Model comparison
Claude 3.5 Haiku vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 29.2 on the Noometry Index.
Last verified . 37 shared benchmarks.
Summary
- They share 37 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 2 categories and o3-mini in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3-mini leads 38.3 to 18.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku and 76.9% for o3-mini.
Side by side
| Claude 3.5 Haiku | o3-mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 29.2 | 36.7 |
| Released | 2024-10-22 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 49 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Claude 3.5 Haiku: 32.9 (#265), o3-mini: 40.8 (#132)
| Benchmark | Claude 3.5 Haiku | o3-mini |
|---|---|---|
| Aider Polyglot | 28% | 60.4% |
| SciCode | 27.4% | 39.8% |
| WeirdML | 30.7% | 43.7% |
| LiveBench Coding | 51.4% | 82.7% |
| LMArena Coding | 1286 | 1378 |
| CadEval | 32% | 54% |
| GSO | — | 1.3% |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 59% | — |
Agentic & Tool Use o3-mini leads
Claude 3.5 Haiku: 28.0 (#95), o3-mini: 29.6 (#84)
Reasoning Claude 3.5 Haiku leads
Claude 3.5 Haiku: 17.7 (#290), o3-mini: 16.3 (#305)
| Benchmark | Claude 3.5 Haiku | o3-mini |
|---|---|---|
| CritPt | 0% | 0.3% |
| LiveBench Reasoning | 28.1% | 89.6% |
| LMArena Hard Prompts | 1251 | 1366 |
| DTBench | 56.7% | 68.8% |
| LiveBench Data Analysis | 48.5% | 70.6% |
| Epoch Capabilities Index | 127.15 | 140.34 |
| LiveBench | 43.5% | 75.9% |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| ARC-AGI-1 | — | 34.5% |
| Chess Puzzles | — | 17% |
| Mystery Game Puzzles | — | 7% |
| LMCA | — | 19% |
| ForecastBench | — | 59.6 |
Math o3-mini leads
Claude 3.5 Haiku: 14.7 (#300), o3-mini: 28.1 (#244)
| Benchmark | Claude 3.5 Haiku | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 76.9% |
| LiveBench Math | 35.5% | 77.3% |
| LMArena Math | 1244 | 1396 |
| MATH Level 5 | 46.4% | 96.5% |
| FrontierMath (Feb 2025 set) | 0.3% | 12.4% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| Omni-MATH | 22.4% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
Claude 3.5 Haiku: 18.7 (#281), o3-mini: 38.3 (#146)
| Benchmark | Claude 3.5 Haiku | o3-mini |
|---|---|---|
| GPQA Diamond | 38.1% | 77% |
| Confabulations | 36.7% | 17.9% |
| LMArena Expert | 1208 | 1364 |
| SimpleQA Verified | — | 15.3% |
| MMLU-Pro | 60.5% | — |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.8 (#117), o3-mini: —
| Benchmark | Claude 3.5 Haiku | o3-mini |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual o3-mini leads
Claude 3.5 Haiku: 40.0 (#218), o3-mini: 45.7 (#164)
| Benchmark | Claude 3.5 Haiku | o3-mini |
|---|---|---|
| LMArena Non-English | 1238 | 1319 |
| LMArena Chinese | 1229 | 1379 |
| LMArena French | 1264 | 1334 |
| LMArena German | 1237 | 1303 |
| LMArena Japanese | 1175 | 1286 |
| LMArena Korean | 1173 | 1314 |
| LMArena Russian | 1253 | 1304 |
| LMArena Spanish | 1261 | 1321 |
Instruction Following o3-mini leads
Claude 3.5 Haiku: 62.9 (#234), o3-mini: 75.1 (#72)
| Benchmark | Claude 3.5 Haiku | o3-mini |
|---|---|---|
| LiveBench Instruction Following | 61.9% | 84.4% |
| LMArena Instruction Following | 1241 | 1337 |
| IFEval | 79.2% | — |
Long Context Claude 3.5 Haiku leads
Claude 3.5 Haiku: 38.3 (#200), o3-mini: 33.8 (#256)
| Benchmark | Claude 3.5 Haiku | o3-mini |
|---|---|---|
| LMArena Longer Query | 1261 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference o3-mini leads
Claude 3.5 Haiku: 42.7 (#234), o3-mini: 50.3 (#182)
| Benchmark | Claude 3.5 Haiku | o3-mini |
|---|---|---|
| LMArena Text | 1255 | 1337 |
| LMArena Creative Writing | 1233 | 1286 |
| Short-Story Creative Writing | 73.5% | 61.7% |
| LMArena Multi-Turn | 1265 | 1320 |
| LiveBench Language | 35.4% | 50.7% |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and o3-mini share?
37 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and o3-mini has 51.