All comparisons
Aider Polyglot 53.3 — Chatbot Arena 1405.0 1398.0 Massive Multi-discipline Multimodal Understanding 78.0 — MMLU PRO 79.9 86.2 HumanEval — 93.1 SWE-bench Verified — 63.2 LiveCodeBench — 70.4 Google-Proof Q&A — 86.4
Grok-3 vs Gemini 2.5 Pro
Side-by-side comparison of specifications, capabilities, and pricing.
| Released | 2026-01-15 | 2025-06-17 |
| Context window | 1M | 1M |
| Parameters | 1B | — |
| Architecture | — | decoder only |
| License | Proprietary | Proprietary |
| Knowledge cutoff | 2025-04 | 2025-01 |
Capabilities | ||
| Vision | ||
| Multimodal | ||
| Reasoning | ||
| Function calling | ||
| Tool use | ||
| Structured Outputs | ||
| Code execution | ||
Availability | ||
| Providers | ||
Benchmarks