# Do coding agents recommend Grok Voice Think Fast 2.0? > Grok Voice Think Fast 2.0 was chosen in 3% of 531 judged voice agents sessions, ranking eighth. Source: https://armature.tech/library/do-coding-agents-recommend-grok-voice-think-fast-2-0 Published: 2026-09-23 Publisher: Armature, Inc. (https://armature.tech) --- > Grok Voice Think Fast 2.0 was chosen in 3% of 531 judged voice agents sessions, ranking eighth. It was also raised as a candidate in 9 further sessions without being chosen. This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in voice agents inside a realistic codebase. Not what a chat assistant says about Grok Voice Think Fast 2.0. What an agent actually installed. ## The numbers | | | | --- | --- | | Category | Voice agents | | Sessions in the category | 531 | | Sessions where Grok Voice Think Fast 2.0 was chosen | 14 | | Install share | 3% | | Rank in category | 8 of 29 | | Codebases it won in | 5 | | Raised as a candidate, not chosen | 9 | | Chosen when considered | 61% | | Site | x.ai | ## By agent With 14 wins spread across 5 agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established. | Agent | Sessions | Chose Grok Voice Think Fast 2.0 | Share | | --- | --- | --- | --- | | Claude Code | 139 | 0 | 0% | | Codex | 155 | 0 | 0% | | Cursor | 149 | 3 | 2% | | Grok Build CLI | 43 | 11 | 26% | | Muse Code | 45 | 0 | 0% | ## By who was asking Grok Voice Think Fast 2.0 performs similarly across the four kinds of buyer, from 0% to 6%. That is unusual: the category leader changed with the persona in 23 of the 29 categories we measured. | Who is asking | Sessions | Chose Grok Voice Think Fast 2.0 | Share | | --- | --- | --- | --- | | Vibe coder | 107 | 0 | 0% | | Junior developer | 72 | 4 | 6% | | Senior engineer | 221 | 4 | 2% | | Enterprise team | 131 | 6 | 5% | ## What Grok Voice Think Fast 2.0 was up against The full ranking in voice agents, from the same sessions: | # | Product | Runs won | Share | | --- | --- | --- | --- | | 1 | Retell AI | 111 | 21% | | 2 | Vapi | 104 | 20% | | 3 | LiveKit Agents | 74 | 14% | | 4 | ElevenLabs Agents | 49 | 9% | | 5 | Twilio ConversationRelay | 48 | 9% | | 6 | OpenAI Realtime API | 41 | 8% | | 7 | Built in-house (no product adopted) | 27 | 5% | | 8 | Azure Voice Live API | 17 | 3% | ## What this means Agents almost never raise Grok Voice Think Fast 2.0 without choosing it: 9 sessions raised against 14 chosen. When it gets considered, it usually wins. The constraint is how rarely it gets considered at all, which is a presence problem: templates, framework integrations and pages that answer the configuration and production questions agents actually search for. ## Where these numbers come from The 531 sessions in voice agents are part of a published set of 11,878, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: [how we measured this](/library/how-we-measured-this). Every voice agents run can be replayed on [the board](/leaderboards/voice-agents). If you work on Grok Voice Think Fast 2.0: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts. ## Common questions ### Do coding agents recommend Grok Voice Think Fast 2.0? Yes. Grok Voice Think Fast 2.0 was chosen in 14 of the 531 judged sessions in voice agents, a 3% install share, ranking eighth in its category. ### Does Claude Code recommend Grok Voice Think Fast 2.0? In 0 of the 139 sessions in voice agents run with Claude Code, which is 0%. ### Do different coding agents treat Grok Voice Think Fast 2.0 differently? Yes, and by a wide margin. Grok Build CLI chose it in 26% of its runs and Claude Code in 0%. ### How was this measured? Real coding agents at pinned versions were run in sandboxes inside 91 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind. ### How often is Grok Voice Think Fast 2.0 considered but not chosen? It was raised as a candidate in 9 sessions without being chosen, and chosen in 14. That is a 61% conversion from considered to chosen. ## Read next - [How to get picked for voice agents by coding agents](https://armature.tech/library/voice-agents-coding-agents-playbook) (Markdown: https://armature.tech/library/voice-agents-coding-agents-playbook.md) - [Do coding agents recommend Retell AI?](https://armature.tech/library/do-coding-agents-recommend-retell-ai) (Markdown: https://armature.tech/library/do-coding-agents-recommend-retell-ai.md) - [Do coding agents recommend Vapi?](https://armature.tech/library/do-coding-agents-recommend-vapi) (Markdown: https://armature.tech/library/do-coding-agents-recommend-vapi.md) - [Do Claude Code, Codex and Cursor pick the same tools?](https://armature.tech/library/do-claude-code-and-codex-agree) (Markdown: https://armature.tech/library/do-claude-code-and-codex-agree.md) --- Armature helps software products get discovered and used by coding agents. Service: https://armature.tech/discoverability · Results: https://armature.tech/leaderboards/sectors · Contact: contact@armature.tech