token.app › Compare › GPT-5.6 Luna vs Claude Opus 5
GPT-5.6 Luna vs Claude Opus 5
Claude Opus 5 leads on 5 of 5 shared benchmarks. GPT-5.6 Luna is 44× cheaper per token on a blended 3:1 basis. GPT-5.6 Luna accepts the larger context window (1.1M).
Head to head
Blended price uses a 3:1 input:output mix
| GPT-5.6 Luna | Claude Opus 5 | |
|---|---|---|
| Provider | OpenAI | Anthropic |
| Input $/1M | $0.100 | $5.00 |
| Output $/1M | $0.600 | $25.00 |
| Blended $/1M | $0.225 | $10.00 |
| Context window | 1.1M | 1M |
| Max output | 128K | 128K |
| Released | Jul 2026 | Jul 2026 |
| Licence | Proprietary | Proprietary |
| GPQA Diamond | 91.6% | 93.9% |
| FrontierMath T1–3 | 82.1% | 85.6% |
| FrontierMath T4 | 61.0% | 73.2% |
| SimpleQA Verified | 41.7% | 56.7% |
| OTIS Mock AIME | 98.3% | 98.9% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose GPT-5.6 Luna if…
- Costs less per token — $0.225 vs $10.00 blended
- Larger context window (1.1M)
Choose Claude Opus 5 if…
- Higher GPQA Diamond (93.9% vs 91.6%)
- Higher FrontierMath T1–3 (85.6% vs 82.1%)
- Higher FrontierMath T4 (73.2% vs 61.0%)
- Higher SimpleQA Verified (56.7% vs 41.7%)
- Newer model (released Jul 2026)
FAQ
Which is better, GPT-5.6 Luna or Claude Opus 5?
Across the 5 benchmarks both models have independently-run scores for, GPT-5.6 Luna leads on 0 and Claude Opus 5 leads on 5. Benchmarks are one input — price and context window are on this page too.
Is GPT-5.6 Luna cheaper than Claude Opus 5?
GPT-5.6 Luna is cheaper: $0.225 versus $10.00 per million tokens blended at 3:1 input:output. Input alone: $0.100 vs $5.00. Output alone: $0.600 vs $25.00.
What context windows do GPT-5.6 Luna and Claude Opus 5 have?
GPT-5.6 Luna: 1,050,000 tokens. Claude Opus 5: 1,000,000 tokens.
Who makes GPT-5.6 Luna and Claude Opus 5?
GPT-5.6 Luna is made by OpenAI. Claude Opus 5 is made by Anthropic.