xAI·released 2025-04-091 source
Grok 3 benchmark scores: 13 benchmarks tracked. 38% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 13 benchmarks·best result 88.75 on MATH level 5 (reproduced)·5 of 13 independently reproduced·$3/$15 per M tokens
Consensus: LiteLLM · See every model’s pricing →
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| MATH level 5 | 88.75accuracy (%) | reproduced· optimizedT1 | 2025-04-09Epoch AI |
| Lech Mazur Writing | 76.4accuracy (%) | unverifiedT1 | 2025-04-09lechmazur/writing Github repository |
| GPQA diamond | 67.68accuracy (%) | reproduced· optimizedT1 | 2025-04-09Epoch AI |
| Fiction.LiveBench | 58.3accuracy (%) | unverifiedT1 | 2025-04-09Fiction.live leaderboard |
| OTIS Mock AIME 2024-2025 | 55.51accuracy (%) | reproduced· optimizedT1 | 2025-04-09Epoch AI |
| Aider polyglot | 53.3accuracy (%) | unverified· optimizedT1 | 2025-04-09https://aider.chat/docs/leaderboards/ |
| WeirdML | 37.24accuracy (%) | unverifiedT1 | 2025-04-09https://htihle.github.io/weirdml.html |
| Balrog | 29.5accuracy (%) | unverifiedT1 | 2025-04-09https://balrogai.com/ |
| SimpleBench | 23.32accuracy (%) | unverifiedT1 | 2025-04-09SimpleBench Leaderboard |
| FrontierMath-2025-02-28-Private | 6.65accuracy (%) | reproduced· optimizedT1 | 2025-04-09Epoch AI |
| ARC-AGI | 5.5accuracy (%) | unverified· optimizedT1 | 2025-04-09ARC Prize Leaderboard |
| FrontierMath-Tier-4-2025-07-01-Private | 0accuracy (%) | reproducedT1 | 2025-04-09Epoch AI |
| ARC-AGI-2 | 0accuracy (%) | unverifiedT2 | 2025-04-09 |
Claims drawn from cited facts, not live model generation.
This model was developed by xAI and released in 2025, placing it among the more recent entrants in the field.
2 cited facts
This model is scored on 13 tracked benchmarks and currently holds no top score among them. The results are independently reproduced, meaning outside evaluation backs up the reported scores and they can be treated as externally verified.
3 cited facts
Its mean gap to the best recorded score across its tracked benchmarks is 45.82 points.
1 cited fact
6 facts cross-checked across data sources: 6 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks, litellm_prices
Grok 3 is an AI model developed by xAI, released 2025-04-09. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Grok 3 has recorded scores on 13 benchmarks, each shown with its evidence status.
Grok 3 has recorded scores on 13 benchmarks — Lech Mazur Writing, GPQA diamond, MATH level 5, OTIS Mock AIME 2024-2025, WeirdML, SimpleBench, and 7 more. The full table above shows each score with its evidence status.
5 of 13 recorded scores (38%) are independently reproduced rather than self-reported by the lab.
Grok 3 has 13 tracked claims: 5 independently reproduced, 8 unverified.
Listed API pricing: $3 per million input tokens, $15 per million output tokens. See the pricing block for the full breakdown.