Model comparison
Claude Haiku 4.5 vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 39.5 on the Noometry Index. Claude Haiku 4.5 costs 18× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Last verified . 7 shared benchmarks.
Summary
- They share 7 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 2 categories and o3-pro in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 43.6.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 9.8% for Claude Haiku 4.5 and 23.3% for o3-pro.
- Claude Haiku 4.5 is cheaper at $1 / $5 per million input/output tokens, against $20 / $80 for o3-pro.
Side by side
| Claude Haiku 4.5 | o3-pro | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 39.5 | 42.9 |
| Released | 2025-10-15 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 200K |
| Max output | 64K | 100K |
| Input $ / M tokens | $1 | $20 |
| Output $ / M tokens | $5 | $80 |
| Results tracked | 53 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Claude Haiku 4.5: 44.0 (#78), o3-pro: 55.5 (#24)
| Benchmark | Claude Haiku 4.5 | o3-pro |
|---|---|---|
| WeirdML | 45.4% | 58.2% |
| SWE-bench Verified (bash only) | 66.6% | — |
| Aider Polyglot | — | 84.9% |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| LMArena Coding | 1453 | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), o3-pro: —
| Benchmark | Claude Haiku 4.5 | o3-pro |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning o3-pro leads
Claude Haiku 4.5: 15.1 (#320), o3-pro: 23.8 (#171)
| Benchmark | Claude Haiku 4.5 | o3-pro |
|---|---|---|
| ARC-AGI-2 | 4% | 4.9% |
| ARC-AGI-1 | 47.7% | 59.3% |
| DTBench | 73.6% | 86.9% |
| LMCA | 30.9% | 38.5% |
| Epoch Capabilities Index | 142.41 | 147.42 |
| Kagi LLM Benchmark | — | 72.1% |
| NYT Connections (extended) | 14.3% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| LMArena Hard Prompts | 1420 | — |
| ForecastBench | 61.4 | — |
Math Not comparable
Claude Haiku 4.5: 44.9 (#78), o3-pro: —
| Benchmark | Claude Haiku 4.5 | o3-pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| LMArena Math | 1396 | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Claude Haiku 4.5 leads
Claude Haiku 4.5: 37.7 (#153), o3-pro: 29.5 (#238)
| Benchmark | Claude Haiku 4.5 | o3-pro |
|---|---|---|
| Vectara Hallucination Rate | 9.8% | 23.3% |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | — | 14.2% |
| GPQA (HELM) | 60.5% | — |
| LMArena Expert | 1442 | — |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), o3-pro: —
| Benchmark | Claude Haiku 4.5 | o3-pro |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Not comparable
Claude Haiku 4.5: 49.9 (#129), o3-pro: —
| Benchmark | Claude Haiku 4.5 | o3-pro |
|---|---|---|
| LMArena Non-English | 1377 | — |
| LMArena Chinese | 1417 | — |
| LMArena French | 1408 | — |
| LMArena German | 1375 | — |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
| LMArena Russian | 1381 | — |
| LMArena Spanish | 1420 | — |
Instruction Following Not comparable
Claude Haiku 4.5: 71.4 (#149), o3-pro: —
| Benchmark | Claude Haiku 4.5 | o3-pro |
|---|---|---|
| IFEval | 80.1% | — |
| LMArena Instruction Following | 1414 | — |
Long Context o3-pro leads
Claude Haiku 4.5: 43.6 (#92), o3-pro: 72.2 (#1)
| Benchmark | Claude Haiku 4.5 | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1427 | — |
Writing & Preference Too close to call
Claude Haiku 4.5: 57.9 (#123), o3-pro: 57.1 (#133)
| Benchmark | Claude Haiku 4.5 | o3-pro |
|---|---|---|
| LMArena Text | 1396 | — |
| LMArena Creative Writing | 1372 | — |
| Short-Story Creative Writing | — | 84.4% |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
| LMArena Multi-Turn | 1409 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 39.5 on the Noometry Index. Claude Haiku 4.5 costs 18× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Which is cheaper, Claude Haiku 4.5 or o3-pro?
Claude Haiku 4.5 is cheaper. It lists at $1 per million input tokens and $5 per million output tokens; o3-pro lists at $20 and $80.
Is Claude Haiku 4.5 or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 44.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do Claude Haiku 4.5 and o3-pro share?
7 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and o3-pro has 12.