xAI·released 2024-12-121 source
Grok-2 (Dec 2024) benchmark scores: 8 benchmarks tracked. 50% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 8 benchmarks·best result 63.6 on Lech Mazur Writing (unverified)·4 of 8 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| Lech Mazur Writing | 63.6accuracy (%) | unverifiedT1 | 2024-12-12lechmazur/writing Github repository |
| MATH level 5 | 63.52accuracy (%) | reproduced· optimizedT1 | 2024-12-12Epoch AI |
| DTBench | 42.02accuracy (%) | unverifiedT1 | 2024-12-12https://conceptualreasoning.ai/dtbench |
| GPQA diamond | 38.38accuracy (%) | reproduced· optimizedT1 | 2024-12-12Epoch AI |
| WeirdML | 22.24accuracy (%) | unverifiedT1 | 2024-12-12https://htihle.github.io/weirdml.html |
| OTIS Mock AIME 2024-2025 | 11.44accuracy (%) | reproduced· optimizedT1 | 2024-12-12Epoch AI |
| SimpleBench | 7.24accuracy (%) | unverifiedT1 | 2024-12-12SimpleBench Leaderboard |
| FrontierMath-2025-02-28-Private | 1.21accuracy (%) | reproduced· optimizedT1 | 2024-12-12Epoch AI |
Claims drawn from cited facts, not live model generation.
This model was developed by xAI and released in 2024.
2 cited facts
The model is scored on 8 tracked benchmarks, but it holds no current top score on any of them. Its record is independently reproduced, meaning outside evaluation backs up the reported scores.
3 cited facts
On average the model trails the state-of-the-art leader by 58.22 points, a wide gap that reads as well behind the front of the pack rather than at the frontier or merely competitive. It also holds the top score on zero of its benchmarks, so there is no category leadership to point to yet.
2 cited facts
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
Grok-2 (Dec 2024) is an AI model developed by xAI, released 2024-12-12. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Grok-2 (Dec 2024) has recorded scores on 8 benchmarks, each shown with its evidence status.
Grok-2 (Dec 2024) has recorded scores on 8 benchmarks — Lech Mazur Writing, GPQA diamond, MATH level 5, OTIS Mock AIME 2024-2025, DTBench, WeirdML, and 2 more. The full table above shows each score with its evidence status.
4 of 8 recorded scores (50%) are independently reproduced rather than self-reported by the lab.
Grok-2 (Dec 2024) has 8 tracked claims: 4 independently reproduced, 4 unverified.