xAI
availableShows if the model has enough results for an index.Grok 4
Grok 4 is a non-reasoning model from xAI. 25 benchmarks count toward its score, in 7 categories.
IndexOverall score out of 100.51.6 ±3.7
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.54/s
Input / 1MUS dollars per 1M input tokens.N/A
Output / 1MUS dollars per 1M output tokens.N/A
ContextMaximum tokens in one request.128K
EloLMArena rating and rank.1412 (#128)
The index is a score out of 100. The ± range shows how much it can change.
39,297 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category, out of 100.
Out of 100Results
25 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result as a score out of 100. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| MATH 500 | Math | 96.2% | 49.3 | — | 9 Jan 2026 | Vals AI |
| MATH 500 | Math | 96.2% | 49.3 | — | 9 Jan 2026 | Vals AI |
| MGSM | Multilingual | 90.9% | — | — | 9 Jan 2026 | Vals AI |
| MGSM | Multilingual | 90.9% | — | — | 9 Jan 2026 | Vals AI |
| AIME | Math | 90.6% | 55.9 | — | 16 Apr 2026 | Vals AI |
| AIME | Math | 90.6% | 55.9 | — | 16 Apr 2026 | Vals AI |
| GPQA Diamond | Knowledge | 88.1% | 59.6 | — | 1 Sept 2026 | Vals AI |
| GPQA Diamond | Knowledge | 88.1% | 59.6 | — | 1 Sept 2026 | Vals AI |
| Artificial Analysis GPQA Diamond | Knowledge | 87.7% | 58.4 | — | — | Artificial Analysis |
| GPQA diamond | Knowledge | 87.0% | 58.6 | — | — | Epoch AI |
| MMLU Pro | Knowledge | 85.3% | 54.9 | — | 1 Sept 2026 | Vals AI |
| MMLU Pro | Knowledge | 85.3% | 54.9 | — | 1 Sept 2026 | Vals AI |
| OTIS Mock AIME 2024-2025 | Math | 84.0% | 58.5 | — | — | Epoch AI |
| LiveCodeBench | Coding | 83.2% | 60.0 | — | 1 Sept 2026 | Vals AI |
| LiveCodeBench | Coding | 83.2% | 60.0 | — | 1 Sept 2026 | Vals AI |
| MMMU Pro | Multimodal | 76.3% | 51.5 | — | 1 Sept 2026 | Vals AI |
| MMMU Pro | Multimodal | 76.3% | 51.5 | — | 1 Sept 2026 | Vals AI |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 74.9% | 52.6 | — | — | Victor Barres et al. |
| React Native Evals | Coding | 72.6% | 49.3 | — | — | Callstack |
| Artificial Analysis MMMU-Pro | Multimodal | 68.8% | 51.2 | — | — | Artificial Analysis |
| Artificial Analysis Long Context Reasoning | Reasoning | 68.0% | 55.3 | — | — | Artificial Analysis |
| SWE-bench | Coding | 57.8% | 43.9 | — | 1 Sept 2026 | Vals AI |
| SWE-bench | Coding | 57.8% | 43.9 | — | 1 Sept 2026 | Vals AI |
| Artificial Analysis IFBench | Instruction | 53.7% | 43.6 | — | — | Artificial Analysis |
| Gert Labs Composite Game Benchmark | Agentic | 42.3% | 50.1 | — | — | Gert Labs |
| Artificial Analysis Omniscience Accuracy | Knowledge | 40.5% | 64.0 | — | — | Artificial Analysis |
| Terminal-Bench 1.0 | Agentic | 38.8% | 44.4 | — | 12 Jan 2026 | Vals AI |
| Terminal-Bench 1.0 | Agentic | 38.8% | 44.4 | — | 12 Jan 2026 | Vals AI |
| Terminal-Bench 2.0 | Agentic | 28.1% | 42.7 | — | 4 Jun 2026 | Vals AI |
| Terminal-Bench 2.0 | Agentic | 28.1% | 42.7 | — | 4 Jun 2026 | Vals AI |
| Chess Puzzles | Reasoning | 28.0% | 59.7 | — | — | Epoch AI |
| Artificial Analysis Humanity's Last Exam | Knowledge | 26.7% | 53.5 | — | — | Artificial Analysis |
| IOI v1 | Coding | 26.2% | 54.8 | — | 9 Aug 2026 | Vals AI |
| IOI v1 | Coding | 26.2% | 54.8 | — | 9 Aug 2026 | Vals AI |
| Artificial Analysis Intelligence Index | Knowledge | 22.5% | 50.5 | — | — | Artificial Analysis |
| FrontierMath-2025-02-28-Private | Math | 19.7% | 49.0 | — | — | Epoch AI |
| FrontierMath-Tier-4-2025-07-01-Private | Math | 2.1% | 45.7 | — | — | Epoch AI |
| Critical Physics Tasks | Reasoning | 2.0% | 42.6 | — | — | Artificial Analysis |
25 benchmarks count, from 36 of 38 results. A grey row does not count. Too few models took that benchmark.