Model comparison
Claude 3 Opus vs Claude Haiku 4.5
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 29.5 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Claude 3 Opus scores higher in 1 category and Claude Haiku 4.5 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 4.5 leads 44.9 to 14.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 66.7% for Claude Haiku 4.5.
Side by side
| Claude 3 Opus | Claude Haiku 4.5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 29.5 | 39.5 |
| Released | 2024-02-29 | 2025-10-15 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 64K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $5 |
| Results tracked | 46 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 4.5 leads
Claude 3 Opus: 32.9 (#267), Claude Haiku 4.5: 44.0 (#78)
| Benchmark | Claude 3 Opus | Claude Haiku 4.5 |
|---|---|---|
| WeirdML | 19.2% | 45.4% |
| LMArena Coding | 1264 | 1453 |
| SWE-bench Verified (bash only) | — | 66.6% |
| LMArena WebDev | — | 1330 |
| SWE-bench Multilingual | — | 64.7% |
| SciCode | — | 43.3% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 653.48 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Claude Haiku 4.5 leads
Claude 3 Opus: 24.6 (#116), Claude Haiku 4.5: 33.6 (#52)
| Benchmark | Claude 3 Opus | Claude Haiku 4.5 |
|---|---|---|
| Terminal-Bench | — | 35.5% |
| Berkeley Function Calling Leaderboard | — | 68.7% |
| Cybench | 10% | — |
| DeepResearch Bench | — | 45.5% |
| BALROG | — | 31.2% |
| ExploitBench | — | 13.7% |
| METR Time Horizons | 29.5% | — |
| Vending-Bench 2 | — | 458.89 |
Reasoning Too close to call
Claude 3 Opus: 14.6 (#324), Claude Haiku 4.5: 15.1 (#320)
| Benchmark | Claude 3 Opus | Claude Haiku 4.5 |
|---|---|---|
| Chess Puzzles | 5% | 8% |
| LMArena Hard Prompts | 1245 | 1420 |
| DTBench | 61.6% | 73.6% |
| LMCA | 17% | 30.9% |
| Epoch Capabilities Index | 126.91 | 142.41 |
| ForecastBench | 58.4 | 61.4 |
| ARC-AGI-2 | — | 4% |
| SimpleBench | 23.5% | — |
| NYT Connections (extended) | — | 14.3% |
| ARC-AGI-1 | — | 47.7% |
| CritPt | — | 0% |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Claude Haiku 4.5 leads
Claude 3 Opus: 14.8 (#299), Claude Haiku 4.5: 44.9 (#78)
| Benchmark | Claude 3 Opus | Claude Haiku 4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 66.7% |
| LMArena Math | 1273 | 1396 |
| MATH Level 5 | 37.5% | 96.4% |
| Omni-MATH | — | 56.1% |
| LiveBench Math | 43.6% | — |
| FrontierMath (Feb 2025 set) | — | 5.9% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Claude Haiku 4.5 leads
Claude 3 Opus: 24.5 (#267), Claude Haiku 4.5: 37.7 (#153)
| Benchmark | Claude 3 Opus | Claude Haiku 4.5 |
|---|---|---|
| GPQA Diamond | 47.2% | 71.2% |
| SimpleQA Verified | 12.6% | 13.2% |
| LMArena Expert | 1223 | 1442 |
| MMLU-Pro | — | 77.7% |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 9.8% |
| GPQA (HELM) | — | 60.5% |
| MMLU | 84.6% | — |
Multimodal Too close to call
Claude 3 Opus: 27.1 (#116), Claude Haiku 4.5: 26.8 (#118)
| Benchmark | Claude 3 Opus | Claude Haiku 4.5 |
|---|---|---|
| LMArena Vision | 1023 | — |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1420 |
Multilingual Claude Haiku 4.5 leads
Claude 3 Opus: 41.4 (#207), Claude Haiku 4.5: 49.9 (#129)
| Benchmark | Claude 3 Opus | Claude Haiku 4.5 |
|---|---|---|
| LMArena Non-English | 1258 | 1377 |
| LMArena Chinese | 1248 | 1417 |
| LMArena French | 1275 | 1408 |
| LMArena German | 1258 | 1375 |
| LMArena Japanese | 1204 | 1339 |
| LMArena Korean | 1187 | 1347 |
| LMArena Russian | 1280 | 1381 |
| LMArena Spanish | 1246 | 1420 |
Instruction Following Claude Haiku 4.5 leads
Claude 3 Opus: 64.1 (#228), Claude Haiku 4.5: 71.4 (#149)
| Benchmark | Claude 3 Opus | Claude Haiku 4.5 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1414 |
| LiveBench Instruction Following | 63.9% | — |
| IFEval | — | 80.1% |
Long Context Claude Haiku 4.5 leads
Claude 3 Opus: 38.2 (#202), Claude Haiku 4.5: 43.6 (#92)
| Benchmark | Claude 3 Opus | Claude Haiku 4.5 |
|---|---|---|
| LMArena Longer Query | 1259 | 1427 |
Writing & Preference Claude Haiku 4.5 leads
Claude 3 Opus: 47.2 (#213), Claude Haiku 4.5: 57.9 (#123)
| Benchmark | Claude 3 Opus | Claude Haiku 4.5 |
|---|---|---|
| LMArena Text | 1262 | 1396 |
| LMArena Creative Writing | 1235 | 1372 |
| LMArena Multi-Turn | 1275 | 1409 |
| WildBench | — | 83.9% |
| EQ-Bench 4 | — | 1064 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Claude Haiku 4.5?
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Claude Haiku 4.5 better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Claude Haiku 4.5 share?
27 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Claude Haiku 4.5 has 53.