Model decision surface
Compare AI models
Start with GPT-6 Luna and Hy4 preview, or choose any two current ranked language models. Compare capability evidence, price, context, provider availability, and weight access without pretending one field decides every use case.
Current public data
GPT-6 Luna vs Hy4 preview
Live dataset updated 9/22/2026, 10:37:09 PM UTC
Open 1200×630 evidence receipt| Field | GPT-6 Luna OpenAI | Hy4 preview Tencent |
|---|---|---|
| ModelCap position | #25 | #28 |
| Index score | 78.6 | 76.4 |
| Evidence | Measured3 public benchmark observations across 3 boards | Measured9 reported rows against measured corpus ladders (46%); publisher-corpus-prior over 209 held-out anchors (10%); opens above measured predecessor tencent/hy3 on same-family ordering evidence (36%); 1 specialist-board observation at 2.5% support (8%); shrunk 1 toward the measured corpus |
| Input / 1M | $0.10 | $0.834 |
| Output / 1M | $0.50 | $2.50 |
| Pricing status | fresh | fresh |
| Context | 1M | 1M |
| Providers | 2 | 1 |
| Weight access | API only | Open weights |
Decision facts
- GPT-6 Luna is #25; Hy4 preview is #28 on the same current language board.
- Index scores are 78.6 for GPT-6 Luna and 76.4 for Hy4 preview. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.
- Both positions use Measured evidence.
- Listed output price per 1M tokens is $0.50 for GPT-6 Luna and $2.50 for Hy4 preview. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $0.45 for GPT-6 Luna versus $2.92 for Hy4 preview. GPT-6 Luna costs 84.6% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.
- Published context is 1,050,000 tokens for GPT-6 Luna and 1,048,576 for Hy4 preview.
- Weight access differs: GPT-6 Luna is none; Hy4 preview is open.
- ModelCap currently lists 2 providers for GPT-6 Luna and 1 for Hy4 preview.
These are separate published fields, not a synthetic winner. ModelCap does not collapse price, access, context, and capability evidence into a hidden recommendation score.
Popular comparisons
- Claude Opus 5.5 vs GPT-6 Sol#1 vs #2 on the ModelCap Index
- Claude Fable 5.1 vs Claude Opus 5.5#3 vs #1 on the ModelCap Index
- Claude Fable 5.1 vs GPT-6 Sol#3 vs #2 on the ModelCap Index
- Claude Opus 5.5 vs Grok 4.7#1 vs #4 on the ModelCap Index
- GPT-6 Sol vs Grok 4.7#2 vs #4 on the ModelCap Index
- Claude Fable 5.1 vs Grok 4.7#3 vs #4 on the ModelCap Index
- Claude Opus 5.5 vs MiMo-V2.6-Pro#1 vs #5 on the ModelCap Index
- GPT-6 Sol vs MiMo-V2.6-Pro#2 vs #5 on the ModelCap Index
- Claude Fable 5.1 vs MiMo-V2.6-Pro#3 vs #5 on the ModelCap Index
- Grok 4.7 vs MiMo-V2.6-Pro#4 vs #5 on the ModelCap Index
- Claude Opus 5.5 vs Qwen3.8 Max (0902)#1 vs #6 on the ModelCap Index
- GPT-6 Sol vs Qwen3.8 Max (0902)#2 vs #6 on the ModelCap Index
- Claude Fable 5.1 vs Qwen3.8 Max (0902)#3 vs #6 on the ModelCap Index
- Qwen3.8 Max (0902) vs Grok 4.7#6 vs #4 on the ModelCap Index
- Qwen3.8 Max (0902) vs MiMo-V2.6-Pro#6 vs #5 on the ModelCap Index
- Claude Opus 5.5 vs GPT-6 Astra#1 vs #7 on the ModelCap Index
- GPT-6 Astra vs GPT-6 Sol#7 vs #2 on the ModelCap Index
- Claude Fable 5.1 vs GPT-6 Astra#3 vs #7 on the ModelCap Index
- GPT-6 Astra vs Grok 4.7#7 vs #4 on the ModelCap Index
- GPT-6 Astra vs MiMo-V2.6-Pro#7 vs #5 on the ModelCap Index
- GPT-6 Astra vs Qwen3.8 Max (0902)#7 vs #6 on the ModelCap Index
- Claude Opus 5.5 vs Muse Spark 1.3#1 vs #8 on the ModelCap Index
- Muse Spark 1.3 vs GPT-6 Sol#8 vs #2 on the ModelCap Index
- Claude Fable 5.1 vs Muse Spark 1.3#3 vs #8 on the ModelCap Index
Each comparison page is a permanent, shareable URL with the same live figures as this tool: ModelCap Index position, API pricing, context window, provider count, weight access and every shared benchmark board.