Claude Haiku 5.5 vs GPT-6 Luna
Claude Haiku 5.5 is from Anthropic. GPT-6 Luna is from OpenAI. Claude Haiku 5.5 costs $0.500 per million output tokens. GPT-6 Luna costs $0.500. Claude Haiku 5.5 leads on the Epoch Capabilities Index: Claude Haiku 5.5 scores 160.4 and GPT-6 Luna scores 156.8. A typical request, about 1,000 words in and 400 words out, costs $0.0004 on Claude Haiku 5.5 and $0.0004 on GPT-6 Luna.
Prices updated . Benchmarks updated .
| Claude Haiku 5.5 | GPT-6 Luna | |
|---|---|---|
| Lab | Anthropic | OpenAI |
| You send / 1M | $0.100 | $0.100 |
| It replies / 1M | $0.500 | $0.500 |
| Context | 1M | 1.05M |
| Launched | 2026-10-07 | 2026-09-22 |
| Weights | Closed | Closed |
| Typical request | $0.0004 | $0.0004 |
| ECI | 160.4 | 156.8 |
| GPQA | 89.7% | 90.5% |
| ARC-AGI-2 | 61.3% | 59.3% |
| HLE | 30.1% | n/a |
| AIME | 98.9% | 98.9% |
| SimpleQA | 23.8% | 41.4% |
| CritPt | 22.6% | 19.4% |
| Arena | 1,401 | 1,389 |
| Arena web | 1,589 | 1,579 |
Which is cheaper?
Claude Haiku 5.5 and GPT-6 Luna cost the same for output tokens, $0.500 per million. Input tokens are $0.100 per million for Claude Haiku 5.5 and $0.100 per million for GPT-6 Luna. A typical request, about 1,000 words in and 400 words out, costs $0.0004 on Claude Haiku 5.5 and $0.0004 on GPT-6 Luna.
Which scores higher?
Claude Haiku 5.5 scores higher on Epoch Capabilities Index: 160.4 against 156.8 for GPT-6 Luna. That index is an independent composite from Epoch AI. Lab-reported scores are kept off this comparison. Context windows are 1M and 1.05M. Prices are US dollars per million tokens at current public rates.
Verdict
Claude Haiku 5.5 scores higher on Epoch Capabilities Index (160.4 vs 156.8). A public token price is missing for at least one model, so this page does not call a cheaper winner. Context is 1M for Claude Haiku 5.5 and 1.05M for GPT-6 Luna. Use the model pages for every score on file, including lab-reported numbers.
FAQ
Which is cheaper, Claude Haiku 5.5 vs GPT-6 Luna?
Claude Haiku 5.5 and GPT-6 Luna cost the same for output tokens, $0.500 per million. Input tokens are $0.100 per million for Claude Haiku 5.5 and $0.100 per million for GPT-6 Luna. A typical request, about 1,000 words in and 400 words out, costs $0.0004 on Claude Haiku 5.5 and $0.0004 on GPT-6 Luna.
Which scores higher, Claude Haiku 5.5 vs GPT-6 Luna?
Claude Haiku 5.5 scores higher on Epoch Capabilities Index: 160.4 against 156.8 for GPT-6 Luna. That index is an independent composite from Epoch AI. Lab-reported scores are kept off this comparison. Context windows are 1M and 1.05M. Prices are US dollars per million tokens at current public rates.
What is the verdict for Claude Haiku 5.5 vs GPT-6 Luna?
Claude Haiku 5.5 scores higher on Epoch Capabilities Index (160.4 vs 156.8). A public token price is missing for at least one model, so this page does not call a cheaper winner. Context is 1M for Claude Haiku 5.5 and 1.05M for GPT-6 Luna. Use the model pages for every score on file, including lab-reported numbers.
Open this pair in the comparison view
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.