xAI
availableShows if the model has enough results for an index.Grok 4.3
Grok 4.3 is a reasoning model from xAI. 35 benchmarks count toward its score, in 7 categories.
IndexOverall score out of 100.56.0 ±3.2
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.91/s
Input / 1MUS dollars per 1M input tokens.$1.25 batch $1
Output / 1MUS dollars per 1M output tokens.$2.5 batch $2 US dollars per 1M output tokens in a batch.
ContextMaximum tokens in one request.1M
EloLMArena rating and rank.1398 (#145)
The index is a score out of 100. The ± range shows how much it can change. Batch work costs less.
66,801 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category, out of 100.
Out of 100Results
35 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. |
|---|---|---|---|---|---|---|
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 97.7% | 68.9 | — | — | Victor Barres et al. |
| GPQA Diamond | Knowledge | 91.4% | 62.6 | — | 1 Sept 2026 | Vals AI |
| Graduate-Level Google-Proof Q&A | Knowledge | 90.1% | 61.4 | — | — | David Rein et al. |
| Artificial Analysis GPQA Diamond | Knowledge | 90.1% | 60.9 | — | — | Artificial Analysis |
| MMLU Pro | Knowledge | 85.8% | 55.8 | — | 1 Sept 2026 | Vals AI |
| LiveCodeBench | Coding | 84.5% | 61.1 | — | 1 Sept 2026 | Vals AI |
| LiveBench Mathematics | Math | 84.3% | 60.6 | — | 25 Jun 2026 | LiveBench |
| MMMU Pro | Multimodal | 83.1% | 62.5 | — | 1 Sept 2026 | Vals AI |
| Instruction Following Benchmark | Instruction | 81.3% | 60.6 | — | — | Benchmark authors |
| Artificial Analysis IFBench | Instruction | 81.3% | 71.6 | — | — | Artificial Analysis |
| Massive Multi-discipline Multimodal Understanding Pro | Multimodal | 78.1% | 54.4 | — | — | MMMU-Pro authors |
| Artificial Analysis MMMU-Pro | Multimodal | 78.1% | 62.5 | — | — | Artificial Analysis |
| LiveBench Language | Knowledge | 73.6% | 59.4 | — | 25 Jun 2026 | LiveBench |
| SWE-bench | Coding | 71.4% | 54.8 | — | 1 Sept 2026 | Vals AI |
| LiveBench Reasoning | Reasoning | 70.8% | 54.3 | — | 25 Jun 2026 | LiveBench |
| LiveBench Coding | Coding | 69.9% | 53.8 | — | 25 Jun 2026 | LiveBench |
| Artificial Analysis Long Context Reasoning | Reasoning | 64.3% | 52.7 | — | — | Artificial Analysis |
| LiveBench Instruction Following | Instruction | 62.8% | 59.2 | — | 25 Jun 2026 | LiveBench |
| LiveBench Data Analysis | Reasoning | 55.8% | 33.4 | — | 25 Jun 2026 | LiveBench |
| Artificial Analysis SciCode | Coding | 48.3% | 59.9 | — | — | Artificial Analysis |
| Scientific Code Benchmark | Coding | 47.3% | 57.7 | — | — | Benchmark authors |
| Gert Labs Composite Game Benchmark | Agentic | 43.9% | 51.5 | — | — | Gert Labs |
| Terminal-Bench 2.0 | Agentic | 43.4% | 53.7 | — | 4 Jun 2026 | Vals AI |
| Artificial Analysis Coding Index | Coding | 42.3% | 48.7 | — | — | Artificial Analysis |
| Terminal-Bench 2.1 | Agentic | 41.9% | 48.8 | — | 21 Sept 2026 | Vals AI |
| SkillsBench | Coding | 40.6% | 57.5 | OpenHands | 11 Sept 2026 | Vals AI |
| Artificial Analysis Intelligence Index | Knowledge | 37.6% | 69.4 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 37.2% | 64.9 | — | — | Artificial Analysis |
| Humanity's Last Exam | Knowledge | 35.0% | 58.4 | — | — | Center for AI Safety et al. |
| Artificial Analysis Omniscience Accuracy | Knowledge | 34.6% | 56.7 | — | — | Artificial Analysis |
| GDPval-AA normalized | Agentic | 29.2% | 58.0 | — | — | Artificial Analysis |
| Vibe Code Bench v1.1 | Coding | 19.4% | 50.2 | OpenHands | 21 Sept 2026 | Vals AI |
| LiveBench Agentic Coding | Agentic | 18.5% | 34.2 | — | 25 Jun 2026 | LiveBench |
| Artificial Analysis Agentic Index | Agentic | 17.2% | 51.2 | — | — | Artificial Analysis |
| APEX-Agents-AA | Agentic | 17.0% | 54.5 | — | — | Artificial Analysis / Mercor |
| IOI v1 | Coding | 15.3% | 48.7 | — | 9 Aug 2026 | Vals AI |
| ResearchClawBench | Agentic | 12.4% | — | — | — | InternScience |
| Critical Physics Tasks | Reasoning | 8.0% | 55.2 | — | — | Artificial Analysis |
| Code Migration | Coding | 6.8% | 49.2 | — | 21 Sept 2026 | Vals AI |
| ProgramBench | Coding | 0.0% | — | — | 21 Sept 2026 | Vals AI |
35 benchmarks count, from 38 of 40 results. A grey row does not count. Too few models took that benchmark.