Model comparison
Amazon Nova Pro vs Claude Haiku 4.5
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 31.0 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. Amazon Nova Pro scores higher in 1 category and Claude Haiku 4.5 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Haiku 4.5 leads 33.6 to 16.7.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 25% for Amazon Nova Pro and 68.7% for Claude Haiku 4.5.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Amazon Nova Pro accepts more context: 300K tokens versus 200K.
Side by side
| Amazon Nova Pro | Claude Haiku 4.5 | |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 31.0 | 39.5 |
| Released | 2024-12-03 | 2025-10-15 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 200K |
| Max output | 10K | 64K |
| Input $ / M tokens | $0.80 | $1 |
| Output $ / M tokens | $3.20 | $5 |
| Results tracked | 38 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 4.5 leads
Amazon Nova Pro: 35.1 (#229), Claude Haiku 4.5: 44.0 (#78)
| Benchmark | Amazon Nova Pro | Claude Haiku 4.5 |
|---|---|---|
| LMArena Coding | 1270 | 1453 |
| SWE-bench Verified (bash only) | — | 66.6% |
| LMArena WebDev | — | 1330 |
| SWE-bench Multilingual | — | 64.7% |
| SciCode | — | 43.3% |
| WeirdML | — | 45.4% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 653.48 |
Agentic & Tool Use Claude Haiku 4.5 leads
Amazon Nova Pro: 16.7 (#147), Claude Haiku 4.5: 33.6 (#52)
| Benchmark | Amazon Nova Pro | Claude Haiku 4.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 68.7% |
| Terminal-Bench | — | 35.5% |
| TheAgentCompany | 1.7% | — |
| DeepResearch Bench | — | 45.5% |
| BALROG | — | 31.2% |
| ExploitBench | — | 13.7% |
| Vending-Bench 2 | — | 458.89 |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Claude Haiku 4.5: 15.1 (#320)
| Benchmark | Amazon Nova Pro | Claude Haiku 4.5 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1420 |
| Epoch Capabilities Index | 123.8 | 142.41 |
| ARC-AGI-2 | — | 4% |
| NYT Connections (extended) | — | 14.3% |
| ARC-AGI-1 | — | 47.7% |
| CritPt | — | 0% |
| Chess Puzzles | — | 8% |
| LiveBench Reasoning | 32.6% | — |
| DTBench | — | 73.6% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 30.9% |
| ForecastBench | — | 61.4 |
| LiveBench | 43.5% | — |
Math Claude Haiku 4.5 leads
Amazon Nova Pro: 28.5 (#243), Claude Haiku 4.5: 44.9 (#78)
| Benchmark | Amazon Nova Pro | Claude Haiku 4.5 |
|---|---|---|
| Omni-MATH | 24.2% | 56.1% |
| LMArena Math | 1252 | 1396 |
| OTIS Mock AIME 2024-2025 | — | 66.7% |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 96.4% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Claude Haiku 4.5 leads
Amazon Nova Pro: 27.4 (#250), Claude Haiku 4.5: 37.7 (#153)
| Benchmark | Amazon Nova Pro | Claude Haiku 4.5 |
|---|---|---|
| MMLU-Pro | 67.3% | 77.7% |
| Vectara Hallucination Rate | 5.1% | 9.8% |
| GPQA (HELM) | 44.6% | 60.5% |
| LMArena Expert | 1211 | 1442 |
| GPQA Diamond | — | 71.2% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 13.2% |
| Confabulations | 30.1% | — |
| MMLU | 82% | — |
Multimodal Claude Haiku 4.5 leads
Amazon Nova Pro: 25.0 (#126), Claude Haiku 4.5: 26.8 (#118)
| Benchmark | Amazon Nova Pro | Claude Haiku 4.5 |
|---|---|---|
| LMArena Vision | 980 | — |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1420 |
Multilingual Claude Haiku 4.5 leads
Amazon Nova Pro: 39.7 (#223), Claude Haiku 4.5: 49.9 (#129)
| Benchmark | Amazon Nova Pro | Claude Haiku 4.5 |
|---|---|---|
| LMArena Non-English | 1234 | 1377 |
| LMArena Chinese | 1244 | 1417 |
| LMArena French | 1271 | 1408 |
| LMArena German | 1243 | 1375 |
| LMArena Japanese | 1200 | 1339 |
| LMArena Korean | 1203 | 1347 |
| LMArena Russian | 1240 | 1381 |
| LMArena Spanish | 1182 | 1420 |
Instruction Following Claude Haiku 4.5 leads
Amazon Nova Pro: 64.9 (#226), Claude Haiku 4.5: 71.4 (#149)
| Benchmark | Amazon Nova Pro | Claude Haiku 4.5 |
|---|---|---|
| IFEval | 81.5% | 80.1% |
| LMArena Instruction Following | 1235 | 1414 |
| LiveBench Instruction Following | 67.1% | — |
Long Context Claude Haiku 4.5 leads
Amazon Nova Pro: 38.1 (#205), Claude Haiku 4.5: 43.6 (#92)
| Benchmark | Amazon Nova Pro | Claude Haiku 4.5 |
|---|---|---|
| LMArena Longer Query | 1255 | 1427 |
Writing & Preference Claude Haiku 4.5 leads
Amazon Nova Pro: 43.9 (#226), Claude Haiku 4.5: 57.9 (#123)
| Benchmark | Amazon Nova Pro | Claude Haiku 4.5 |
|---|---|---|
| LMArena Text | 1259 | 1396 |
| LMArena Creative Writing | 1212 | 1372 |
| WildBench | 77.7% | 83.9% |
| LMArena Multi-Turn | 1246 | 1409 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench 4 | — | 1064 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Claude Haiku 4.5?
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or Claude Haiku 4.5?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Amazon Nova Pro or Claude Haiku 4.5 better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 200K.
How many benchmarks do Amazon Nova Pro and Claude Haiku 4.5 share?
25 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Claude Haiku 4.5 has 53.