |
| LMArena Spanish | 1166 | 1458 |
Instruction Following Claude Opus 4.5 leads
Claude 3 Haiku: 61.3 (#247), Claude Opus 4.5: 77.5 (#19)
| Benchmark | Claude 3 Haiku | Claude Opus 4.5 |
|---|---|---|
| LMArena Instruction Following | 1173 | 1478 |
Long Context Claude Opus 4.5 leads
Claude 3 Haiku: 36.1 (#237), Claude Opus 4.5: 46.5 (#22)
| Benchmark | Claude 3 Haiku | Claude Opus 4.5 |
|---|---|---|
| LMArena Longer Query | 1190 | 1480 |
| CL-bench | — | 21.1% |
Writing & Preference Claude Opus 4.5 leads
Claude 3 Haiku: 29.7 (#291), Claude Opus 4.5: 68.1 (#28)
| Benchmark | Claude 3 Haiku | Claude Opus 4.5 |
|---|---|---|
| LMArena Text | 1195 | 1451 |
| LMArena Creative Writing | 1157 | 1445 |
| EQ-Bench Creative Writing | 717 | 1687 |
| LMArena Multi-Turn | 1190 | 1466 |
Frequently asked questions
Is Claude 3 Haiku better than Claude Opus 4.5?
Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Claude Opus 4.5 better for coding?
Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Claude Opus 4.5 share?
26 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Claude Opus 4.5 has 69.