Pick models to compare
Click a model to add it, then ask your question below.
Intelligence: the Artificial Analysis Intelligence Index at each model's highest effort. Models without a score yet sit in the lane under the chart, placed by price. Lines at $2 blended and the median score (39.5).
DeepSeek V4 ProvsGPT OSS 120B
Send one prompt to every model and read the answers side by side, with speed and cost for each.
Shareable link:
Before you run
Highlighted values are the best among your picks.
DeepSeek V4 ProDeepSeek· open weights DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes | GPT OSS 120BOpen AI· open weights Open GPT reasoning model for self-hosted agents and controllable deployments | |
|---|---|---|
| Intelligence | ||
| Intelligence index | 36 | 11.6 |
| Price | ||
| Input, $ per 1M | $0.66 | $0.10 |
| Output, $ per 1M | $1.98 | $0.50 |
| Typical message (500 in / 250 out) | $0.00082 | $0.00017 |
| Repeated input, cached | $0.02 · 30× cheaper | $0.10 |
| Prompts over 200K tokens | Same price | Same price |
| Limits | ||
| Context window | 1M | 131K |
| Longest answer | 393K tokens | 131K tokens |
| Knowledge cutoff | Not published | Not published |
| What it can take and do | ||
| Accepts | Text | Text |
| Reasoning effort | Low · High · Max | Low · Med · High |
| Tool use | Yes | Yes |
| Guaranteed JSON output | Yes | Yes |
| Availability | ||
| Released | 12 Aug 2026 | 5 Aug 2025 |
| Open weights | Yes, can self-host | Yes, can self-host |
| API providers offering it | 43 | 44 |