Model comparison
Grok-2 (Dec 2024) vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 33.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 2 categories and Yi-Lightning in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-Lightning leads 36.2 to 20.8.
Side by side
| Grok-2 (Dec 2024) | Yi-Lightning | |
|---|---|---|
| Provider | xAI | 01.AI |
| Noometry Index | 33.7 | 37.1 |
| Released | 2024-08-13 | 2024-12-02 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 34 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 33.3 (#258), Yi-Lightning: 27.4 (#320)
| Benchmark | Grok-2 (Dec 2024) | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1287 | 1312 |
| Aider Polyglot | — | 12.9% |
| WeirdML | 22.2% | — |
| LiveBench Coding | 46.4% | — |
Reasoning Yi-Lightning leads
Grok-2 (Dec 2024): 16.9 (#299), Yi-Lightning: 25.9 (#139)
| Benchmark | Grok-2 (Dec 2024) | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1302 |
| SimpleBench | 22.7% | — |
| LiveBench Reasoning | 54.8% | — |
| DTBench | 65.2% | — |
| LiveBench Data Analysis | 54.5% | — |
| Epoch Capabilities Index | 130.48 | — |
| LiveBench | 54.3% | — |
Math Yi-Lightning leads
Grok-2 (Dec 2024): 20.8 (#284), Yi-Lightning: 36.2 (#172)
| Benchmark | Grok-2 (Dec 2024) | Yi-Lightning |
|---|---|---|
| LMArena Math | 1283 | 1300 |
| OTIS Mock AIME 2024-2025 | 11.5% | — |
| LiveBench Math | 54.9% | — |
| MATH Level 5 | 63.5% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Yi-Lightning leads
Grok-2 (Dec 2024): 29.8 (#233), Yi-Lightning: 35.4 (#185)
| Benchmark | Grok-2 (Dec 2024) | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1254 | 1286 |
| GPQA Diamond | 53.8% | — |
| Confabulations | 20.1% | — |
Multilingual Too close to call
Grok-2 (Dec 2024): 43.1 (#188), Yi-Lightning: 42.2 (#196)
| Benchmark | Grok-2 (Dec 2024) | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1282 | 1269 |
| LMArena Chinese | 1289 | 1320 |
| LMArena French | 1318 | 1305 |
| LMArena German | 1287 | 1267 |
| LMArena Japanese | 1244 | 1228 |
| LMArena Korean | 1237 | 1192 |
| LMArena Russian | 1286 | 1255 |
| LMArena Spanish | 1281 | 1315 |
Instruction Following Too close to call
Grok-2 (Dec 2024): 66.9 (#202), Yi-Lightning: 67.4 (#196)
| Benchmark | Grok-2 (Dec 2024) | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1270 | 1278 |
| LiveBench Instruction Following | 69.6% | — |
Long Context Too close to call
Grok-2 (Dec 2024): 38.8 (#190), Yi-Lightning: 39.4 (#181)
| Benchmark | Grok-2 (Dec 2024) | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1276 | 1297 |
Writing & Preference Yi-Lightning leads
Grok-2 (Dec 2024): 48.6 (#198), Yi-Lightning: 50.2 (#184)
| Benchmark | Grok-2 (Dec 2024) | Yi-Lightning |
|---|---|---|
| LMArena Text | 1305 | 1302 |
| LMArena Creative Writing | 1284 | 1280 |
| LMArena Multi-Turn | 1290 | 1311 |
| Short-Story Creative Writing | 63.6% | — |
| LiveBench Language | 45.6% | — |
Frequently asked questions
Is Grok-2 (Dec 2024) better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 33.7 on the Noometry Index.
Is Grok-2 (Dec 2024) or Yi-Lightning better for coding?
Grok-2 (Dec 2024) scores higher on coding benchmarks: 33.3 versus 27.4 in the Noometry coding category.
How many benchmarks do Grok-2 (Dec 2024) and Yi-Lightning share?
17 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Yi-Lightning has 18.