Model decision surface
Compare AI models
Start with Llama 3.3 70B Instruct and gpt-oss-20b, 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
Llama 3.3 70B Instruct vs gpt-oss-20b
Live dataset updated 9/15/2026, 9:19:37 PM UTC
Open 1200×630 evidence receipt| Field | gpt-oss-20b OpenAI | |
|---|---|---|
| ModelCap position | #166 | #161 |
| Index score | 24.2 | 28.0 |
| Evidence | Measured2 public benchmark observations across 2 boards | Measured3 public benchmark observations across 3 boards |
| Input / 1M | $0.10 | $0.03 |
| Output / 1M | $0.32 | $0.13 |
| Pricing status | fresh | fresh |
| Context | 131K | 131K |
| Providers | 10 | 13 |
| Weight access | Gated access | Open weights |
Decision facts
- Llama 3.3 70B Instruct is #166; gpt-oss-20b is #161 on the same current language board.
- Index scores are 24.2 for Llama 3.3 70B Instruct and 28.0 for gpt-oss-20b. 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 $0.32 for Llama 3.3 70B Instruct and $0.13 for gpt-oss-20b. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $0.36 for Llama 3.3 70B Instruct versus $0.13 for gpt-oss-20b. gpt-oss-20b costs 65.3% 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 131,072 tokens for Llama 3.3 70B Instruct and 131,072 for gpt-oss-20b.
- Weight access differs: Llama 3.3 70B Instruct is gated; gpt-oss-20b is open.
- ModelCap currently lists 10 providers for Llama 3.3 70B Instruct and 13 for gpt-oss-20b.
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 Fable 5.1 vs Claude Opus 5#1 vs #2 on the ModelCap Index
- Claude Fable 5.1 vs GPT-6 Astra#1 vs #3 on the ModelCap Index
- Claude Opus 5 vs GPT-6 Astra#2 vs #3 on the ModelCap Index
- Claude Fable 5.1 vs Muse Spark 1.3#1 vs #4 on the ModelCap Index
- Claude Opus 5 vs Muse Spark 1.3#2 vs #4 on the ModelCap Index
- Muse Spark 1.3 vs GPT-6 Astra#4 vs #3 on the ModelCap Index
- Claude Fable 5.1 vs Qwen3.8 Max (0902)#1 vs #5 on the ModelCap Index
- Claude Opus 5 vs Qwen3.8 Max (0902)#2 vs #5 on the ModelCap Index
- GPT-6 Astra vs Qwen3.8 Max (0902)#3 vs #5 on the ModelCap Index
- Muse Spark 1.3 vs Qwen3.8 Max (0902)#4 vs #5 on the ModelCap Index
- Claude Fable 5.1 vs Gemini 3.8 Flash#1 vs #6 on the ModelCap Index
- Claude Opus 5 vs Gemini 3.8 Flash#2 vs #6 on the ModelCap Index
- Gemini 3.8 Flash vs GPT-6 Astra#6 vs #3 on the ModelCap Index
- Gemini 3.8 Flash vs Muse Spark 1.3#6 vs #4 on the ModelCap Index
- Gemini 3.8 Flash vs Qwen3.8 Max (0902)#6 vs #5 on the ModelCap Index
- Claude Fable 5.1 vs GPT-5.6 Sol#1 vs #7 on the ModelCap Index
- Claude Opus 5 vs GPT-5.6 Sol#2 vs #7 on the ModelCap Index
- GPT-5.6 Sol vs GPT-6 Astra#7 vs #3 on the ModelCap Index
- Muse Spark 1.3 vs GPT-5.6 Sol#4 vs #7 on the ModelCap Index
- GPT-5.6 Sol vs Qwen3.8 Max (0902)#7 vs #5 on the ModelCap Index
- Gemini 3.8 Flash vs GPT-5.6 Sol#6 vs #7 on the ModelCap Index
- Claude Fable 5.1 vs Kimi K3#1 vs #8 on the ModelCap Index
- Claude Opus 5 vs Kimi K3#2 vs #8 on the ModelCap Index
- Kimi K3 vs GPT-6 Astra#8 vs #3 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.