Model comparison
Claude Haiku 5.5 vs o3-mini
Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 36.7 on the Noometry Index.
Last verified . 6 shared benchmarks.
Summary
- They share 6 benchmarks with published results for both. Claude Haiku 5.5 scores higher in 4 categories and o3-mini in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 5.5 leads 73.6 to 28.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 75.1% for Claude Haiku 5.5 and 18.6% for o3-mini.
- Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- Claude Haiku 5.5 accepts more context: 1M tokens versus 200K.
Side by side
| Claude Haiku 5.5 | o3-mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 49.5 | 36.7 |
| Released | 2026-10-07 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $0.10 | $1.10 |
| Output $ / M tokens | $0.50 | $4.40 |
| Results tracked | 9 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 5.5 leads
Claude Haiku 5.5: 49.2 (#50), o3-mini: 40.8 (#132)
| Benchmark | Claude Haiku 5.5 | o3-mini |
|---|---|---|
| Aider Polyglot | — | 60.4% |
| LMArena WebDev | 1587 | — |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| LiveBench Coding | — | 82.7% |
| LMArena Coding | — | 1378 |
| CadEval | — | 54% |
Agentic & Tool Use Not comparable
Claude Haiku 5.5: —, o3-mini: 29.6 (#84)
| Benchmark | Claude Haiku 5.5 | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |
Reasoning Claude Haiku 5.5 leads
Claude Haiku 5.5: 35.2 (#69), o3-mini: 16.3 (#305)
| Benchmark | Claude Haiku 5.5 | o3-mini |
|---|---|---|
| Mystery Game Puzzles | 30% | 7% |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| NYT Connections (extended) | 65.7% | — |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| LiveBench Reasoning | — | 89.6% |
| LMArena Hard Prompts | — | 1366 |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| Epoch Capabilities Index | — | 140.34 |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math Claude Haiku 5.5 leads
Claude Haiku 5.5: 73.6 (#18), o3-mini: 28.1 (#244)
| Benchmark | Claude Haiku 5.5 | o3-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 75.1% | 18.6% |
| FrontierMath Tier 4 | 46.3% | 0% |
| OTIS Mock AIME 2024-2025 | 98.9% | 76.9% |
| LiveBench Math | — | 77.3% |
| LMArena Math | — | 1396 |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Claude Haiku 5.5 leads
Claude Haiku 5.5: 50.8 (#70), o3-mini: 38.3 (#146)
| Benchmark | Claude Haiku 5.5 | o3-mini |
|---|---|---|
| GPQA Diamond | 89.6% | 77% |
| SimpleQA Verified | 23.8% | 15.3% |
| Confabulations | — | 17.9% |
| LMArena Expert | — | 1364 |
Multimodal Not comparable
Claude Haiku 5.5: 43.7 (#21), o3-mini: —
| Benchmark | Claude Haiku 5.5 | o3-mini |
|---|---|---|
| Furniture Assembly | 47.5% | — |
Multilingual Not comparable
Claude Haiku 5.5: —, o3-mini: 45.7 (#164)
| Benchmark | Claude Haiku 5.5 | o3-mini |
|---|---|---|
| LMArena Non-English | — | 1319 |
| LMArena Chinese | — | 1379 |
| LMArena French | — | 1334 |
| LMArena German | — | 1303 |
| LMArena Japanese | — | 1286 |
| LMArena Korean | — | 1314 |
| LMArena Russian | — | 1304 |
| LMArena Spanish | — | 1321 |
Instruction Following Not comparable
Claude Haiku 5.5: —, o3-mini: 75.1 (#72)
| Benchmark | Claude Haiku 5.5 | o3-mini |
|---|---|---|
| LiveBench Instruction Following | — | 84.4% |
| LMArena Instruction Following | — | 1337 |
Long Context Not comparable
Claude Haiku 5.5: —, o3-mini: 33.8 (#256)
| Benchmark | Claude Haiku 5.5 | o3-mini |
|---|---|---|
| Fiction.LiveBench | — | 50% |
| LMArena Longer Query | — | 1343 |
Writing & Preference Not comparable
Claude Haiku 5.5: —, o3-mini: 50.3 (#182)
| Benchmark | Claude Haiku 5.5 | o3-mini |
|---|---|---|
| LMArena Text | — | 1337 |
| LMArena Creative Writing | — | 1286 |
| Short-Story Creative Writing | — | 61.7% |
| LMArena Multi-Turn | — | 1320 |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Claude Haiku 5.5 better than o3-mini?
Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 36.7 on the Noometry Index.
Which is cheaper, Claude Haiku 5.5 or o3-mini?
Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is Claude Haiku 5.5 or o3-mini better for coding?
Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Claude Haiku 5.5 does, with 1M tokens against 200K.
How many benchmarks do Claude Haiku 5.5 and o3-mini share?
6 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and o3-mini has 51.