Model comparison
Claude Haiku 4.5 vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 39.3 on the Noometry Index.
Last verified . 41 shared benchmarks.
Summary
- They share 41 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 5 categories and o4-mini in 5 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where o4-mini leads 39.5 to 27.0.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 66.6% for Claude Haiku 4.5 and 45% for o4-mini.
- Both cost about the same: $1 input and $5 output per million tokens.
Side by side
| Claude Haiku 4.5 | o4-mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 39.3 | 41.6 |
| Released | 2025-10-15 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 200K |
| Max output | 64K | 100K |
| Input $ / M tokens | $1 | $1.10 |
| Output $ / M tokens | $5 | $4.40 |
| Results tracked | 53 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.9 (#71), o4-mini: 41.6 (#110)
| Benchmark | Claude Haiku 4.5 | o4-mini |
|---|---|---|
| SWE-bench Verified (bash only) | 66.6% | 45% |
| WeirdML | 45.4% | 52.6% |
| LMArena Coding | 1454 | 1369 |
| ALE-Bench | 653.48 | 826.17 |
| Aider Polyglot | — | 72% |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| GSO | — | 3.6% |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Claude Haiku 4.5 leads
Claude Haiku 4.5: 33.5 (#50), o4-mini: 32.3 (#57)
| Benchmark | Claude Haiku 4.5 | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 68.7% | 53.2% |
| Terminal-Bench | 35.5% | — |
| GDPval | — | 25.3% |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| METR Time Horizons | — | 63.9% |
| Vending-Bench 2 | 458.89 | — |
Reasoning o4-mini leads
Claude Haiku 4.5: 15.1 (#310), o4-mini: 24.6 (#143)
| Benchmark | Claude Haiku 4.5 | o4-mini |
|---|---|---|
| ARC-AGI-2 | 4% | 6.1% |
| ARC-AGI-1 | 47.7% | 58.7% |
| CritPt | 0% | 0.6% |
| Chess Puzzles | 8% | 26% |
| LMArena Hard Prompts | 1420 | 1351 |
| DTBench | 73.6% | 77.6% |
| LMCA | 30.9% | 26.5% |
| Epoch Capabilities Index | 142.42 | 145.63 |
| ForecastBench | 61.4 | 61.8 |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 14.3% | — |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.0 (#69), o4-mini: 40.2 (#79)
| Benchmark | Claude Haiku 4.5 | o4-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 81.7% |
| Omni-MATH | 56.1% | 72% |
| LMArena Math | 1395 | 1390 |
| MATH Level 5 | 96.4% | 97.8% |
| FrontierMath (Feb 2025 set) | 5.9% | 24.8% |
| FrontierMath Tier 4 (v1) | 2.1% | 6.3% |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
Knowledge o4-mini leads
Claude Haiku 4.5: 37.6 (#146), o4-mini: 43.5 (#83)
| Benchmark | Claude Haiku 4.5 | o4-mini |
|---|---|---|
| GPQA Diamond | 71.2% | 79.6% |
| SimpleQA Verified | 13.2% | 19.6% |
| MMLU-Pro | 77.7% | 82% |
| Vectara Hallucination Rate | 9.8% | 18.6% |
| GPQA (HELM) | 60.5% | 73.5% |
| LMArena Expert | 1443 | 1344 |
| Humanity's Last Exam | — | 18.1% |
| Confabulations | — | 15.8% |
Multimodal o4-mini leads
Claude Haiku 4.5: 27.0 (#111), o4-mini: 39.5 (#46)
| Benchmark | Claude Haiku 4.5 | o4-mini |
|---|---|---|
| LMArena Vision | — | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 50.1 (#124), o4-mini: 47.2 (#149)
| Benchmark | Claude Haiku 4.5 | o4-mini |
|---|---|---|
| LMArena Non-English | 1376 | 1336 |
| LMArena Chinese | 1415 | 1355 |
| LMArena French | 1408 | 1362 |
| LMArena German | 1377 | 1336 |
| LMArena Japanese | 1339 | 1308 |
| LMArena Korean | 1346 | 1313 |
| LMArena Russian | 1380 | 1334 |
| LMArena Spanish | 1420 | 1346 |
Instruction Following o4-mini leads
Claude Haiku 4.5: 71.6 (#144), o4-mini: 75.4 (#63)
| Benchmark | Claude Haiku 4.5 | o4-mini |
|---|---|---|
| IFEval | 80.1% | 92.8% |
| LMArena Instruction Following | 1414 | 1321 |
Long Context o4-mini leads
Claude Haiku 4.5: 43.6 (#86), o4-mini: 45.5 (#31)
| Benchmark | Claude Haiku 4.5 | o4-mini |
|---|---|---|
| LMArena Longer Query | 1427 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 58.1 (#119), o4-mini: 54.2 (#148)
| Benchmark | Claude Haiku 4.5 | o4-mini |
|---|---|---|
| LMArena Text | 1396 | 1353 |
| LMArena Creative Writing | 1371 | 1294 |
| WildBench | 83.9% | 85.4% |
| LMArena Multi-Turn | 1409 | 1350 |
| Short-Story Creative Writing | — | 75% |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 39.3 on the Noometry Index.
Which is cheaper, Claude Haiku 4.5 or o4-mini?
o4-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or o4-mini better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 43.9 versus 41.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do Claude Haiku 4.5 and o4-mini share?
41 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and o4-mini has 60.