xAI·released 2026-09-211 source
Grok 4.7 benchmark scores: 16 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 16 benchmarks·best result 98.05 on OTIS Mock AIME 2024-2025 (unverified)·0 of 16 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.05accuracy (%) | unverifiedT2 | 2026-09-21 |
| DTBench | 93.33accuracy (%) | unverifiedT1 | 2026-09-21https://conceptualreasoning.ai/dtbench |
| GPQA diamond | 90.32accuracy (%) | unverifiedT2 | 2026-09-21 |
| ARC-AGI | 90.17accuracy (%) | unverifiedT1 | 2026-09-21https://arcprize.org/leaderboard |
| ARC-AGI-2 | 61.39accuracy (%) | unverifiedT2 | 2026-09-21 |
| LMCA | 58.09accuracy (%) | unverifiedT1 | 2026-09-21https://conceptualreasoning.ai/lmca |
| SimpleQA Verified | 56accuracy (%) | unverifiedT2 | 2026-09-21 |
| APEX-Agents | 54.6accuracy (%) | unverifiedT2 | 2026-09-21 |
| FrontierMath-Tiers-1-3-v2-Private | 52.98accuracy (%) | unverifiedT2 | 2026-09-21 |
| FrontierCode | 47.59accuracy (%) | unverifiedT1 | 2026-09-21https://cognition.com/frontiercode |
| Chess Puzzles | 37.92accuracy (%) | unverifiedT2 | 2026-09-21 |
| ProofBench | 34accuracy (%) | unverifiedT1 | 2026-09-21https://www.vals.ai/benchmarks/proof_bench |
| FrontierSWE | 29.5accuracy (%) | unverifiedT1 | 2026-09-21https://www.frontierswe.com/ |
| Mystery Game Puzzles | 21.79accuracy (%) | unverifiedT2 | 2026-09-21 |
| FrontierMath-Tier-4-v2-Private | 17.07accuracy (%) | unverifiedT2 | 2026-09-21 |
| Furniture Assembly | 0accuracy (%) | unverifiedT2 | 2026-09-21 |
Claims drawn from cited facts, not live model generation.
This model was developed by xAI and released in 2026.
2 cited facts
The model is scored on 16 tracked benchmarks. It holds no current top score on any of them. Its record remains unverified, meaning outside evaluation has neither confirmed nor disputed the reported numbers, so they are best read as claims rather than settled results.
3 cited facts
On average the model trails the leading score by 32.99 points across its benchmarks, a wide gap under the disclosed harness that places it well behind the front of the pack rather than at the frontier. It holds the top score on none of those benchmarks, so there is no category in which it demonstrates genuine leadership 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 4.7 is an AI model developed by xAI, released 2026-09-21. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Grok 4.7 has recorded scores on 16 benchmarks, each shown with its evidence status.
Grok 4.7 has recorded scores on 16 benchmarks — GPQA diamond, OTIS Mock AIME 2024-2025, DTBench, LMCA, SimpleQA Verified, Chess Puzzles, and 10 more. The full table above shows each score with its evidence status.
0 of 16 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Grok 4.7 has 16 tracked claims: 16 unverified.