xAI
availableShows if the model has enough results for an index.Grok 4 Fast (Reasoning)
Grok 4 Fast (Reasoning) is a reasoning model from xAI in the Grok 4 Fast family. 21 benchmarks count toward its score, in 7 categories.
IndexOverall score. 50 is the middle.45.9 ±4.0
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.N/A
Output / 1MUS dollars per 1M output tokens.N/A
ContextMaximum tokens in one request.2M
EloLMArena rating and rank.1399 (#143)
50 is the middle of the board. The range shows the doubt in the index.
17,975 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
21 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| AIME | Math | 91.3% | 56.3 | — | 16 Apr 2026 | Vals AI |
| MGSM | Multilingual | 90.9% | — | — | 9 Jan 2026 | Vals AI |
| GPQA Diamond | Knowledge | 85.4% | 57.0 | — | 1 Sept 2026 | Vals AI |
| Artificial Analysis GPQA Diamond | Knowledge | 84.7% | 55.4 | — | — | Artificial Analysis |
| MMLU Pro | Knowledge | 79.7% | 46.1 | — | 1 Sept 2026 | Vals AI |
| LiveCodeBench | Coding | 79.0% | 56.1 | — | 1 Sept 2026 | Vals AI |
| Artificial Analysis Long Context Reasoning | Reasoning | 73.7% | 59.2 | — | — | Artificial Analysis |
| MMMU Pro | Multimodal | 72.8% | 45.8 | — | 1 Sept 2026 | Vals AI |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 65.8% | 46.0 | — | — | Victor Barres et al. |
| Artificial Analysis MMMU-Pro | Multimodal | 61.8% | 42.6 | — | — | Artificial Analysis |
| Artificial Analysis IFBench | Instruction | 50.5% | 40.4 | — | — | Artificial Analysis |
| ARC-AGI-1 (semi-private) | Reasoning | 48.5% | 50.1 | — | — | ARC Prize Foundation |
| SWE-bench | Coding | 45.4% | 33.9 | — | 1 Sept 2026 | Vals AI |
| Terminal-Bench 2.0 | Agentic | 29.2% | 43.5 | — | 4 Jun 2026 | Vals AI |
| Terminal-Bench 1.0 | Agentic | 27.5% | 34.9 | — | 12 Jan 2026 | Vals AI |
| Artificial Analysis Omniscience Accuracy | Knowledge | 22.8% | 42.1 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 19.1% | 45.3 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 17.9% | 44.8 | — | — | Artificial Analysis |
| IOI v1 | Coding | 11.5% | 46.5 | — | 9 Aug 2026 | Vals AI |
| ARC-AGI-2 (semi-private) | Reasoning | 5.3% | 42.4 | — | — | ARC Prize Foundation |
| Critical Physics Tasks | Reasoning | 2.9% | 44.5 | — | — | Artificial Analysis |
| Vibe Code Bench v1.1 | Coding | 0.0% | 42.2 | OpenHands | 21 Sept 2026 | Vals AI |
21 benchmarks count, from 21 of 22 results. A grey row does not count. Too few models took that benchmark.