Model comparison
Claude Haiku 4.5 vs Claude Haiku 5.5
Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 39.5 on the Noometry Index.
Last verified . 5 shared benchmarks.
Summary
- They share 5 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 0 categories and Claude Haiku 5.5 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 5.5 leads 73.6 to 44.9.
- The biggest single-benchmark swing is NYT Connections (extended): 14.3% for Claude Haiku 4.5 and 65.7% for Claude Haiku 5.5.
- Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Claude Haiku 5.5 accepts more context: 1M tokens versus 200K.
Side by side
| Claude Haiku 4.5 | Claude Haiku 5.5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 39.5 | 49.5 |
| Released | 2025-10-15 | 2026-10-07 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1M |
| Max output | 64K | 128K |
| Input $ / M tokens | $1 | $0.10 |
| Output $ / M tokens | $5 | $0.50 |
| Results tracked | 53 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 5.5 leads
Claude Haiku 4.5: 44.0 (#78), Claude Haiku 5.5: 49.2 (#50)
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| LMArena WebDev | 1330 | 1587 |
| SWE-bench Verified (bash only) | 66.6% | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| LMArena Coding | 1453 | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), Claude Haiku 5.5: —
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| 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 Claude Haiku 5.5 leads
Claude Haiku 4.5: 15.1 (#320), Claude Haiku 5.5: 35.2 (#69)
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| NYT Connections (extended) | 14.3% | 65.7% |
| ARC-AGI-2 | 4% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| LMArena Hard Prompts | 1420 | — |
| Mystery Game Puzzles | — | 30% |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |
Math Claude Haiku 5.5 leads
Claude Haiku 4.5: 44.9 (#78), Claude Haiku 5.5: 73.6 (#18)
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 98.9% |
| FrontierMath (Tiers 1-3) | — | 75.1% |
| FrontierMath Tier 4 | — | 46.3% |
| 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 5.5 leads
Claude Haiku 4.5: 37.7 (#153), Claude Haiku 5.5: 50.8 (#70)
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| GPQA Diamond | 71.2% | 89.6% |
| SimpleQA Verified | 13.2% | 23.8% |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
| LMArena Expert | 1442 | — |
Multimodal Claude Haiku 5.5 leads
Claude Haiku 4.5: 26.8 (#118), Claude Haiku 5.5: 43.7 (#21)
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| Furniture Assembly | — | 47.5% |
| LMArena Document | 1420 | — |
Multilingual Not comparable
Claude Haiku 4.5: 49.9 (#129), Claude Haiku 5.5: —
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| 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), Claude Haiku 5.5: —
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| IFEval | 80.1% | — |
| LMArena Instruction Following | 1414 | — |
Long Context Not comparable
Claude Haiku 4.5: 43.6 (#92), Claude Haiku 5.5: —
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| LMArena Longer Query | 1427 | — |
Writing & Preference Not comparable
Claude Haiku 4.5: 57.9 (#123), Claude Haiku 5.5: —
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| LMArena Text | 1396 | — |
| LMArena Creative Writing | 1372 | — |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
| LMArena Multi-Turn | 1409 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Claude Haiku 5.5?
Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 39.5 on the Noometry Index.
Which is cheaper, Claude Haiku 4.5 or Claude Haiku 5.5?
Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or Claude Haiku 5.5 better for coding?
Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 44.0 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 4.5 and Claude Haiku 5.5 share?
5 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Claude Haiku 5.5 has 9.