Side-by-side comparison · models
Grok 4.1 Fast vs Grok 4.20
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Models
Grok 4.1 Fast
Fast Grok model for responsive chat, reasoning, and tool-assisted work.
Models
Grok 4.20
Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities.
Checked facts
Line by line
| Measure | Grok 4.1 Fast | Grok 4.20 |
|---|---|---|
| Input price | Not checked yet | $1.25 per million tokens |
| Output price | Not checked yet | $2.50 per million tokens |
| Price on xai | Not checked yet | $0.200 per million cached input tokens |
| Price on xai | Not checked yet | $1.25 per million input tokens |
| Price on xai | Not checked yet | $2.50 per million output tokens |
| Latest version | Not checked yet | x-ai/grok-4.20-20260309 |
| Time to first token (ms) on xai | Not checked yet | 577 |
| Output speed (tokens a second) on xai | Not checked yet | 68 |
| Tokens served on OpenRouter in a day | Not checked yet | 3B (for 7 Nov 2026) |
| Tool calls on OpenRouter in a day | Not checked yet | 43.5K (for 7 Nov 2026) |
| Dtbench | 87.7% (for 19 Nov 2025) | 90.1% (for 17 Feb 2026) |
| Proofbench | 4% (for 19 Nov 2025) | 14% (for 17 Feb 2026) |
| Simplebench | 56% (for 19 Nov 2025) | Not checked yet |
| Artificial Analysis Intelligence Index | Not checked yet | 25.7 |
| Design Arena rating (Elo) | Not checked yet | 1,228 |
| Gpqa diamond | Not checked yet | 89.3% (for 17 Feb 2026) |
| Frontiermath tiers 1 3 v2 private | Not checked yet | 44.9% (for 17 Feb 2026) |
| Terminal bench | Not checked yet | 57.3% (for 17 Feb 2026) |
| Simpleqa verified | Not checked yet | 30.2% (for 17 Feb 2026) |
| Arc agi 2 | Not checked yet | 65.1% (for 17 Feb 2026) |
| Arc agi | Not checked yet | 89.5% (for 17 Feb 2026) |
| Chess puzzles | Not checked yet | 29% (for 17 Feb 2026) |
| Cl bench | Not checked yet | 22.2% (for 17 Feb 2026) |
| Cl bench life | Not checked yet | 11.9% (for 17 Feb 2026) |
| Frontiermath tier 4 v2 private | Not checked yet | 17.1% (for 17 Feb 2026) |
| Lmca | Not checked yet | 38.7% (for 17 Feb 2026) |
| Weirdml | Not checked yet | 52.3% (for 17 Feb 2026) |
| Otis mock aime 2024 2025 | Not checked yet | 92.2% (saturated benchmark: the top models all score near the ceiling) (for 17 Feb 2026) |
A line appears only when at least one record has a value we confirmed from a source. Values we have not confirmed are left out, never guessed. Records of different types share fewer lines.
Add a third
Compare with one more record
How this works
Share it, or build your own
This page works for any two or three records in the directory, of any type. The link stays the same whichever order you name them in, so you can share it as it is. Change the records in the address, for example /directories/vs/claude-code-vs-cursor, or start from our editorial comparisons.