Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | AnthropicClaude Haiku 5.5Remove × | elorianElorian: GlimpseRemove × |
|---|---|---|
| What’s different | 1M context · Reasoning · Image input | Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than... |
| Date | Oct 7, 2026Released | Oct 17, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | See provider quotes | $0.60 in / $3.00 out/ 1M tokensTogether · via OpenRouter · all routes ↗together |
| Provider endpoints | 0 endpoints → | 2 endpoints → |
Benchmarks Each result retains its evaluation configuration | ||
| AA Intelligence ↗4.3.2 | 43.4 ↗Effort: max · MaxIndependent result | Not reported |
| AA-Briefcase ↗1.1 | 1,576.55 ↗Effort: max · MaxIndependent result | Not reported |
| GDPval-AA ↗2.1 | 1,617.13 ↗Effort: max · MaxIndependent result | Not reported |
| AutomationBench-AA ↗AA Index 4.3.2 collection | 35.41% ↗Effort: max · MaxIndependent result | Not reported |
| Terminal-Bench 4.0 · AA ↗ | 32.83% ↗Effort: max · MaxHarness unreportedIndependent result | Not reported |
| SciCode ↗AA Index 4.3.2 collection | 54.98% ↗AA · Under reviewEffort: max · MaxIndependent result | Not reported |
| Humanity’s Last Exam ↗AA Index 4.3.2 collection | 44.39% ↗Effort: max · MaxIndependent result | Not reported |
| GDP.pdf ↗AA Index 4.3.2 collection | 20.8% ↗Effort: max · MaxIndependent result | Not reported |
| CritPt ↗AA Index 4.3.2 collection | 18.86% ↗AA · Under reviewEffort: max · MaxIndependent result | Not reported |
| AA-Omniscience ↗AA Index 4.3.2 collection | 10.67 ↗Effort: max · MaxIndependent result | Not reported |
| AA-LCR ↗1.1 | 82.67% ↗Effort: max · MaxIndependent result | Not reported |
Specifications | ||
| Context window | 1M | 262.1K |
| Max output | — | 256K |
| Parameters | — | — |
| Tool calling | Not reported | Supported |
| Structured output | Not reported | Supported |
| Image input | Supported | Supported |
| Video input | Not reported | Supported |
| Reasoning | Supported | Supported |
| Prompt caching | Not reported | Supported |