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).
Claude Haiku 5.5vsNemotron 3 Ultra
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.
Claude Haiku 5.5AnthropicNEW Fast Claude model for responsive assistance, classification, and lightweight agents | Nemotron 3 UltraNVIDIA· open weights Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy | |
|---|---|---|
| Intelligence | ||
| Intelligence index | 43.4 | 22.9 |
| Price | ||
| Input, $ per 1M | $0.10 | $0.60 |
| Output, $ per 1M | $0.50 | $2.40 |
| Typical message (500 in / 250 out) | $0.00017 | $0.00090 |
| Repeated input, cached | $0.01 · 10× cheaper | $0.12 · 5× cheaper |
| Prompts over 200K tokens | Same price | Same price |
| Limits | ||
| Context window | 1M | 1M |
| Longest answer | 128K tokens | 65K tokens |
| Knowledge cutoff | Jun 2026 | Not published |
| What it can take and do | ||
| Accepts | TextImagePDF | Text |
| Reasoning effort | Low · Med · High · X-high · Max | Off · Low · Med · High |
| Tool use | Yes | Yes |
| Guaranteed JSON output | Yes | Not listed |
| Availability | ||
| Released | 7 Oct 2026 | 4 Jun 2026 |
| Open weights | No | Yes, can self-host |
| API providers offering it | 32 | 23 |