# Grok 3 vs Yi-Lightning

> Grok 3 is the stronger model overall, scoring 39.6 to 36.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-vs-yi-lightning
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Grok 3 scores higher in 6 categories and Yi-Lightning in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Grok 3 leads 41.5 to 27.0.
- The biggest single-benchmark swing is Aider Polyglot: 53.3% for Grok 3 and 12.9% for Yi-Lightning.

## Snapshot

| | Grok 3 | Yi-Lightning |
|---|---|---|
| Provider | xAI | 01.AI |
| Noometry Index | 39.6 | 36.5 |
| Rank | 150 | 206 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Grok 3: 41.5 (#113)
- Yi-Lightning: 27.0 (#315)

| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| Aider Polyglot | 53.3% | 12.9% |
| LMArena Coding | 1432 | 1313 |
| WeirdML | 37.2% | — |

## Agentic & Tool Use

- Grok 3: 30.2 (#69)
- Yi-Lightning: —

| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| BALROG | 29.5% | — |

## Reasoning

- Grok 3: 13.8 (#322)
- Yi-Lightning: 24.9 (#137)

| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1302 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| Epoch Capabilities Index | 138.34 | — |

## Math

- Grok 3: 36.2 (#122)
- Yi-Lightning: 33.5 (#173)

| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| LMArena Math | 1390 | 1300 |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| Omni-MATH | 46.4% | — |
| MATH Level 5 | 88.7% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Grok 3: 46.0 (#76)
- Yi-Lightning: 34.8 (#182)

| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1420 | 1286 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |

## Multilingual

- Grok 3: 52.5 (#81)
- Yi-Lightning: 42.4 (#191)

| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1411 | 1269 |
| LMArena Chinese | 1448 | 1320 |
| LMArena French | 1460 | 1304 |
| LMArena German | 1431 | 1267 |
| LMArena Japanese | 1389 | 1228 |
| LMArena Korean | 1374 | 1192 |
| LMArena Russian | 1416 | 1255 |
| LMArena Spanish | 1417 | 1315 |

## Instruction Following

- Grok 3: 75.2 (#69)
- Yi-Lightning: 67.6 (#191)

| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1409 | 1278 |
| IFEval | 88.4% | — |

## Long Context

- Grok 3: 38.7 (#187)
- Yi-Lightning: 39.4 (#176)

| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1439 | 1297 |
| Fiction.LiveBench | 58.3% | — |

## Writing & Preference

- Grok 3: 56.0 (#136)
- Yi-Lightning: 50.4 (#178)

| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| LMArena Text | 1426 | 1302 |
| LMArena Creative Writing | 1414 | 1280 |
| LMArena Multi-Turn | 1424 | 1311 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |

## FAQ

### Is Grok 3 better than Yi-Lightning?

Grok 3 is the stronger model overall, scoring 39.6 to 36.5 on the Noometry Index.

### Is Grok 3 or Yi-Lightning better for coding?

Grok 3 scores higher on coding benchmarks: 41.5 versus 27.0 in the Noometry coding category.

### How many benchmarks do Grok 3 and Yi-Lightning share?

18 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Yi-Lightning has 18.