xAI
availableShows if the model has enough results for an index.Grok 4.1 Fast (Reasoning)
Grok 4.1 Fast (Reasoning) is a reasoning model from xAI in the Grok 4.1 Fast family. 20 benchmarks count toward its score, in 8 categories.
IndexOverall score. 50 is the middle.49.0 ±3.6
CoverageShare of the index weight with results.100%
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.1408 (#132)
50 is the middle of the board. The range shows the doubt in the index.
55,363 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
20 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. |
|---|---|---|---|---|---|---|
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 93.3% | 65.8 | — | — | Victor Barres et al. |
| AIME | Math | 91.9% | 56.6 | — | 16 Apr 2026 | Vals AI |
| MGSM | Multilingual | 89.5% | — | — | 9 Jan 2026 | Vals AI |
| Artificial Analysis GPQA Diamond | Knowledge | 85.3% | 56.0 | — | — | Artificial Analysis |
| GPQA Diamond | Knowledge | 84.3% | 56.1 | — | 1 Sept 2026 | Vals AI |
| MMLU Pro | Knowledge | 84.2% | 53.2 | — | 1 Sept 2026 | Vals AI |
| LiveCodeBench | Coding | 80.6% | 57.6 | — | 1 Sept 2026 | Vals AI |
| Artificial Analysis Long Context Reasoning | Reasoning | 74.0% | 59.4 | — | — | Artificial Analysis |
| MMMU Pro | Multimodal | 72.7% | 45.6 | — | 1 Sept 2026 | Vals AI |
| EuroEval Swedish | Multilingual | 68.3% | 87.5 | — | — | EuroEval |
| EuroEval Italian | Multilingual | 66.1% | 84.8 | — | — | EuroEval |
| EuroEval French | Multilingual | 65.4% | 83.9 | — | — | EuroEval |
| EuroEval Portuguese | Multilingual | 64.8% | 83.2 | — | — | EuroEval |
| EuroEval Dutch | Multilingual | 63.8% | 82.0 | — | — | EuroEval |
| Artificial Analysis MMMU-Pro | Multimodal | 63.3% | 44.5 | — | — | Artificial Analysis |
| EuroEval Spanish | Multilingual | 59.8% | 77.0 | — | — | EuroEval |
| EuroEval Polish | Multilingual | 57.6% | 74.3 | — | — | EuroEval |
| EuroEval German | Multilingual | 54.8% | 70.7 | — | — | EuroEval |
| Artificial Analysis IFBench | Instruction | 52.7% | 42.6 | — | — | Artificial Analysis |
| SWE-bench | Coding | 41.4% | 30.7 | — | 1 Sept 2026 | Vals AI |
| Terminal-Bench 1.0 | Agentic | 28.8% | 35.9 | — | 12 Jan 2026 | Vals AI |
| Artificial Analysis Omniscience Accuracy | Knowledge | 25.1% | 44.9 | — | — | Artificial Analysis |
| Terminal-Bench 2.0 | Agentic | 24.7% | 40.3 | — | 4 Jun 2026 | Vals AI |
| Artificial Analysis Intelligence Index | Knowledge | 20.4% | 47.9 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 19.3% | 45.5 | — | — | Artificial Analysis |
| IOI v1 | Coding | 3.1% | 41.7 | — | 9 Aug 2026 | Vals AI |
| Critical Physics Tasks | Reasoning | 2.9% | 44.5 | — | — | Artificial Analysis |
| Vibe Code Bench v1.1 | Coding | 1.2% | 42.7 | OpenHands | 21 Sept 2026 | Vals AI |
20 benchmarks count, from 27 of 28 results. A grey row does not count. Too few models took that benchmark.