Model comparison
Llama-3.3-70B-Instruct vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 30.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 2 categories and Yi-Lightning in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-Lightning leads 36.2 to 15.3.
- Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.
Side by side
| Llama-3.3-70B-Instruct | Yi-Lightning | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 30.6 | 37.1 |
| Released | 2024-12-06 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.32 | — |
| Results tracked | 43 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 31.0 (#290), Yi-Lightning: 27.4 (#320)
| Benchmark | Llama-3.3-70B-Instruct | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1268 | 1312 |
| Aider Polyglot | — | 12.9% |
| SciCode | 26% | — |
| WeirdML | 14.4% | — |
| BigCodeBench Instruct | 46.9% | — |
| LiveBench Coding | 36.6% | — |
| BigCodeBench Complete | 57.5% | — |
Agentic & Tool Use Not comparable
Llama-3.3-70B-Instruct: 25.8 (#105), Yi-Lightning: —
| Benchmark | Llama-3.3-70B-Instruct | Yi-Lightning |
|---|---|---|
| Berkeley Function Calling Leaderboard | 31.9% | — |
| BALROG | 23% | — |
Reasoning Yi-Lightning leads
Llama-3.3-70B-Instruct: 14.1 (#327), Yi-Lightning: 25.9 (#139)
| Benchmark | Llama-3.3-70B-Instruct | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1302 |
| SimpleBench | 19.9% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 50.8% | — |
| DTBench | 59.5% | — |
| LiveBench Data Analysis | 49.5% | — |
| LMCA | 17.5% | — |
| Epoch Capabilities Index | 127.33 | — |
| ForecastBench | 58.6 | — |
| LiveBench | 50.2% | — |
Math Yi-Lightning leads
Llama-3.3-70B-Instruct: 15.3 (#298), Yi-Lightning: 36.2 (#172)
| Benchmark | Llama-3.3-70B-Instruct | Yi-Lightning |
|---|---|---|
| LMArena Math | 1267 | 1300 |
| OTIS Mock AIME 2024-2025 | 5.1% | — |
| LiveBench Math | 42.2% | — |
| MATH Level 5 | 41.6% | — |
Knowledge Yi-Lightning leads
Llama-3.3-70B-Instruct: 30.6 (#226), Yi-Lightning: 35.4 (#185)
| Benchmark | Llama-3.3-70B-Instruct | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1225 | 1286 |
| GPQA Diamond | 47.4% | — |
| Confabulations | 22.8% | — |
| Vectara Hallucination Rate | 4.1% | — |
| MMLU | 86.3% | — |
Multilingual Yi-Lightning leads
Llama-3.3-70B-Instruct: 39.9 (#220), Yi-Lightning: 42.2 (#196)
| Benchmark | Llama-3.3-70B-Instruct | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1236 | 1269 |
| LMArena Chinese | 1217 | 1320 |
| LMArena French | 1281 | 1305 |
| LMArena German | 1251 | 1267 |
| LMArena Japanese | 1150 | 1228 |
| LMArena Korean | 1143 | 1192 |
| LMArena Russian | 1252 | 1255 |
| LMArena Spanish | 1270 | 1315 |
Instruction Following Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 71.1 (#157), Yi-Lightning: 67.4 (#196)
| Benchmark | Llama-3.3-70B-Instruct | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1242 | 1278 |
| LiveBench Instruction Following | 82.7% | — |
Long Context Yi-Lightning leads
Llama-3.3-70B-Instruct: 26.4 (#295), Yi-Lightning: 39.4 (#181)
| Benchmark | Llama-3.3-70B-Instruct | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1256 | 1297 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Yi-Lightning leads
Llama-3.3-70B-Instruct: 47.6 (#207), Yi-Lightning: 50.2 (#184)
| Benchmark | Llama-3.3-70B-Instruct | Yi-Lightning |
|---|---|---|
| LMArena Text | 1274 | 1302 |
| LMArena Creative Writing | 1250 | 1280 |
| LMArena Multi-Turn | 1280 | 1311 |
| LiveBench Language | 39.2% | — |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 30.6 on the Noometry Index.
Is Llama-3.3-70B-Instruct or Yi-Lightning better for coding?
Llama-3.3-70B-Instruct scores higher on coding benchmarks: 31.0 versus 27.4 in the Noometry coding category.
How many benchmarks do Llama-3.3-70B-Instruct and Yi-Lightning share?
17 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Yi-Lightning has 18.