# GPT-5 Nano vs Yi-Lightning

> Yi-Lightning is the stronger model overall, scoring 37.1 to 33.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-nano-vs-yi-lightning
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. GPT-5 Nano scores higher in 4 categories and Yi-Lightning in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Yi-Lightning leads 50.2 to 39.1.

## Snapshot

| | GPT-5 Nano | Yi-Lightning |
|---|---|---|
| Provider | OpenAI | 01.AI |
| Noometry Index | 33.5 | 37.1 |
| Rank | 241 | 209 |
| Context | 400K | — |
| Input $/M | $0.05 | — |
| Output $/M | $0.40 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5 Nano: 33.6 (#254)
- Yi-Lightning: 27.4 (#320)

| Benchmark | GPT-5 Nano | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1351 | 1312 |
| SWE-bench Verified (bash only) | 34.8% | — |
| Aider Polyglot | — | 12.9% |
| WeirdML | 38.1% | — |
| ALE-Bench | 718.67 | — |

## Agentic & Tool Use

- GPT-5 Nano: 25.8 (#106)
- Yi-Lightning: —

| Benchmark | GPT-5 Nano | Yi-Lightning |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |

## Reasoning

- GPT-5 Nano: 16.3 (#306)
- Yi-Lightning: 25.9 (#139)

| Benchmark | GPT-5 Nano | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1328 | 1302 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| Epoch Capabilities Index | 139.38 | — |
| ForecastBench | 59.1 | — |

## Math

- GPT-5 Nano: 29.4 (#241)
- Yi-Lightning: 36.2 (#172)

| Benchmark | GPT-5 Nano | Yi-Lightning |
|---|---|---|
| LMArena Math | 1317 | 1300 |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GPT-5 Nano: 35.9 (#178)
- Yi-Lightning: 35.4 (#185)

| Benchmark | GPT-5 Nano | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1321 | 1286 |
| GPQA Diamond | 69.4% | — |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |

## Multimodal

- GPT-5 Nano: 31.3 (#108)
- Yi-Lightning: —

| Benchmark | GPT-5 Nano | Yi-Lightning |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |

## Multilingual

- GPT-5 Nano: 45.3 (#172)
- Yi-Lightning: 42.2 (#196)

| Benchmark | GPT-5 Nano | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1313 | 1269 |
| LMArena Chinese | 1356 | 1320 |
| LMArena German | 1327 | 1267 |
| LMArena Japanese | 1226 | 1228 |
| LMArena Korean | 1269 | 1192 |
| LMArena Russian | 1296 | 1255 |
| LMArena Spanish | 1360 | 1315 |
| LMArena French | — | 1305 |

## Instruction Following

- GPT-5 Nano: 75.0 (#79)
- Yi-Lightning: 67.4 (#196)

| Benchmark | GPT-5 Nano | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1306 | 1278 |
| IFEval | 93.2% | — |

## Long Context

- GPT-5 Nano: 31.3 (#281)
- Yi-Lightning: 39.4 (#181)

| Benchmark | GPT-5 Nano | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1312 | 1297 |
| Fiction.LiveBench | 44.4% | — |

## Writing & Preference

- GPT-5 Nano: 39.1 (#249)
- Yi-Lightning: 50.2 (#184)

| Benchmark | GPT-5 Nano | Yi-Lightning |
|---|---|---|
| LMArena Text | 1320 | 1302 |
| LMArena Creative Writing | 1249 | 1280 |
| LMArena Multi-Turn | 1311 | 1311 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |

## FAQ

### Is GPT-5 Nano better than Yi-Lightning?

Yi-Lightning is the stronger model overall, scoring 37.1 to 33.5 on the Noometry Index.

### Is GPT-5 Nano or Yi-Lightning better for coding?

GPT-5 Nano scores higher on coding benchmarks: 33.6 versus 27.4 in the Noometry coding category.

### How many benchmarks do GPT-5 Nano and Yi-Lightning share?

16 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Yi-Lightning has 18.