Model comparison
Grok 3 vs Yi-Lightning
Grok 3 is the stronger model overall, scoring 39.9 to 37.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
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 41.9 to 27.4.
- The biggest single-benchmark swing is Aider Polyglot: 53.3% for Grok 3 and 12.9% for Yi-Lightning.
Side by side
| Grok 3 | Yi-Lightning | |
|---|---|---|
| Provider | xAI | 01.AI |
| Noometry Index | 39.9 | 37.1 |
| Released | 2025-04-09 | 2024-12-02 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 40 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.9 (#115), Yi-Lightning: 27.4 (#320)
| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| Aider Polyglot | 53.3% | 12.9% |
| LMArena Coding | 1432 | 1312 |
| WeirdML | 37.2% | — |
Agentic & Tool Use Not comparable
Grok 3: 30.5 (#76), Yi-Lightning: —
| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| BALROG | 29.5% | — |
Reasoning Yi-Lightning leads
Grok 3: 13.7 (#333), Yi-Lightning: 25.9 (#139)
| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1434 | 1302 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| Epoch Capabilities Index | 138.33 | — |
Math Grok 3 leads
Grok 3: 38.0 (#145), Yi-Lightning: 36.2 (#172)
| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| LMArena Math | 1391 | 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 leads
Grok 3: 46.2 (#82), Yi-Lightning: 35.4 (#185)
| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1421 | 1286 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |
Multilingual Grok 3 leads
Grok 3: 52.3 (#87), Yi-Lightning: 42.2 (#196)
| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1410 | 1269 |
| LMArena Chinese | 1448 | 1320 |
| LMArena French | 1460 | 1305 |
| LMArena German | 1431 | 1267 |
| LMArena Japanese | 1387 | 1228 |
| LMArena Korean | 1373 | 1192 |
| LMArena Russian | 1416 | 1255 |
| LMArena Spanish | 1417 | 1315 |
Instruction Following Grok 3 leads
Grok 3: 75.0 (#73), Yi-Lightning: 67.4 (#196)
| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1409 | 1278 |
| IFEval | 88.4% | — |
Long Context Too close to call
Grok 3: 38.7 (#192), Yi-Lightning: 39.4 (#181)
| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1439 | 1297 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Grok 3 leads
Grok 3: 55.8 (#141), Yi-Lightning: 50.2 (#184)
| Benchmark | Grok 3 | Yi-Lightning |
|---|---|---|
| LMArena Text | 1426 | 1302 |
| LMArena Creative Writing | 1414 | 1280 |
| LMArena Multi-Turn | 1425 | 1311 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than Yi-Lightning?
Grok 3 is the stronger model overall, scoring 39.9 to 37.1 on the Noometry Index.
Is Grok 3 or Yi-Lightning better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 27.4 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.