xAI · proprietary

Grok-3

Grok-3 by xAI appears in 1 source with Reasoning at 39.69. Best read for LLM, Low cost, Math.

CreatorxAI

Release date2025-02-17

Knowledge cutoffNot published

Context128K tokens

Input price$3/M tokens

Output price$15/M tokens

Modalitytext + vision

CountryUS

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank37ranking · source_rank

Reasoning39.69reasoning · index_reasoning

Math38.88math · index_math

Coding26.11coding · index_code

Vision20.84multimodal · index_vision

Healthcare31.34domain · index_healthcare

GPQA84.6 %reasoning · gpqa_score

AIME 202593.3 %math · aime_2025_score

Code Arena1,111.37 %coding · coding_arena_score

MMMU78 %multimodal · mmmu_score

Context128,000 tokenscontext · context

Speed265.26 c/sperformance · throughput

Latency19,601 msperformance · latency

Input price3 $/Mpricing · input_price

Output price15 $/Mpricing · output_price

Evidence

Citations and source overlap

LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is Grok-3 verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.