Claude Haiku 5.5 vs GPT-6 Astra
GPT-6 Astra leads Claude Haiku 5.5 on coding, 85.1 to 70.7 on the Vibe Coding Index, and Claude Haiku 5.5 costs 100.0x less per output token ($0.50 vs $50.00 per million). Updated October 22, 2026; 63 benchmarks have a result for both.
Claude Haiku 5.5 or GPT-6 Astra: which to pick
Pick GPT-6 Astra for coding: it scores 85.1 on the Vibe Coding Index against 70.7 for Claude Haiku 5.5.
Pick Claude Haiku 5.5 for output tokens 100.0x cheaper ($0.50 vs $50.00 per million) and work measured by Vibe Code Bench (Vals AI) or SWE-bench Multimodal (Vals AI), where it leads.
- Shared results
- 63
- Claude Haiku 5.5 only
- 2
- GPT-6 Astra only
- 66
- 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
GPT-6 Astra
GPT-6 Astra scores 85.1 against 70.7.
5 benchmarks behind each score
Intelligence
AA Intelligence Index
GPT-6 Astra
GPT-6 Astra leads, 52.7 against 43.4.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only GPT-6 Astra has a AA Agentic Index result, 51.0.
Directional only
Web design
Design Arena: websites
GPT-6 Astra
GPT-6 Astra leads, 1336 against 1262.
Same board, both measured
General
Vals Index
GPT-6 Astra
GPT-6 Astra leads, 65.0% against 58.7%.
Same board, both measured
Long documents
Listed context window
GPT-6 Astra
GPT-6 Astra 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-6 Astra $0.035 per turn.
List prices
At a glance
- Coding index
- Claude Haiku 5.5 70.7 from 5 benchmarks, GPT-6 Astra 85.1 from 5 benchmarks.
- Widest category
- Knowledge, 27.4 points apart on average over 2 shared benchmarks.
- Widest single gap
- Vending-Bench 2: Claude Haiku 5.5 $3,602 against GPT-6 Astra $15,515, 74.5 points apart on a 0 to 100 scale.
- Output price
- Claude Haiku 5.5 $0.50 against GPT-6 Astra $50.00 per million output tokens, 100.0x apart.
- Context window
- Claude Haiku 5.5 takes 1M tokens, GPT-6 Astra 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 Astra | Ties |
|---|---|---|---|---|
| Coding | 3 | 14 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 3 | 11 | ||
| Reasoning | 0 | 9 | ||
| Math | 0 | 4 | ||
| Knowledge | 1 | 1 | ||
| Web design | 1 | 6 | ||
| General | 2 | 6 | ||
| All shared boards | 10 | 53 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index314
| Benchmark | Claude Haiku 5.5 | GPT-6 Astra | Leader |
|---|---|---|---|
| LiveBench coding | 91.4% | 93.7% | GPT-6 Astra |
| LMArena WebDev | 1586 | 1774 | GPT-6 Astra |
| AA Coding Index | Not measured | 76.9 | Only GPT-6 Astra measured |
| Terminal-Bench 4 (Vals AI) | 36.4% | 59.6% | GPT-6 Astra |
| Vibe Code Bench (Vals AI) | 90.4% | 89.6% | Claude Haiku 5.5 |
| Code migration (Vals AI) | 44.6% | 67.7% | GPT-6 Astra |
| ProgramBench (Vals AI) | 2.5% | 5.5% | GPT-6 Astra |
| IOI (Vals AI) | 47.3% | 100.0% | GPT-6 Astra |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 87.3% | Only GPT-6 Astra measured |
| SWE-bench Multimodal (Vals AI) | 44.0% | 43.3% | Claude Haiku 5.5 |
| Vibe Code Bench 1-100 (Vals AI) | 20.4% | 27.6% | GPT-6 Astra |
| CyberBench (Vals AI) | 75.5% | 41.1% | Claude Haiku 5.5 |
| SciCode | 55.0% | 56.5% | GPT-6 Astra |
| FrontierCode | 46.4% | 53.3% | GPT-6 Astra |
| FrontierSWE | 43.8% | 65.5% | GPT-6 Astra |
| GSO-Bench | Not measured | 79.4% | Only GPT-6 Astra measured |
| WeirdML | Not measured | 93.3% | Only GPT-6 Astra measured |
| MirrorCode | Not measured | 46.7% | Only GPT-6 Astra measured |
| ALE-Bench | Not measured | 2951.3 | Only GPT-6 Astra measured |
| LMArena Text: coding | Not measured | 1489 | Only GPT-6 Astra measured |
| LMArena Text: software and IT | Not measured | 1474 | Only GPT-6 Astra measured |
| LMArena WebDev: React | 1605 | 1798 | GPT-6 Astra |
| LMArena WebDev: HTML | 1569 | 1775 | GPT-6 Astra |
| LMArena WebDev: from an image | Not measured | 1726 | Only GPT-6 Astra measured |
| SciCode | 9.2% | 12.3% | GPT-6 Astra |
| SWE-Bench Pro V2 | 87.2% | 96.9% | GPT-6 Astra |
| SWE Atlas: Codebase QnA | Not measured | 59.1% | Only GPT-6 Astra measured |
| SWE Atlas: Refactoring | Not measured | 59.1% | Only GPT-6 Astra measured |
| SWE Atlas: Test Writing | Not measured | 50.7% | Only GPT-6 Astra measured |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Haiku 5.5 | GPT-6 Astra | Leader |
|---|---|---|---|
| AA Intelligence Index | 43.4 | 52.7 | GPT-6 Astra |
| Epoch Capabilities Index | 159.3 | 168.8 | GPT-6 Astra |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index311
| Benchmark | Claude Haiku 5.5 | GPT-6 Astra | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 51.0 | Only GPT-6 Astra measured |
| Design Arena: agents building web apps | Not measured | 1374 | Only GPT-6 Astra measured |
| Design Arena: agents building full-stack apps | Not measured | 1357 | Only GPT-6 Astra measured |
| Design Arena: agents building mobile apps | Not measured | 1312 | Only GPT-6 Astra measured |
| Design Arena: agents building Godot games | Not measured | 1348 | Only GPT-6 Astra measured |
| Design Arena: PowerPoint slides | Not measured | 1217 | Only GPT-6 Astra measured |
| Design Arena: spreadsheets | Not measured | 1378 | Only GPT-6 Astra measured |
| LiveBench research | 81.9% | 85.2% | GPT-6 Astra |
| LiveBench browser | 80.0% | 84.0% | GPT-6 Astra |
| LiveBench long agentic | 57.6% | 82.4% | GPT-6 Astra |
| SREBench (Vals AI) | 5.7% | 56.9% | GPT-6 Astra |
| Finance Agent (Vals AI) | 54.1% | 53.5% | Claude Haiku 5.5 |
| Tax Agent Bench (Vals AI) | 31.9% | 20.7% | Claude Haiku 5.5 |
| Legal Research Bench (Vals AI) | 43.3% | 39.4% | Claude Haiku 5.5 |
| Harvey's Legal Agent Benchmark (Vals AI) | 4.2% | 7.1% | GPT-6 Astra |
| Excel Modeling Benchmark (Vals AI) | 59.0% | 71.7% | GPT-6 Astra |
| BioMysteryBench (Vals AI) | 70.4% | 79.3% | GPT-6 Astra |
| Terminal-Bench-Science (Vals AI) | 10.0% | 62.9% | GPT-6 Astra |
| Vals Science Index | 38.5% | 65.1% | GPT-6 Astra |
| Time Horizon Index (Vals AI) | Not measured | 90.5% | Only GPT-6 Astra measured |
| CUA-bench (Vals AI) | Not measured | 19.2% | Only GPT-6 Astra measured |
| Robo-bench (Vals AI) | Not measured | 23.3% | Only GPT-6 Astra measured |
| APEX-Agents | 56.1% | 64.7% | GPT-6 Astra |
| Remote Labor Index | Not measured | 20.8% | Only GPT-6 Astra measured |
| BALROG | Not measured | 68.3% | Only GPT-6 Astra measured |
| SpireClimb | Not measured | 25.7% | Only GPT-6 Astra measured |
| Vending-Bench 2 | $3,602 | $15,515 | GPT-6 Astra |
| Neither model has a result on the other 15 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index09
| Benchmark | Claude Haiku 5.5 | GPT-6 Astra | Leader |
|---|---|---|---|
| LiveBench reasoning | 82.4% | 92.7% | GPT-6 Astra |
| MysteryMechanism (Vals AI) | 35.1% | 53.1% | GPT-6 Astra |
| GPQA Diamond (Artificial Analysis run) | Not measured | 96.3% | Only GPT-6 Astra measured |
| Humanity's Last Exam (Artificial Analysis run) | 44.4% | 54.7% | GPT-6 Astra |
| GPQA Diamond (Epoch AI run) | 89.6% | 95.8% | GPT-6 Astra |
| ARC-AGI | 89.0% | 98.5% | GPT-6 Astra |
| ARC-AGI-2 | 61.3% | 95.0% | GPT-6 Astra |
| Chess puzzles | 55.0% | 74.0% | GPT-6 Astra |
| Mystery game puzzles | 30.0% | 84.0% | GPT-6 Astra |
| EBR-bench | 43.8% | 76.2% | GPT-6 Astra |
| LMArena Text: hard prompts | Not measured | 1463 | Only GPT-6 Astra measured |
| LMArena Text: expert | Not measured | 1489 | Only GPT-6 Astra measured |
| LMArena Text: hard prompts in English | Not measured | 1464 | Only GPT-6 Astra measured |
| LMArena Vision: diagrams | Not measured | 1297 | Only GPT-6 Astra measured |
| LMArena Vision: homework | Not measured | 1337 | Only GPT-6 Astra measured |
| Humanity's Last Exam (Scale run) | Not measured | 60.6% | Only GPT-6 Astra measured |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Claude Haiku 5.5 | GPT-6 Astra | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.9% | 100.0% | GPT-6 Astra |
| FrontierMath, tiers 1 to 3 | 75.1% | 93.7% | GPT-6 Astra |
| FrontierMath, tier 4 | 46.3% | 97.6% | GPT-6 Astra |
| ProofBench | 89.0% | 99.0% | GPT-6 Astra |
| LMArena Text: math | Not measured | 1465 | Only GPT-6 Astra measured |
| LMArena Text: mathematical work | Not measured | 1484 | Only GPT-6 Astra measured |
| MathArena | Not measured | 81.9% | Only GPT-6 Astra 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-6 Astra | Leader |
|---|---|---|---|
| MedCode (Vals AI) | 51.5% | 48.5% | Claude Haiku 5.5 |
| SimpleQA Verified | 23.8% | 75.6% | GPT-6 Astra |
| LMArena Text: science | Not measured | 1451 | Only GPT-6 Astra measured |
| LMArena Text: medicine and healthcare | Not measured | 1425 | Only GPT-6 Astra measured |
| LMArena Text: legal and government | Not measured | 1462 | Only GPT-6 Astra measured |
| LMArena Text: business and finance | Not measured | 1439 | Only GPT-6 Astra measured |
| FACTS Benchmark Suite | Not measured | 75.7% | Only GPT-6 Astra measured |
| PRBench Finance | Not measured | 47.5% | Only GPT-6 Astra measured |
| PRBench Legal | Not measured | 48.4% | Only GPT-6 Astra measured |
| Neither model has a result on the other 11 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index16
| Benchmark | Claude Haiku 5.5 | GPT-6 Astra | Leader |
|---|---|---|---|
| Design Arena: websites | 1262 | 1336 | GPT-6 Astra |
| Design Arena: UI components | 1283 | 1394 | GPT-6 Astra |
| Design Arena: game dev | 1315 | 1480 | GPT-6 Astra |
| Design Arena: data viz | 1297 | 1334 | GPT-6 Astra |
| Design Arena: 3D | 1342 | 1500 | GPT-6 Astra |
| Design Arena: all code categories | 1278 | 1379 | GPT-6 Astra |
| Design Arena: SVG | Not measured | 1430 | Only GPT-6 Astra measured |
| Design Arena: ASCII art | Not measured | 1353 | Only GPT-6 Astra measured |
| LiveBench design | 83.1% | 82.0% | Claude Haiku 5.5 |
GeneralLike-for-likePublic boards, shown as published, kept out of the index26
| Benchmark | Claude Haiku 5.5 | GPT-6 Astra | Leader |
|---|---|---|---|
| Vals Index | 58.7% | 65.0% | GPT-6 Astra |
| LiveBench data analysis | 53.1% | 83.0% | GPT-6 Astra |
| Public Benefits Bench (Vals AI) | 63.2% | Not measured | Only Claude Haiku 5.5 measured |
| SAGE (Vals AI) | 45.8% | 46.4% | GPT-6 Astra |
| MedScribe (Vals AI) | 89.5% | 87.9% | Claude Haiku 5.5 |
| Long context reasoning (AA-LCR) | 82.7% | 80.7% | Claude Haiku 5.5 |
| DTBench | 95.0% | 97.3% | GPT-6 Astra |
| LMCA | 51.1% | 64.4% | GPT-6 Astra |
| Furniture assembly | 47.5% | 80.0% | GPT-6 Astra |
| LMArena Text | Not measured | 1441 | Only GPT-6 Astra measured |
| LMArena Text: instruction following | Not measured | 1455 | Only GPT-6 Astra measured |
| LMArena Text: creative writing | Not measured | 1420 | Only GPT-6 Astra measured |
| LMArena Vision | Not measured | 1280 | Only GPT-6 Astra measured |
| LMArena Text: English | Not measured | 1447 | Only GPT-6 Astra measured |
| LMArena Text: non-English | Not measured | 1432 | Only GPT-6 Astra measured |
| LMArena Text: Chinese | Not measured | 1489 | Only GPT-6 Astra measured |
| LMArena Text: German | Not measured | 1459 | Only GPT-6 Astra measured |
| LMArena Text: Japanese | Not measured | 1405 | Only GPT-6 Astra measured |
| LMArena Text: Korean | Not measured | 1428 | Only GPT-6 Astra measured |
| LMArena Text: French | Not measured | 1432 | Only GPT-6 Astra measured |
| LMArena Text: Spanish | Not measured | 1422 | Only GPT-6 Astra measured |
| LMArena Text: Russian | Not measured | 1438 | Only GPT-6 Astra measured |
| LMArena Text: Polish | Not measured | 1422 | Only GPT-6 Astra measured |
| LMArena Text: multi-turn | Not measured | 1447 | Only GPT-6 Astra measured |
| LMArena Text: longer queries | Not measured | 1460 | Only GPT-6 Astra measured |
| LMArena Text: writing and language | Not measured | 1437 | Only GPT-6 Astra measured |
| LMArena Text: entertainment and media | Not measured | 1427 | Only GPT-6 Astra measured |
| LMArena Vision: English | Not measured | 1280 | Only GPT-6 Astra measured |
| LMArena Vision: Chinese | Not measured | 1361 | Only GPT-6 Astra measured |
| LMArena Vision: reading text | Not measured | 1292 | Only GPT-6 Astra measured |
| LMArena Vision: creative writing | Not measured | 1286 | Only GPT-6 Astra 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 Astra | 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-6 Astra |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | October 7, 2026 | September 4, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $0.10 | $10.00 |
| Output $/Mtok | $0.50 | $50.00 |
| Coding index | 70.7 | 85.1 |
| 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 Astra for coding?
Pick GPT-6 Astra for coding: it scores 85.1 on the Vibe Coding Index against 70.7 for Claude Haiku 5.5. Pick Claude Haiku 5.5 for output tokens 100.0x cheaper ($0.50 vs $50.00 per million) and work measured by Vibe Code Bench (Vals AI) or SWE-bench Multimodal (Vals AI), where it leads.
Which is cheaper, Claude Haiku 5.5 or GPT-6 Astra?
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens; GPT-6 Astra costs $10.00 and $50.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Claude Haiku 5.5 or GPT-6 Astra?
GPT-6 Astra, with 1.05M tokens against 1M.
How many benchmarks is the Claude Haiku 5.5 vs GPT-6 Astra comparison based on?
63 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 Astra's on 5. Where only one model has a result, the page says so instead of naming a winner.