Claude Haiku 5.5 vs GPT-5.6 Luna
Updated October 21, 2026. 57 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Claude Haiku 5.5 for coding: it scores 75.9 on the Vibe Coding Index against 61.5 for GPT-5.6 Luna.
Pick GPT-5.6 Luna when the context window is larger, 1.05M against 1M tokens, or when what matters is IOI (Vals AI) or Vibe Code Bench 1-100 (Vals AI), where it leads.
- Shared results
- 57
- Claude Haiku 5.5 only
- 5
- GPT-5.6 Luna only
- 59
- Like-for-like categories
- 8 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
Claude Haiku 5.5
Claude Haiku 5.5 scores 75.9 against 61.5.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
Claude Haiku 5.5
Claude Haiku 5.5 leads, 43.4 against 37.3.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only GPT-5.6 Luna has a AA Agentic Index result, 42.1.
Directional only
Reasoning
GPQA Diamond
No call
Only GPT-5.6 Luna has a GPQA Diamond result, 91.7%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-5.6 Luna has a MMLU Pro result, 86.0%.
Directional only
Web design
Design Arena: websites
Claude Haiku 5.5
Claude Haiku 5.5 leads, 1263 against 1256.
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
GPT-5.6 Luna
GPT-5.6 Luna takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Claude Haiku 5.5
Claude Haiku 5.5 $0.0003, GPT-5.6 Luna $0.0008 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.6 Luna has the number, $0.04.
Directional only
At a glance
- Coding index
- Claude Haiku 5.5 75.9 from 2 benchmarks, GPT-5.6 Luna 61.5 from 2 benchmarks.
- Widest category
- Knowledge, 13.2 points apart on average over 2 shared benchmarks.
- Widest single gap
- LiveBench research: Claude Haiku 5.5 81.9% against GPT-5.6 Luna 51.0%, 30.9 points apart on a 0 to 100 scale.
- Output price
- Claude Haiku 5.5 $0.50 against GPT-5.6 Luna $1.20 per million output tokens, 2.4x apart.
- Context window
- Claude Haiku 5.5 takes 1M tokens, GPT-5.6 Luna 1.05M.
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 5.5 | Bars | GPT-5.6 Luna | Ties |
|---|---|---|---|---|
| Coding | 11 | 2 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 10 | 3 | ||
| Reasoning | 6 | 2 | ||
| Math | 2 | 2 | ||
| Knowledge | 1 | 1 | ||
| Web design | 7 | 0 | ||
| General | 6 | 2 | ||
| All shared boards | 45 | 12 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index112
| Benchmark | Claude Haiku 5.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| LiveBench coding | 91.4% | 73.6% | Claude Haiku 5.5 |
| LMArena WebDev | 1586 | 1518 | Claude Haiku 5.5 |
| AA Coding Index | Not measured | 71.4 | Only GPT-5.6 Luna measured |
| SWE-bench Verified (Vals AI) | Not measured | 93.0% | Only GPT-5.6 Luna measured |
| Terminal-Bench 4 (Vals AI) | 36.4% | 11.6% | Claude Haiku 5.5 |
| Vibe Code Bench (Vals AI) | 90.4% | 77.1% | Claude Haiku 5.5 |
| Code migration (Vals AI) | 44.6% | 44.5% | Claude Haiku 5.5 |
| ProgramBench (Vals AI) | 2.5% | 0.0% | Claude Haiku 5.5 |
| IOI (Vals AI) | 47.3% | 61.8% | GPT-5.6 Luna |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 79.0% | Only GPT-5.6 Luna measured |
| SWE-bench Multimodal (Vals AI) | 44.0% | Not measured | Only Claude Haiku 5.5 measured |
| Vibe Code Bench 1-100 (Vals AI) | 20.4% | 22.6% | GPT-5.6 Luna |
| SkillsBench (Vals AI) | Not measured | 60.5% | Only GPT-5.6 Luna measured |
| CyberBench (Vals AI) | 75.5% | 73.6% | Claude Haiku 5.5 |
| SciCode | 55.0% | 53.6% | Claude Haiku 5.5 |
| FrontierCode | 46.4% | 39.8% | Claude Haiku 5.5 |
| FrontierSWE | 43.8% | Not measured | Only Claude Haiku 5.5 measured |
| WeirdML | Not measured | 60.9% | Only GPT-5.6 Luna measured |
| ALE-Bench | Not measured | 1667.4 | Only GPT-5.6 Luna measured |
| LMArena Text: coding | Not measured | 1466 | Only GPT-5.6 Luna measured |
| LMArena Text: software and IT | Not measured | 1463 | Only GPT-5.6 Luna measured |
| LMArena WebDev: React | 1605 | 1508 | Claude Haiku 5.5 |
| LMArena WebDev: HTML | 1569 | 1520 | Claude Haiku 5.5 |
| LMArena WebDev: from an image | Not measured | 1517 | Only GPT-5.6 Luna measured |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Haiku 5.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| AA Intelligence Index | 43.4 | 37.3 | Claude Haiku 5.5 |
| Epoch Capabilities Index | 159.3 | 156.5 | Claude Haiku 5.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index103
| Benchmark | Claude Haiku 5.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 42.1 | Only GPT-5.6 Luna measured |
| LiveBench research | 81.9% | 51.0% | Claude Haiku 5.5 |
| LiveBench browser | 80.0% | 68.0% | Claude Haiku 5.5 |
| LiveBench long agentic | 57.6% | 30.4% | Claude Haiku 5.5 |
| SREBench (Vals AI) | 5.7% | 1.5% | Claude Haiku 5.5 |
| Finance Agent (Vals AI) | 54.1% | 55.0% | GPT-5.6 Luna |
| Tax Agent Bench (Vals AI) | 31.9% | 24.8% | Claude Haiku 5.5 |
| Legal Research Bench (Vals AI) | 43.3% | 36.5% | Claude Haiku 5.5 |
| Harvey's Legal Agent Benchmark (Vals AI) | 4.2% | Not measured | Only Claude Haiku 5.5 measured |
| Excel Modeling Benchmark (Vals AI) | 59.0% | 67.1% | GPT-5.6 Luna |
| BioMysteryBench (Vals AI) | 70.4% | 61.5% | Claude Haiku 5.5 |
| Terminal-Bench-Science (Vals AI) | 10.0% | 0.0% | Claude Haiku 5.5 |
| Vals Science Index | 38.5% | 25.3% | Claude Haiku 5.5 |
| APEX-Agents | 56.1% | 43.0% | Claude Haiku 5.5 |
| BALROG | Not measured | 45.6% | Only GPT-5.6 Luna measured |
| Vending-Bench 2 | $3,602 | $4,095 | GPT-5.6 Luna |
| Neither model has a result on the other 23 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index62
| Benchmark | Claude Haiku 5.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 91.7% | Only GPT-5.6 Luna measured |
| LiveBench reasoning | 82.4% | 85.6% | GPT-5.6 Luna |
| MysteryMechanism (Vals AI) | 35.1% | 14.4% | Claude Haiku 5.5 |
| MMMU Pro (Vals AI) | Not measured | 85.0% | Only GPT-5.6 Luna measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 91.1% | Only GPT-5.6 Luna measured |
| Humanity's Last Exam (Artificial Analysis run) | 44.4% | 39.5% | Claude Haiku 5.5 |
| GPQA Diamond (Epoch AI run) | 89.6% | 91.6% | GPT-5.6 Luna |
| ARC-AGI | 89.0% | 88.0% | Claude Haiku 5.5 |
| ARC-AGI-2 | 61.3% | 59.5% | Claude Haiku 5.5 |
| SimpleBench | Not measured | 46.8% | Only GPT-5.6 Luna measured |
| Chess puzzles | 55.0% | 43.0% | Claude Haiku 5.5 |
| Mystery game puzzles | 30.0% | 21.0% | Claude Haiku 5.5 |
| EBR-bench | 43.8% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: hard prompts | Not measured | 1451 | Only GPT-5.6 Luna measured |
| LMArena Text: expert | Not measured | 1478 | Only GPT-5.6 Luna measured |
| LMArena Text: hard prompts in English | Not measured | 1460 | Only GPT-5.6 Luna measured |
| LMArena Vision: diagrams | Not measured | 1273 | Only GPT-5.6 Luna measured |
| LMArena Vision: homework | Not measured | 1282 | Only GPT-5.6 Luna measured |
| Neither model has a result on the other 3 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | Claude Haiku 5.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.9% | 98.3% | Claude Haiku 5.5 |
| FrontierMath, tiers 1 to 3 | 75.1% | 82.1% | GPT-5.6 Luna |
| FrontierMath, tier 4 | 46.3% | 61.0% | GPT-5.6 Luna |
| ProofBench | 89.0% | 60.0% | Claude Haiku 5.5 |
| LMArena Text: math | Not measured | 1459 | Only GPT-5.6 Luna measured |
| LMArena Text: mathematical work | Not measured | 1470 | Only GPT-5.6 Luna measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Claude Haiku 5.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 86.0% | Only GPT-5.6 Luna measured |
| LegalBench (Vals AI) | Not measured | 84.0% | Only GPT-5.6 Luna measured |
| CorpFin (Vals AI) | Not measured | 64.2% | Only GPT-5.6 Luna measured |
| TaxEval (Vals AI) | Not measured | 76.2% | Only GPT-5.6 Luna measured |
| MortgageTax (Vals AI) | Not measured | 67.3% | Only GPT-5.6 Luna measured |
| MedCode (Vals AI) | 51.5% | 42.4% | Claude Haiku 5.5 |
| SimpleQA Verified | 23.8% | 41.0% | GPT-5.6 Luna |
| LMArena Text: science | Not measured | 1433 | Only GPT-5.6 Luna measured |
| LMArena Text: medicine and healthcare | Not measured | 1399 | Only GPT-5.6 Luna measured |
| LMArena Text: legal and government | Not measured | 1446 | Only GPT-5.6 Luna measured |
| LMArena Text: business and finance | Not measured | 1439 | Only GPT-5.6 Luna measured |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | Claude Haiku 5.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| Design Arena: websites | 1263 | 1256 | Claude Haiku 5.5 |
| Design Arena: UI components | 1295 | 1250 | Claude Haiku 5.5 |
| Design Arena: game dev | 1315 | 1196 | Claude Haiku 5.5 |
| Design Arena: data viz | 1292 | 1212 | Claude Haiku 5.5 |
| Design Arena: 3D | 1343 | 1121 | Claude Haiku 5.5 |
| Design Arena: all code categories | 1279 | 1231 | Claude Haiku 5.5 |
| Design Arena: SVG | Not measured | 1193 | Only GPT-5.6 Luna measured |
| Design Arena: ASCII art | Not measured | 1144 | Only GPT-5.6 Luna measured |
| LiveBench design | 83.1% | 76.0% | Claude Haiku 5.5 |
GeneralLike-for-likePublic boards, shown as published, kept out of the index62
| Benchmark | Claude Haiku 5.5 | GPT-5.6 Luna | Leader |
|---|---|---|---|
| Vals Index | 58.7% | Not measured | Only Claude Haiku 5.5 measured |
| LiveBench data analysis | 53.1% | 78.0% | GPT-5.6 Luna |
| Public Benefits Bench (Vals AI) | 63.2% | 61.2% | Claude Haiku 5.5 |
| SAGE (Vals AI) | 45.8% | 44.2% | Claude Haiku 5.5 |
| MedScribe (Vals AI) | 89.5% | 84.4% | Claude Haiku 5.5 |
| Vals Multimodal Index | Not measured | 69.1% | Only GPT-5.6 Luna measured |
| Long context reasoning (AA-LCR) | 82.7% | 83.7% | GPT-5.6 Luna |
| DTBench | 95.0% | 89.1% | Claude Haiku 5.5 |
| LMCA | 51.1% | 48.5% | Claude Haiku 5.5 |
| Surface Evolver Bench | Not measured | 61.9% | Only GPT-5.6 Luna measured |
| Furniture assembly | 47.5% | 42.5% | Claude Haiku 5.5 |
| LMArena Text | Not measured | 1431 | Only GPT-5.6 Luna measured |
| LMArena Text: instruction following | Not measured | 1437 | Only GPT-5.6 Luna measured |
| LMArena Text: creative writing | Not measured | 1396 | Only GPT-5.6 Luna measured |
| LMArena Vision | Not measured | 1257 | Only GPT-5.6 Luna measured |
| LMArena Text: English | Not measured | 1441 | Only GPT-5.6 Luna measured |
| LMArena Text: non-English | Not measured | 1417 | Only GPT-5.6 Luna measured |
| LMArena Text: Chinese | Not measured | 1470 | Only GPT-5.6 Luna measured |
| LMArena Text: German | Not measured | 1455 | Only GPT-5.6 Luna measured |
| LMArena Text: Japanese | Not measured | 1415 | Only GPT-5.6 Luna measured |
| LMArena Text: Korean | Not measured | 1415 | Only GPT-5.6 Luna measured |
| LMArena Text: French | Not measured | 1458 | Only GPT-5.6 Luna measured |
| LMArena Text: Spanish | Not measured | 1446 | Only GPT-5.6 Luna measured |
| LMArena Text: Russian | Not measured | 1427 | Only GPT-5.6 Luna measured |
| LMArena Text: Polish | Not measured | 1405 | Only GPT-5.6 Luna measured |
| LMArena Text: multi-turn | Not measured | 1434 | Only GPT-5.6 Luna measured |
| LMArena Text: longer queries | Not measured | 1436 | Only GPT-5.6 Luna measured |
| LMArena Text: writing and language | Not measured | 1419 | Only GPT-5.6 Luna measured |
| LMArena Text: entertainment and media | Not measured | 1402 | Only GPT-5.6 Luna measured |
| LMArena Vision: English | Not measured | 1263 | Only GPT-5.6 Luna measured |
| LMArena Vision: Chinese | Not measured | 1294 | Only GPT-5.6 Luna measured |
| LMArena Vision: reading text | Not measured | 1264 | Only GPT-5.6 Luna measured |
| LMArena Vision: humor | Not measured | 1190 | Only GPT-5.6 Luna measured |
| LMArena Vision: creative writing | Not measured | 1257 | Only GPT-5.6 Luna measured |
| LMArena Document | Not measured | 1457 | Only GPT-5.6 Luna measured |
| Neither model has a result on the other 11 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Haiku 5.5 | GPT-5.6 Luna | 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 5.5 | OpenAI GPT-5.6 Luna |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | October 7, 2026 | July 9, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $0.10 | $0.20 |
| Output $/Mtok | $0.50 | $1.20 |
| Coding index | 75.9 | 61.5 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | Not computable | $0.04 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Haiku 5.5 better than GPT-5.6 Luna for coding?
Pick Claude Haiku 5.5 for coding: it scores 75.9 on the Vibe Coding Index against 61.5 for GPT-5.6 Luna. Pick GPT-5.6 Luna when the context window is larger, 1.05M against 1M tokens, or when what matters is IOI (Vals AI) or Vibe Code Bench 1-100 (Vals AI), where it leads.
Which is cheaper, Claude Haiku 5.5 or GPT-5.6 Luna?
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens; GPT-5.6 Luna costs $0.20 and $1.20. Cost per solved task is known for GPT-5.6 Luna only.
Which has the bigger context window, Claude Haiku 5.5 or GPT-5.6 Luna?
GPT-5.6 Luna, with 1.05M tokens against 1M.
How many benchmarks is the Claude Haiku 5.5 vs GPT-5.6 Luna comparison based on?
57 benchmarks have a result for both models as of October 21, 2026. Claude Haiku 5.5's coding index rests on 2 independent benchmarks and GPT-5.6 Luna's on 2. Where only one model has a result, the page says so instead of naming a winner.