Grok 4 Fast ranks first on AgentDojo.
Closed weights
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SimpleQA | 95% | #3 of 59 | Model card | |
| Fiction.LiveBench | 94.4% | #4 of 57 | Epoch AI | |
| LMArena (Elo) | 1,418 | #105 of 333 | Official leaderboard | |
| Phare | 66.5% | #31 of 62 | Official leaderboard | |
| FACTS Search | 67.3% | #17 of 31 | Official leaderboard | |
| Humanity's Last Exam | 20% | #98 of 147 | Model card | |
| SimpleQA Verified | 19.7% | #42 of 56 | Official leaderboard | |
| FACTS Parametric | 15.8% | #36 of 45 | Official leaderboard | |
| Vectara Hallucination Leaderboard (2025 dataset) | 19.7% | #99 of 104 | Official leaderboard | |
| FACTS Multimodal | 17.7% | #38 of 39 | Official leaderboard | |
| FACTS Benchmark Suite | 17.7% | #40 of 40 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 85.7% | #67 of 284 | Model card | |
| BRUMO 2025 | 95.8% | #11 of 42 | Official leaderboard | |
| AIME 2025 | 92% | #42 of 143 | Model card | |
| HMMT 2025 | 93.3% | #18 of 49 | Model card | |
| CMIMC 2025 | 85% | #14 of 33 | Official leaderboard | |
| DTBench | 71.1% | #78 of 178 | Official leaderboard | |
| HMMT Nov 2025 | 90.8% | #10 of 22 | Official leaderboard | |
| MathArena (Apex, IMO, USAMO) | 5.21% | #26 of 47 | Official leaderboard | |
| SMT 2025 | 84.4% | #23 of 40 | Official leaderboard | |
| ARC-AGI-2 | 5.28% | #64 of 95 | Official leaderboard | |
| ARC-AGI | 48.5% | #65 of 92 | Official leaderboard | |
| ForecastBench | 64.8 | #72 of 86 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveCodeBench | 80% | #12 of 73 | Model card | |
| IOI (Vals) | 11.5% | #32 of 55 | Official leaderboard | |
| WeirdML | 42.9% | #67 of 112 | Official leaderboard | |
| Vibe Code Bench v1 | 0% | #16 of 17 | Official leaderboard | |
| Vibe Code Bench | 0% | #112 of 115 | Official leaderboard | |
| Code Arena | 1,159 | #123 of 124 | Official leaderboard | |
| WebDev Arena | 1,149 | #105 of 105 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 33 | #17 of 183 | Official leaderboard | |
| MCP-Universe | 32.5% | #7 of 30 | Official leaderboard | |
| LLM Chess | 735 | #34 of 124 | Official leaderboard | |
| LisanBench | 2749.6 | #37 of 133 | Official leaderboard | |
| MCPMark | 24% | #13 of 28 | Official leaderboard | |
| Research-Eval | 66% | #1 of 2 | Model card | |
| X Browse (xAI) | 58% | #1 of 2 | Model card | |
| Agent Poker Bench | 1,034 | #10 of 17 | Official leaderboard | |
| CompileBench | 73.3% | #13 of 20 | Official leaderboard | |
| xbench-DeepSearch | 74% | #2 of 3 | Model card | |
| BrowseComp-ZH | 51.2% | #12 of 17 | Model card | |
| BrowseComp | 44.9% | #63 of 77 | Model card | |
| Toolathlon | 18.5% | #41 of 50 | Official leaderboard | |
| τ³-bench Banking | 15.7% | #21 of 25 | Official leaderboard | |
| LMArena Search Arena | 1,161 | #32 of 35 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| TaxEval v2 | 75.7% | #13 of 129 | Official leaderboard | |
| CorpFin v2 | 66.9% | #16 of 119 | Official leaderboard | |
| CaseLaw v2 | 65.7% | #10 of 53 | Official leaderboard | |
| Vals Finance Agent v1 | 37.1% | #20 of 47 | Official leaderboard | |
| ProfBench | 48.7% | #33 of 72 | Official leaderboard | |
| MedScribe | 81.6% | #49 of 98 | Official leaderboard | |
| FailureSensorIQ | 64.1% | #14 of 24 | Official leaderboard | |
| LegalBench | 80.6% | #81 of 138 | Official leaderboard | |
| Vals Finance Agent | 46.1% | #35 of 49 | Official leaderboard | |
| MedCode | 37.4% | #70 of 96 | Official leaderboard | |
| MortgageTax | 42.1% | #81 of 86 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ClockBench | 3.30% | #37 of 37 | Official leaderboard | |
| Math Kangaroo 2025 (MathArena) | 66.8% | #22 of 22 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| PCT (Polarized Contrastive Pairs) | 30.8% | #3 of 46 | Official leaderboard | |
| AgentDojo | 0% | #1 of 7 | Model card | |
| Virology Capabilities Test (VCT) | 54.5% | #12 of 28 | Model card | |
| General refusals (xAI) | 0% | #3 of 7 | Model card | |
| BioLP-bench | 39% | #4 of 9 | Model card | |
| Cybench | 30% | #12 of 24 | Official leaderboard | |
| Refusals + System Jailbreak (xAI) | 0% | #2 of 4 | Model card | |
| Human Pathogen Capabilities Test v2 (HPCT v2) | 50.9% | #40 of 71 | Official leaderboard | |
| Spiral-Bench v1.2 | 37.5 | #12 of 21 | Official leaderboard | |
| SycophancyEval (answer sycophancy) | 10% | #2 of 3 | Model card | |
| Refusals + User Jailbreak (xAI) | 0% | #3 of 4 | Model card | |
| MASK | 47% | #16 of 21 | Model card | |
| MakeMeSay | 12% | #8 of 9 | Model card | |
| AgentHarm | 8.00% | #6 of 6 | Model card | |
| Soft Bias (Internal) | 0.79 | #2 of 2 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CAIS Risk Index | 58.3 | #45 of 65 | Official leaderboard | |
| CAIS Text Capabilities Index | 19.0 | #50 of 66 | Official leaderboard | |
| CAIS Vision Capabilities Index | 37.7 | #47 of 53 | Official leaderboard | |
| SAGE (Vals) | 29.8% | #77 of 81 | Official leaderboard |
xAI's models in color, against every other model on the Epoch Capabilities Index, by release date.
The benchmarks the lab chose to headline, with the scores it gave.
Every result in the longer documents the lab published with it. 13 of them aren't in the launch post.