Claude Haiku 5.5 vs GPT-6 Luna
Claude Haiku 5.5 leads GPT-6 Luna on coding, 70.7 to 57.3 on the Vibe Coding Index, at about the same output price ($0.50 vs $0.50 per million). Updated October 22, 2026; 58 benchmarks have a result for both.
Claude Haiku 5.5 or GPT-6 Luna: which to pick
Pick Claude Haiku 5.5 for coding: it scores 70.7 on the Vibe Coding Index against 57.3 for GPT-6 Luna.
Pick GPT-6 Luna for a larger context window (1.05M against 1M tokens) and work measured by IOI (Vals AI) or CyberBench (Vals AI), where it leads.
- Shared results
- 58
- Claude Haiku 5.5 only
- 7
- GPT-6 Luna only
- 46
- 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 57.3.
5 benchmarks behind each score
Intelligence
AA Intelligence Index
Claude Haiku 5.5
Claude Haiku 5.5 leads, 43.4 against 38.1.
Same board, both measured
Web design
Design Arena: websites
GPT-6 Luna
GPT-6 Luna leads, 1271 against 1262.
Same board, both measured
General
Vals Index
Claude Haiku 5.5
Claude Haiku 5.5 leads, 58.7% against 52.3%.
Same board, both measured
Long documents
Listed context window
GPT-6 Luna
GPT-6 Luna takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
No call
Claude Haiku 5.5 $0.0003, GPT-6 Luna $0.0003 per turn.
List prices
At a glance
- Coding index
- Claude Haiku 5.5 70.7 from 5 benchmarks, GPT-6 Luna 57.3 from 5 benchmarks.
- Widest category
- Knowledge, 12.2 points apart on average over 2 shared benchmarks.
- Widest single gap
- LiveBench research: Claude Haiku 5.5 81.9% against GPT-6 Luna 43.5%, 38.4 points apart on a 0 to 100 scale.
- Output price
- Both cost $0.50 per million output tokens.
- Context window
- Claude Haiku 5.5 takes 1M tokens, GPT-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-6 Luna | Ties |
|---|---|---|---|---|
| Coding | 10 | 3 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 11 | 1 | 1 tie | |
| Reasoning | 7 | 1 | ||
| Math | 1 | 2 | 1 tie | |
| Knowledge | 1 | 1 | ||
| Web design | 5 | 2 | ||
| General | 6 | 3 | ||
| All shared boards | 43 | 13 | 2 ties |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index103
| Benchmark | Claude Haiku 5.5 | GPT-6 Luna | Leader |
|---|---|---|---|
| LiveBench coding | 91.4% | 84.5% | Claude Haiku 5.5 |
| LMArena WebDev | 1586 | 1578 | Claude Haiku 5.5 |
| Terminal-Bench 4 (Vals AI) | 36.4% | 13.6% | Claude Haiku 5.5 |
| Vibe Code Bench (Vals AI) | 90.4% | 81.7% | Claude Haiku 5.5 |
| Code migration (Vals AI) | 44.6% | 42.5% | Claude Haiku 5.5 |
| ProgramBench (Vals AI) | 2.5% | 0.5% | Claude Haiku 5.5 |
| IOI (Vals AI) | 47.3% | 55.6% | GPT-6 Luna |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 73.0% | Only GPT-6 Luna measured |
| SWE-bench Multimodal (Vals AI) | 44.0% | 37.5% | Claude Haiku 5.5 |
| Vibe Code Bench 1-100 (Vals AI) | 20.4% | Not measured | Only Claude Haiku 5.5 measured |
| CyberBench (Vals AI) | 75.5% | 76.3% | GPT-6 Luna |
| SciCode | 55.0% | 54.6% | Claude Haiku 5.5 |
| FrontierCode | 46.4% | 42.4% | Claude Haiku 5.5 |
| FrontierSWE | 43.8% | Not measured | Only Claude Haiku 5.5 measured |
| ALE-Bench | Not measured | 1576.9 | Only GPT-6 Luna measured |
| LMArena Text: coding | Not measured | 1437 | Only GPT-6 Luna measured |
| LMArena Text: software and IT | Not measured | 1423 | Only GPT-6 Luna measured |
| LMArena WebDev: React | 1605 | 1573 | Claude Haiku 5.5 |
| LMArena WebDev: HTML | 1569 | 1595 | GPT-6 Luna |
| LMArena WebDev: from an image | Not measured | 1571 | Only GPT-6 Luna measured |
| SciCode | 9.2% | Not measured | Only Claude Haiku 5.5 measured |
| SWE-Bench Pro V2 | 87.2% | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 21 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Haiku 5.5 | GPT-6 Luna | Leader |
|---|---|---|---|
| AA Intelligence Index | 43.4 | 38.1 | Claude Haiku 5.5 |
| Epoch Capabilities Index | 159.3 | 156.8 | Claude Haiku 5.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index111
| Benchmark | Claude Haiku 5.5 | GPT-6 Luna | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | Not measured | 1191 | Only GPT-6 Luna measured |
| Design Arena: agents building full-stack apps | Not measured | 1158 | Only GPT-6 Luna measured |
| Design Arena: agents building mobile apps | Not measured | 1131 | Only GPT-6 Luna measured |
| LiveBench research | 81.9% | 43.5% | Claude Haiku 5.5 |
| LiveBench browser | 80.0% | 72.0% | Claude Haiku 5.5 |
| LiveBench long agentic | 57.6% | 48.1% | Claude Haiku 5.5 |
| SREBench (Vals AI) | 5.7% | 2.7% | Claude Haiku 5.5 |
| Finance Agent (Vals AI) | 54.1% | 49.9% | Claude Haiku 5.5 |
| Tax Agent Bench (Vals AI) | 31.9% | 19.9% | Claude Haiku 5.5 |
| Legal Research Bench (Vals AI) | 43.3% | 30.3% | Claude Haiku 5.5 |
| Harvey's Legal Agent Benchmark (Vals AI) | 4.2% | 4.2% | Tie |
| Excel Modeling Benchmark (Vals AI) | 59.0% | 68.5% | GPT-6 Luna |
| BioMysteryBench (Vals AI) | 70.4% | 61.5% | Claude Haiku 5.5 |
| Terminal-Bench-Science (Vals AI) | 10.0% | 4.3% | Claude Haiku 5.5 |
| Vals Science Index | 38.5% | 28.4% | Claude Haiku 5.5 |
| APEX-Agents | 56.1% | 44.3% | Claude Haiku 5.5 |
| SpireClimb | Not measured | 0.0% | Only GPT-6 Luna measured |
| Vending-Bench 2 | $3,602 | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index71
| Benchmark | Claude Haiku 5.5 | GPT-6 Luna | Leader |
|---|---|---|---|
| LiveBench reasoning | 82.4% | 81.8% | Claude Haiku 5.5 |
| MysteryMechanism (Vals AI) | 35.1% | 19.4% | Claude Haiku 5.5 |
| Humanity's Last Exam (Artificial Analysis run) | 44.4% | 38.5% | Claude Haiku 5.5 |
| GPQA Diamond (Epoch AI run) | 89.6% | 90.5% | GPT-6 Luna |
| ARC-AGI | 89.0% | 86.7% | Claude Haiku 5.5 |
| ARC-AGI-2 | 61.3% | 59.3% | Claude Haiku 5.5 |
| Chess puzzles | 55.0% | 36.0% | Claude Haiku 5.5 |
| Mystery game puzzles | 30.0% | 7.0% | Claude Haiku 5.5 |
| EBR-bench | 43.8% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: hard prompts | Not measured | 1410 | Only GPT-6 Luna measured |
| LMArena Text: expert | Not measured | 1442 | Only GPT-6 Luna measured |
| LMArena Text: hard prompts in English | Not measured | 1410 | Only GPT-6 Luna measured |
| LMArena Vision: diagrams | Not measured | 1245 | Only GPT-6 Luna measured |
| LMArena Vision: homework | Not measured | 1261 | Only GPT-6 Luna measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | Claude Haiku 5.5 | GPT-6 Luna | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.9% | 98.9% | Tie |
| FrontierMath, tiers 1 to 3 | 75.1% | 78.9% | GPT-6 Luna |
| FrontierMath, tier 4 | 46.3% | 56.1% | GPT-6 Luna |
| ProofBench | 89.0% | 64.0% | Claude Haiku 5.5 |
| LMArena Text: math | Not measured | 1409 | Only GPT-6 Luna measured |
| LMArena Text: mathematical work | Not measured | 1427 | Only GPT-6 Luna measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Claude Haiku 5.5 | GPT-6 Luna | Leader |
|---|---|---|---|
| MedCode (Vals AI) | 51.5% | 44.7% | Claude Haiku 5.5 |
| SimpleQA Verified | 23.8% | 41.4% | GPT-6 Luna |
| LMArena Text: science | Not measured | 1386 | Only GPT-6 Luna measured |
| LMArena Text: medicine and healthcare | Not measured | 1352 | Only GPT-6 Luna measured |
| LMArena Text: legal and government | Not measured | 1400 | Only GPT-6 Luna measured |
| LMArena Text: business and finance | Not measured | 1388 | Only GPT-6 Luna measured |
| FACTS Benchmark Suite | Not measured | 63.3% | Only GPT-6 Luna measured |
| PRBench Legal | Not measured | 42.9% | Only GPT-6 Luna measured |
| Neither model has a result on the other 12 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index52
| Benchmark | Claude Haiku 5.5 | GPT-6 Luna | Leader |
|---|---|---|---|
| Design Arena: websites | 1262 | 1271 | GPT-6 Luna |
| Design Arena: UI components | 1283 | 1295 | GPT-6 Luna |
| Design Arena: game dev | 1315 | 1258 | Claude Haiku 5.5 |
| Design Arena: data viz | 1297 | 1217 | Claude Haiku 5.5 |
| Design Arena: 3D | 1342 | 1218 | Claude Haiku 5.5 |
| Design Arena: all code categories | 1278 | 1270 | Claude Haiku 5.5 |
| Design Arena: SVG | Not measured | 1253 | Only GPT-6 Luna measured |
| Design Arena: ASCII art | Not measured | 1153 | Only GPT-6 Luna measured |
| LiveBench design | 83.1% | 82.5% | Claude Haiku 5.5 |
GeneralLike-for-likePublic boards, shown as published, kept out of the index63
| Benchmark | Claude Haiku 5.5 | GPT-6 Luna | Leader |
|---|---|---|---|
| Vals Index | 58.7% | 52.3% | Claude Haiku 5.5 |
| LiveBench data analysis | 53.1% | 73.4% | GPT-6 Luna |
| Public Benefits Bench (Vals AI) | 63.2% | 57.6% | Claude Haiku 5.5 |
| SAGE (Vals AI) | 45.8% | 48.1% | GPT-6 Luna |
| MedScribe (Vals AI) | 89.5% | 83.7% | Claude Haiku 5.5 |
| Long context reasoning (AA-LCR) | 82.7% | 83.3% | GPT-6 Luna |
| DTBench | 95.0% | 90.1% | Claude Haiku 5.5 |
| LMCA | 51.1% | 44.5% | Claude Haiku 5.5 |
| Furniture assembly | 47.5% | 44.2% | Claude Haiku 5.5 |
| LMArena Text | Not measured | 1389 | Only GPT-6 Luna measured |
| LMArena Text: instruction following | Not measured | 1408 | Only GPT-6 Luna measured |
| LMArena Text: creative writing | Not measured | 1363 | Only GPT-6 Luna measured |
| LMArena Vision | Not measured | 1216 | Only GPT-6 Luna measured |
| LMArena Text: English | Not measured | 1393 | Only GPT-6 Luna measured |
| LMArena Text: non-English | Not measured | 1381 | Only GPT-6 Luna measured |
| LMArena Text: Chinese | Not measured | 1427 | Only GPT-6 Luna measured |
| LMArena Text: German | Not measured | 1376 | Only GPT-6 Luna measured |
| LMArena Text: Japanese | Not measured | 1369 | Only GPT-6 Luna measured |
| LMArena Text: Korean | Not measured | 1359 | Only GPT-6 Luna measured |
| LMArena Text: French | Not measured | 1408 | Only GPT-6 Luna measured |
| LMArena Text: Spanish | Not measured | 1391 | Only GPT-6 Luna measured |
| LMArena Text: Russian | Not measured | 1392 | Only GPT-6 Luna measured |
| LMArena Text: Polish | Not measured | 1383 | Only GPT-6 Luna measured |
| LMArena Text: multi-turn | Not measured | 1392 | Only GPT-6 Luna measured |
| LMArena Text: longer queries | Not measured | 1408 | Only GPT-6 Luna measured |
| LMArena Text: writing and language | Not measured | 1384 | Only GPT-6 Luna measured |
| LMArena Text: entertainment and media | Not measured | 1364 | Only GPT-6 Luna measured |
| LMArena Vision: English | Not measured | 1204 | Only GPT-6 Luna measured |
| LMArena Vision: Chinese | Not measured | 1266 | Only GPT-6 Luna measured |
| LMArena Vision: reading text | Not measured | 1225 | Only GPT-6 Luna measured |
| LMArena Vision: creative writing | Not measured | 1205 | Only GPT-6 Luna measured |
| MultiChallenge | 67.7% | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Haiku 5.5 | GPT-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
Same cost
Repository review
50K input + 3K output tokens
Same cost
Agent loop
200K input + 10K output tokens
Same cost
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-6 Luna |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | October 7, 2026 | September 22, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $0.10 | $0.10 |
| Output $/Mtok | $0.50 | $0.50 |
| Coding index | 70.7 | 57.3 |
| Independent measurements behind it | 5 | 5 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Haiku 5.5 better than GPT-6 Luna for coding?
Pick Claude Haiku 5.5 for coding: it scores 70.7 on the Vibe Coding Index against 57.3 for GPT-6 Luna. Pick GPT-6 Luna for a larger context window (1.05M against 1M tokens) and work measured by IOI (Vals AI) or CyberBench (Vals AI), where it leads.
Which is cheaper, Claude Haiku 5.5 or GPT-6 Luna?
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens; GPT-6 Luna costs $0.10 and $0.50. Cost per solved task is known for neither of them.
Which has the bigger context window, Claude Haiku 5.5 or GPT-6 Luna?
GPT-6 Luna, with 1.05M tokens against 1M.
How many benchmarks is the Claude Haiku 5.5 vs GPT-6 Luna comparison based on?
58 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 5.5's coding index rests on 5 independent benchmarks and GPT-6 Luna's on 5. Where only one model has a result, the page says so instead of naming a winner.