Claude Haiku 5.5vsClaude Opus 5.5vsMiMo V2.6 Pro
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 | Claude Opus 5.5AnthropicNEW Claude model for long-running agentic coding and knowledge work | MiMo V2.6 ProXiaomi· open weightsNEW Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution | |
|---|---|---|---|
| Intelligence | |||
| Intelligence index | 43.4 | 57.6 | 46.3 |
| Price | |||
| Input, $ per 1M | $0.10 | $4 | $0.43 |
| Output, $ per 1M | $0.50 | $20 | $0.87 |
| Typical message (500 in / 250 out) | $0.00017 | $0.0070 | $0.00044 |
| Repeated input, cached | $0.01 · 10× cheaper | $0.20 · 20× cheaper | $0.0036 · 121× cheaper |
| Prompts over 200K tokens | Same price | Same price | Same price |
| Limits | |||
| Context window | 1M | 1M | 1.05M |
| Longest answer | 128K tokens | 128K tokens | 131K tokens |
| Knowledge cutoff | Jun 2026 | Jun 2026 | Not published |
| What it can take and do | |||
| Accepts | TextImagePDF | TextImagePDF | TextImage |
| Reasoning effort | Low · Med · High · X-high · Max | Low · Med · High · X-high · Max | Off · Minimal · Low · Med · High |
| Tool use | Yes | Yes | Yes |
| Guaranteed JSON output | Yes | Yes | Not listed |
| Availability | |||
| Released | 7 Oct 2026 | 22 Sept 2026 | 22 Sept 2026 |
| Open weights | No | No | Yes, can self-host |
| API providers offering it | 33 | 36 | 24 |