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 Opus 5.5vsGemma 4 31B IT
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 Opus 5.5AnthropicNEW Claude model for long-running agentic coding and knowledge work | Gemma 4 31B ITGoogle· open weights Largest Gemma 4 instruction model for open, self-hosted chat and reasoning | |
|---|---|---|
| Intelligence | ||
| Intelligence index | 57.6 | No score yet |
| Price | ||
| Input, $ per 1M | $4 | $0.14 |
| Output, $ per 1M | $20 | $0.40 |
| Typical message (500 in / 250 out) | $0.0070 | $0.00017 |
| Repeated input, cached | $0.20 · 20× cheaper | No discount |
| Prompts over 200K tokens | Same price | Same price |
| Limits | ||
| Context window | 1M | 262K |
| Longest answer | 128K tokens | 131K tokens |
| Knowledge cutoff | Jun 2026 | Not published |
| What it can take and do | ||
| Accepts | TextImagePDF | TextImagePDF |
| Reasoning effort | Low · Med · High · X-high · Max | Fixed |
| Tool use | Yes | Yes |
| Guaranteed JSON output | Yes | Yes |
| Availability | ||
| Released | 22 Sept 2026 | 2 Apr 2026 |
| Open weights | No | Yes, can self-host |
| API providers offering it | 35 | 40 |