Model comparison
Claude 3 Haiku vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 25.9 on the Noometry Index.
Last verified . 6 shared benchmarks.
Summary
- They share 6 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and o3-pro in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 36.1.
- The biggest single-benchmark swing is WeirdML: 9.8% for Claude 3 Haiku and 58.2% for o3-pro.
Side by side
| Claude 3 Haiku | o3-pro | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 25.9 | 42.9 |
| Released | 2024-03-07 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $20 |
| Output $ / M tokens | — | $80 |
| Results tracked | 37 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Claude 3 Haiku: 26.4 (#325), o3-pro: 55.5 (#24)
| Benchmark | Claude 3 Haiku | o3-pro |
|---|---|---|
| WeirdML | 9.8% | 58.2% |
| Aider Polyglot | — | 84.9% |
| BigCodeBench Instruct | 39.4% | — |
| LMArena Coding | 1199 | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning o3-pro leads
Claude 3 Haiku: 16.3 (#307), o3-pro: 23.8 (#171)
| Benchmark | Claude 3 Haiku | o3-pro |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 72.1% |
| DTBench | 50.1% | 86.9% |
| LMCA | 8.8% | 38.5% |
| Epoch Capabilities Index | 118.35 | 147.42 |
| ARC-AGI-2 | — | 4.9% |
| ARC-AGI-1 | — | 59.3% |
| LMArena Hard Prompts | 1174 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Not comparable
Claude 3 Haiku: 9.8 (#319), o3-pro: —
| Benchmark | Claude 3 Haiku | o3-pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| LMArena Math | 1188 | — |
| MATH Level 5 | 14.9% | — |
Knowledge o3-pro leads
Claude 3 Haiku: 17.3 (#285), o3-pro: 29.5 (#238)
| Benchmark | Claude 3 Haiku | o3-pro |
|---|---|---|
| Confabulations | 34.2% | 14.2% |
| GPQA Diamond | 36.3% | — |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1148 | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), o3-pro: —
| Benchmark | Claude 3 Haiku | o3-pro |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Not comparable
Claude 3 Haiku: 36.0 (#243), o3-pro: —
| Benchmark | Claude 3 Haiku | o3-pro |
|---|---|---|
| LMArena Non-English | 1178 | — |
| LMArena Chinese | 1155 | — |
| LMArena French | 1195 | — |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1109 | — |
| LMArena Russian | 1204 | — |
| LMArena Spanish | 1166 | — |
Instruction Following Not comparable
Claude 3 Haiku: 61.3 (#247), o3-pro: —
| Benchmark | Claude 3 Haiku | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1173 | — |
Long Context o3-pro leads
Claude 3 Haiku: 36.1 (#237), o3-pro: 72.2 (#1)
| Benchmark | Claude 3 Haiku | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1190 | — |
Writing & Preference o3-pro leads
Claude 3 Haiku: 29.7 (#291), o3-pro: 57.1 (#133)
| Benchmark | Claude 3 Haiku | o3-pro |
|---|---|---|
| LMArena Text | 1195 | — |
| LMArena Creative Writing | 1157 | — |
| Short-Story Creative Writing | — | 84.4% |
| EQ-Bench Creative Writing | 717 | — |
| LMArena Multi-Turn | 1190 | — |
Frequently asked questions
Is Claude 3 Haiku better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and o3-pro share?
6 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and o3-pro has 12.