Model comparison
Claude Haiku 5.5 vs o4-mini
Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 41.6 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 5 categories and o4-mini in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 5.5 leads 73.6 to 40.8.
- The biggest single-benchmark swing is FrontierMath Tier 4: 46.3% for Claude Haiku 5.5 and 4.9% for o4-mini.
- Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- Claude Haiku 5.5 accepts more context: 1M tokens versus 200K.
Side by side
| Claude Haiku 5.5 | o4-mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 49.5 | 41.6 |
| Released | 2026-10-07 | 2025-04-16 |
| 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 | 60 |
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), o4-mini: 40.9 (#127)
| Benchmark | Claude Haiku 5.5 | o4-mini |
|---|---|---|
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| LMArena WebDev | 1587 | — |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| LMArena Coding | — | 1368 |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Not comparable
Claude Haiku 5.5: —, o4-mini: 32.6 (#61)
| Benchmark | Claude Haiku 5.5 | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning Claude Haiku 5.5 leads
Claude Haiku 5.5: 35.2 (#69), o4-mini: 24.6 (#162)
| Benchmark | Claude Haiku 5.5 | o4-mini |
|---|---|---|
| Mystery Game Puzzles | 30% | 5% |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 65.7% | — |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| LMArena Hard Prompts | — | 1351 |
| DTBench | — | 77.6% |
| LMCA | — | 26.5% |
| Epoch Capabilities Index | — | 145.64 |
| ForecastBench | — | 61.8 |
Math Claude Haiku 5.5 leads
Claude Haiku 5.5: 73.6 (#18), o4-mini: 40.8 (#89)
| Benchmark | Claude Haiku 5.5 | o4-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 75.1% | 36.1% |
| FrontierMath Tier 4 | 46.3% | 4.9% |
| OTIS Mock AIME 2024-2025 | 98.9% | 81.7% |
| Omni-MATH | — | 72% |
| LMArena Math | — | 1389 |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge Claude Haiku 5.5 leads
Claude Haiku 5.5: 50.8 (#70), o4-mini: 43.6 (#91)
| Benchmark | Claude Haiku 5.5 | o4-mini |
|---|---|---|
| GPQA Diamond | 89.6% | 79.6% |
| SimpleQA Verified | 23.8% | 19.6% |
| Humanity's Last Exam | — | 18.1% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| Vectara Hallucination Rate | — | 18.6% |
| GPQA (HELM) | — | 73.5% |
| LMArena Expert | — | 1343 |
Multimodal Claude Haiku 5.5 leads
Claude Haiku 5.5: 43.7 (#21), o4-mini: 40.2 (#49)
| Benchmark | Claude Haiku 5.5 | o4-mini |
|---|---|---|
| LMArena Vision | — | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
| Furniture Assembly | 47.5% | — |
Multilingual Not comparable
Claude Haiku 5.5: —, o4-mini: 47.0 (#154)
| Benchmark | Claude Haiku 5.5 | o4-mini |
|---|---|---|
| LMArena Non-English | — | 1337 |
| LMArena Chinese | — | 1354 |
| LMArena French | — | 1364 |
| LMArena German | — | 1336 |
| LMArena Japanese | — | 1308 |
| LMArena Korean | — | 1312 |
| LMArena Russian | — | 1334 |
| LMArena Spanish | — | 1347 |
Instruction Following Not comparable
Claude Haiku 5.5: —, o4-mini: 75.2 (#68)
| Benchmark | Claude Haiku 5.5 | o4-mini |
|---|---|---|
| IFEval | — | 92.8% |
| LMArena Instruction Following | — | 1321 |
Long Context Not comparable
Claude Haiku 5.5: —, o4-mini: 45.5 (#33)
| Benchmark | Claude Haiku 5.5 | o4-mini |
|---|---|---|
| Fiction.LiveBench | — | 77.8% |
| LMArena Longer Query | — | 1315 |
Writing & Preference Not comparable
Claude Haiku 5.5: —, o4-mini: 54.0 (#152)
| Benchmark | Claude Haiku 5.5 | o4-mini |
|---|---|---|
| LMArena Text | — | 1353 |
| LMArena Creative Writing | — | 1294 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |
| LMArena Multi-Turn | — | 1350 |
Frequently asked questions
Is Claude Haiku 5.5 better than o4-mini?
Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 41.6 on the Noometry Index.
Which is cheaper, Claude Haiku 5.5 or o4-mini?
Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is Claude Haiku 5.5 or o4-mini better for coding?
Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 40.9 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 o4-mini share?
6 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and o4-mini has 60.