Claude Haiku 4.5 vs Claude Haiku 5.5
Claude Haiku 5.5 leads Claude Haiku 4.5 on coding, 70.7 to 35.6 on the Vibe Coding Index, and Claude Haiku 5.5 costs 10.0x less per output token ($0.50 vs $5.00 per million). Updated October 22, 2026; 39 benchmarks have a result for both.
Claude Haiku 4.5 or Claude Haiku 5.5: which to pick
Pick Claude Haiku 5.5 for coding: it scores 70.7 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5.
Pick Claude Haiku 4.5 for work measured by LiveBench data analysis, where it leads.
- Shared results
- 39
- Claude Haiku 4.5 only
- 59
- Claude Haiku 5.5 only
- 26
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
Claude Haiku 5.5
Claude Haiku 5.5 scores 70.7 against 35.6.
4 and 5 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Haiku 5.5
Claude Haiku 5.5 leads, 43.4 against 16.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Claude Haiku 4.5 has a AA Agentic Index result, 8.0.
Directional only
Reasoning
GPQA Diamond
No call
Only Claude Haiku 4.5 has a GPQA Diamond result, 72.2%.
Directional only
Math
AIME
No call
Only Claude Haiku 4.5 has a AIME result, 82.7%.
Directional only
Knowledge
MMLU Pro
No call
Only Claude Haiku 4.5 has a MMLU Pro result, 78.7%.
Directional only
Web design
Design Arena: websites
Claude Haiku 5.5
Claude Haiku 5.5 leads, 1262 against 1122.
Same board, both measured
General
Vals Index
No call
Only Claude Haiku 5.5 has a Vals Index result, 58.7%.
Directional only
Long documents
Listed context window
Claude Haiku 5.5
Claude Haiku 5.5 takes 1M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Claude Haiku 5.5
Claude Haiku 4.5 $0.0035, Claude Haiku 5.5 $0.0003 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Claude Haiku 4.5 has the number, $0.56.
Directional only
At a glance
- Coding index
- Claude Haiku 4.5 35.6 from 4 benchmarks, Claude Haiku 5.5 70.7 from 5 benchmarks.
- Widest category
- Coding, 40.8 points apart on average over 7 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): Claude Haiku 4.5 11.4% against Claude Haiku 5.5 90.4%, 79.0 points apart on a 0 to 100 scale.
- Output price
- Claude Haiku 4.5 $5.00 against Claude Haiku 5.5 $0.50 per million output tokens, 10.0x apart.
- Context window
- Claude Haiku 4.5 takes 200K tokens, Claude Haiku 5.5 1M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Claude Haiku 4.5 | Bars | Claude Haiku 5.5 | Ties |
|---|---|---|---|---|
| Coding | 0 | 7 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 8 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 1 | ||
| Knowledge | 0 | 2 | ||
| Web design | 0 | 7 | ||
| General | 1 | 6 | ||
| All shared boards | 1 | 38 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index07
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| SWE-bench Verified | 66.6% | Not measured | Only Claude Haiku 4.5 measured |
| SWE-bench Multilingual | 64.7% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench coding | 48.1% | 91.4% | Claude Haiku 5.5 |
| LMArena WebDev | 1330 | 1586 | Claude Haiku 5.5 |
| AA Coding Index | 43.9 | Not measured | Only Claude Haiku 4.5 measured |
| LiveCodeBench (Vals AI) | 41.2% | Not measured | Only Claude Haiku 4.5 measured |
| SWE-bench Verified (Vals AI) | 66.6% | Not measured | Only Claude Haiku 4.5 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 36.4% | Only Claude Haiku 5.5 measured |
| Vibe Code Bench (Vals AI) | 11.4% | 90.4% | Claude Haiku 5.5 |
| Code migration (Vals AI) | 7.5% | 44.6% | Claude Haiku 5.5 |
| ProgramBench (Vals AI) | 0.0% | 2.5% | Claude Haiku 5.5 |
| IOI (Vals AI) | Not measured | 47.3% | Only Claude Haiku 5.5 measured |
| Terminal-Bench 2.1 (Vals AI) | 43.8% | Not measured | Only Claude Haiku 4.5 measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 44.0% | Only Claude Haiku 5.5 measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 20.4% | Only Claude Haiku 5.5 measured |
| CyberBench (Vals AI) | Not measured | 75.5% | Only Claude Haiku 5.5 measured |
| SciCode | Not measured | 55.0% | Only Claude Haiku 5.5 measured |
| Terminal-Bench | 35.5% | Not measured | Only Claude Haiku 4.5 measured |
| FrontierCode | Not measured | 46.4% | Only Claude Haiku 5.5 measured |
| FrontierSWE | Not measured | 43.8% | Only Claude Haiku 5.5 measured |
| WeirdML | 45.4% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: coding | 1454 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: software and IT | 1439 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena WebDev: React | 1326 | 1605 | Claude Haiku 5.5 |
| LMArena WebDev: HTML | 1318 | 1569 | Claude Haiku 5.5 |
| SciCode | Not measured | 9.2% | Only Claude Haiku 5.5 measured |
| SWE-Bench Pro V2 | Not measured | 87.2% | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 16 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.9 | 43.4 | Claude Haiku 5.5 |
| Epoch Capabilities Index | 142.2 | 159.3 | Claude Haiku 5.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 8.0 | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench research | 42.2% | 81.9% | Claude Haiku 5.5 |
| LiveBench browser | 40.0% | 80.0% | Claude Haiku 5.5 |
| LiveBench long agentic | 11.1% | 57.6% | Claude Haiku 5.5 |
| SREBench (Vals AI) | Not measured | 5.7% | Only Claude Haiku 5.5 measured |
| Finance Agent (Vals AI) | 31.0% | 54.1% | Claude Haiku 5.5 |
| Tax Agent Bench (Vals AI) | 5.9% | 31.9% | Claude Haiku 5.5 |
| Legal Research Bench (Vals AI) | 10.6% | 43.3% | Claude Haiku 5.5 |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 4.2% | Only Claude Haiku 5.5 measured |
| Excel Modeling Benchmark (Vals AI) | 22.7% | 59.0% | Claude Haiku 5.5 |
| BioMysteryBench (Vals AI) | Not measured | 70.4% | Only Claude Haiku 5.5 measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 10.0% | Only Claude Haiku 5.5 measured |
| Vals Science Index | Not measured | 38.5% | Only Claude Haiku 5.5 measured |
| APEX-Agents | Not measured | 56.1% | Only Claude Haiku 5.5 measured |
| BALROG | 31.2% | Not measured | Only Claude Haiku 4.5 measured |
| DeepResearch Bench | 45.5% | Not measured | Only Claude Haiku 4.5 measured |
| Vending-Bench 2 | $459 | $3,602 | Claude Haiku 5.5 |
| Berkeley Function Calling Leaderboard (BFCL) | 68.7% | Not measured | Only Claude Haiku 4.5 measured |
| MCP Atlas | 40.2% | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 23 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 72.2% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench reasoning | 61.7% | 82.4% | Claude Haiku 5.5 |
| MysteryMechanism (Vals AI) | Not measured | 35.1% | Only Claude Haiku 5.5 measured |
| MMMU Pro (Vals AI) | 46.1% | Not measured | Only Claude Haiku 4.5 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 44.4% | Only Claude Haiku 5.5 measured |
| GPQA Diamond (Epoch AI run) | 71.2% | 89.6% | Claude Haiku 5.5 |
| ARC-AGI | 47.7% | 89.0% | Claude Haiku 5.5 |
| ARC-AGI-2 | 4.0% | 61.3% | Claude Haiku 5.5 |
| Chess puzzles | 8.0% | 55.0% | Claude Haiku 5.5 |
| Mystery game puzzles | Not measured | 30.0% | Only Claude Haiku 5.5 measured |
| EBR-bench | Not measured | 43.8% | Only Claude Haiku 5.5 measured |
| LMArena Text: hard prompts | 1421 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: expert | 1443 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: hard prompts in English | 1435 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| AIME | 82.7% | Not measured | Only Claude Haiku 4.5 measured |
| MGSM (Vals AI) | 92.2% | Not measured | Only Claude Haiku 4.5 measured |
| OTIS Mock AIME | 66.7% | 98.9% | Claude Haiku 5.5 |
| FrontierMath, tiers 1 to 3 | Not measured | 75.1% | Only Claude Haiku 5.5 measured |
| FrontierMath, tier 4 | Not measured | 46.3% | Only Claude Haiku 5.5 measured |
| ProofBench | Not measured | 89.0% | Only Claude Haiku 5.5 measured |
| MATH level 5 | 96.4% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: math | 1398 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: mathematical work | 1430 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 5 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| MMLU Pro | 78.7% | Not measured | Only Claude Haiku 4.5 measured |
| LegalBench (Vals AI) | 81.2% | Not measured | Only Claude Haiku 4.5 measured |
| CaseLaw (Vals AI) | 56.5% | Not measured | Only Claude Haiku 4.5 measured |
| CorpFin (Vals AI) | 60.6% | Not measured | Only Claude Haiku 4.5 measured |
| TaxEval (Vals AI) | 67.5% | Not measured | Only Claude Haiku 4.5 measured |
| MortgageTax (Vals AI) | 62.2% | Not measured | Only Claude Haiku 4.5 measured |
| MedQA (Vals AI) | 79.6% | Not measured | Only Claude Haiku 4.5 measured |
| MedCode (Vals AI) | 32.7% | 51.5% | Claude Haiku 5.5 |
| SimpleQA Verified | 13.2% | 23.8% | Claude Haiku 5.5 |
| LMArena Text: science | 1406 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: medicine and healthcare | 1394 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: legal and government | 1400 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: business and finance | 1400 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index07
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1122 | 1262 | Claude Haiku 5.5 |
| Design Arena: UI components | 1097 | 1283 | Claude Haiku 5.5 |
| Design Arena: game dev | 1096 | 1315 | Claude Haiku 5.5 |
| Design Arena: data viz | 1124 | 1297 | Claude Haiku 5.5 |
| Design Arena: 3D | 1071 | 1342 | Claude Haiku 5.5 |
| Design Arena: all code categories | 1114 | 1278 | Claude Haiku 5.5 |
| Design Arena: SVG | 1025 | Not measured | Only Claude Haiku 4.5 measured |
| Design Arena: ASCII art | 1140 | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench design | 59.9% | 83.1% | Claude Haiku 5.5 |
GeneralLike-for-likePublic boards, shown as published, kept out of the index16
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| Vals Index | Not measured | 58.7% | Only Claude Haiku 5.5 measured |
| LiveBench data analysis | 59.3% | 53.1% | Claude Haiku 4.5 |
| Public Benefits Bench (Vals AI) | 54.3% | 63.2% | Claude Haiku 5.5 |
| SAGE (Vals AI) | 31.8% | 45.8% | Claude Haiku 5.5 |
| MedScribe (Vals AI) | 85.2% | 89.5% | Claude Haiku 5.5 |
| Vals Multimodal Index | 42.9% | Not measured | Only Claude Haiku 4.5 measured |
| Long context reasoning (AA-LCR) | Not measured | 82.7% | Only Claude Haiku 5.5 measured |
| DTBench | 73.6% | 95.0% | Claude Haiku 5.5 |
| LMCA | 30.9% | 51.1% | Claude Haiku 5.5 |
| Furniture assembly | Not measured | 47.5% | Only Claude Haiku 5.5 measured |
| ExploitBench | 13.7% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text | 1397 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: instruction following | 1414 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: creative writing | 1371 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: English | 1414 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: non-English | 1377 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Chinese | 1418 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: German | 1374 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Japanese | 1338 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Korean | 1346 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: French | 1411 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Spanish | 1421 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Russian | 1381 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Polish | 1343 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: multi-turn | 1409 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: longer queries | 1427 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: writing and language | 1386 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: entertainment and media | 1369 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Document | 1420 | Not measured | Only Claude Haiku 4.5 measured |
| MultiChallenge | 50.5% | 67.7% | Claude Haiku 5.5 |
| EQ-Bench 4 | 1064 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 17 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Claude Haiku 5.5 costs less
Repository review
50K input + 3K output tokens
Claude Haiku 5.5 costs less
Agent loop
200K input + 10K output tokens
Claude Haiku 5.5 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Anthropic Claude Haiku 4.5 | Anthropic Claude Haiku 5.5 |
|---|---|---|
| Maker | Anthropic | Anthropic |
| Weights | No public weights listed | No public weights listed |
| Released | October 15, 2025 | October 7, 2026 |
| Context window | 200K | 1M |
| Input $/Mtok | $1.00 | $0.10 |
| Output $/Mtok | $5.00 | $0.50 |
| Coding index | 35.6 | 70.7 |
| Independent measurements behind it | 4 | 5 |
| Cost per solved task | $0.56 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Haiku 4.5 better than Claude Haiku 5.5 for coding?
Pick Claude Haiku 5.5 for coding: it scores 70.7 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5. Pick Claude Haiku 4.5 for work measured by LiveBench data analysis, where it leads.
Which is cheaper, Claude Haiku 4.5 or Claude Haiku 5.5?
Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Claude Haiku 5.5 costs $0.10 and $0.50. Cost per solved task is known for Claude Haiku 4.5 only.
Which has the bigger context window, Claude Haiku 4.5 or Claude Haiku 5.5?
Claude Haiku 5.5, with 1M tokens against 200K.
How many benchmarks is the Claude Haiku 4.5 vs Claude Haiku 5.5 comparison based on?
39 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 4.5's coding index rests on 4 independent benchmarks and Claude Haiku 5.5's on 5. Where only one model has a result, the page says so instead of naming a winner.