Model comparison
GPT-4o vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 28.6 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. GPT-4o scores higher in 3 categories and Yi-Lightning in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-Lightning leads 36.2 to 10.6.
- The biggest single-benchmark swing is Aider Polyglot: 45.3% for GPT-4o and 12.9% for Yi-Lightning.
Side by side
| GPT-4o | Yi-Lightning | |
|---|---|---|
| Provider | OpenAI | 01.AI |
| Noometry Index | 28.6 | 37.1 |
| Released | 2024-05-13 | 2024-12-02 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 72 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-Lightning leads
GPT-4o: 24.8 (#328), Yi-Lightning: 27.4 (#320)
| Benchmark | GPT-4o | Yi-Lightning |
|---|---|---|
| Aider Polyglot | 45.3% | 12.9% |
| LMArena Coding | 1297 | 1312 |
| SWE-bench Verified | 31% | — |
| SWE-bench Verified (bash only) | 21.6% | — |
| GSO | 0% | — |
| WeirdML | 25.1% | — |
| BigCodeBench Instruct | 51.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 61.1% | — |
| CadEval | 26% | — |
| HumanEval+ | 87.2% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Not comparable
GPT-4o: 21.0 (#141), Yi-Lightning: —
| Benchmark | GPT-4o | Yi-Lightning |
|---|---|---|
| GDPval | 9.9% | — |
| TheAgentCompany | 8.6% | — |
| Cybench | 12.5% | — |
| BALROG | 32.3% | — |
| LMArena Search | 1006 | — |
| METR Time Horizons | 40.8% | — |
Reasoning Yi-Lightning leads
GPT-4o: 9.4 (#343), Yi-Lightning: 25.9 (#139)
| Benchmark | GPT-4o | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1281 | 1302 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 17.8% | — |
| ARC-AGI-1 | 4.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | 13% | — |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 55.8% | — |
| DTBench | 64.5% | — |
| LiveBench Data Analysis | 60.9% | — |
| LMCA | 16.6% | — |
| Epoch Capabilities Index | 128.97 | — |
| ForecastBench | 57.7 | — |
| LiveBench | 55.3% | — |
Math Yi-Lightning leads
GPT-4o: 10.6 (#312), Yi-Lightning: 36.2 (#172)
| Benchmark | GPT-4o | Yi-Lightning |
|---|---|---|
| LMArena Math | 1285 | 1300 |
| FrontierMath (Tiers 1-3) | 0.4% | — |
| OTIS Mock AIME 2024-2025 | 6.4% | — |
| Omni-MATH | 29.3% | — |
| LiveBench Math | 49.5% | — |
| MATH Level 5 | 53.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Yi-Lightning leads
GPT-4o: 28.8 (#242), Yi-Lightning: 35.4 (#185)
| Benchmark | GPT-4o | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1250 | 1286 |
| GPQA Diamond | 49.2% | — |
| Humanity's Last Exam | 2.7% | — |
| SimpleQA Verified | 26% | — |
| MMLU-Pro | 71.3% | — |
| Confabulations | 15.3% | — |
| Vectara Hallucination Rate | 9.6% | — |
| GPQA (HELM) | 52% | — |
| MMLU | 88.1% | — |
Multimodal Not comparable
GPT-4o: 34.5 (#91), Yi-Lightning: —
| Benchmark | GPT-4o | Yi-Lightning |
|---|---|---|
| LMArena Vision | 1137 | — |
| Video-MME | 71.9% | — |
| GeoBench | 71% | — |
| VPCT | 40% | — |
| ScienceQA | 88.5% | — |
Multilingual Too close to call
GPT-4o: 43.2 (#186), Yi-Lightning: 42.2 (#196)
| Benchmark | GPT-4o | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1283 | 1269 |
| LMArena Chinese | 1277 | 1320 |
| LMArena French | 1304 | 1305 |
| LMArena German | 1282 | 1267 |
| LMArena Japanese | 1257 | 1228 |
| LMArena Korean | 1234 | 1192 |
| LMArena Russian | 1286 | 1255 |
| LMArena Spanish | 1292 | 1315 |
Instruction Following Too close to call
GPT-4o: 66.6 (#207), Yi-Lightning: 67.4 (#196)
| Benchmark | GPT-4o | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1278 | 1278 |
| LiveBench Instruction Following | 68.6% | — |
| IFEval | 81.7% | — |
Long Context Too close to call
GPT-4o: 39.4 (#179), Yi-Lightning: 39.4 (#181)
| Benchmark | GPT-4o | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1289 | 1297 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference GPT-4o leads
GPT-4o: 52.6 (#166), Yi-Lightning: 50.2 (#184)
| Benchmark | GPT-4o | Yi-Lightning |
|---|---|---|
| LMArena Text | 1300 | 1302 |
| LMArena Creative Writing | 1292 | 1280 |
| LMArena Multi-Turn | 1302 | 1311 |
| Short-Story Creative Writing | 81.8% | — |
| WildBench | 82.8% | — |
| LiveBench Language | 47.6% | — |
Frequently asked questions
Is GPT-4o better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 28.6 on the Noometry Index.
Is GPT-4o or Yi-Lightning better for coding?
Yi-Lightning scores higher on coding benchmarks: 27.4 versus 24.8 in the Noometry coding category.
How many benchmarks do GPT-4o and Yi-Lightning share?
18 benchmarks have published results for both models. GPT-4o has 72 scored results on Noometry and Yi-Lightning has 18.