xAI · model passport
Grok 4 Fast Reasoning
grok-4-fast-reasoning- Cloud only
- Proprietary licence
- Released 2026-10-13(first seen on LMArena)
- Overall · LMArena
- 1,405#142 of 396
- Best percentile
- 64.4Overall
- Cohort standing
- 43.2median 60.8
What the data says
Benchmarked on 7 of 27 tracked axes. Every figure below is the model's own published result on that board.
Weakest axes
- 2.2 pct — WebDev Arena (1,159)
- 5.7 pct — HHEM Hallucination (Vectara) (79.8%)
Uneven: 62.2 percentile points between its best and worst axis — 64.4 pct on Overall versus 2.2 pct on WebDev Arena.
- Overall64.4 pct1,405Verify →
- Instruction following62.9 pct1,389Verify →
- Coding60.6 pct1,439Verify →
- Hard prompts60.4 pct1,414Verify →
- Factuality Arena26.2 pct1,417Verify →
- HHEM Hallucination (Vectara)5.7 pct79.8%Verify →
- WebDev Arena2.2 pct1,159Verify →
- Vision ArenaNot benchmarked
- Search ArenaNot benchmarked
- Document ArenaNot benchmarked
- Agent ArenaNot benchmarked
- GPQA DiamondNot benchmarked
- AIME (math)Not benchmarked
- FrontierMathNot benchmarked
- SimpleQA VerifiedNot benchmarked
- ARC-AGI-2Not benchmarked
- Humanity's Last ExamNot benchmarked
- SimpleBenchNot benchmarked
- LiveBenchNot benchmarked
- BFCL v4 (function calling)Not benchmarked
- SWE-bench Verified (live board)Not benchmarked
- Terminal-Bench 4.0Not benchmarked
- MMLU-Pro (Artificial Analysis)Not benchmarked
- LiveCodeBench (Artificial Analysis)Not benchmarked
- IFBench (Artificial Analysis)Not benchmarked
- SWE-bench VerifiedNot benchmarked
- Terminal-BenchNot benchmarked
Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.
grok-4-fast-reasoning stands at 43.2 (raw mean 40.3) — measured on 7 of 27 axes.
grok-4-fast-reasoning stands at 43.2 versus a cohort median of 60.8 across 168 models released within 180 days — below the peer median.
grok-4-fast-reasoning scores at percentile 2.2 on WebDev Arena.
grok-4-fast-reasoning scores at percentile 5.7 on HHEM Hallucination (Vectara).
grok-4-fast-reasoning ranks between #157 and #936 across 6 built-in weightings — best under "Agentic", worst under "All sources".
Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →