# GPT-5.4 mini vs Yi-Lightning

> GPT-5.4 mini is the stronger model overall, scoring 44.8 to 36.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-4-mini-vs-yi-lightning
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GPT-5.4 mini scores higher in 8 categories and Yi-Lightning in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-5.4 mini leads 45.0 to 27.0.

## Snapshot

| | GPT-5.4 mini | Yi-Lightning |
|---|---|---|
| Provider | OpenAI | 01.AI |
| Noometry Index | 44.8 | 36.5 |
| Rank | 69 | 206 |
| Context | 400K | — |
| Input $/M | $0.75 | — |
| Output $/M | $4.50 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.4 mini: 45.0 (#67)
- Yi-Lightning: 27.0 (#315)

| Benchmark | GPT-5.4 mini | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1438 | 1313 |
| FrontierCode | 27% | — |
| Aider Polyglot | — | 12.9% |
| LMArena WebDev | 1397 | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |
| ALE-Bench | 1,189 | — |

## Agentic & Tool Use

- GPT-5.4 mini: 29.6 (#74)
- Yi-Lightning: —

| Benchmark | GPT-5.4 mini | Yi-Lightning |
|---|---|---|
| DeepResearch Bench | 36.3% | — |

## Reasoning

- GPT-5.4 mini: 30.3 (#77)
- Yi-Lightning: 24.9 (#137)

| Benchmark | GPT-5.4 mini | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1302 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| NYT Connections (extended) | 61.8% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| Epoch Capabilities Index | 148.83 | — |
| ForecastBench | 57 | — |

## Math

- GPT-5.4 mini: 45.4 (#63)
- Yi-Lightning: 33.5 (#173)

| Benchmark | GPT-5.4 mini | Yi-Lightning |
|---|---|---|
| LMArena Math | 1418 | 1300 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GPT-5.4 mini: 51.4 (#62)
- Yi-Lightning: 34.8 (#182)

| Benchmark | GPT-5.4 mini | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1434 | 1286 |
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |

## Multimodal

- GPT-5.4 mini: 39.0 (#51)
- Yi-Lightning: —

| Benchmark | GPT-5.4 mini | Yi-Lightning |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- GPT-5.4 mini: 52.1 (#94)
- Yi-Lightning: 42.4 (#191)

| Benchmark | GPT-5.4 mini | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1405 | 1269 |
| LMArena Chinese | 1446 | 1320 |
| LMArena French | 1440 | 1304 |
| LMArena German | 1407 | 1267 |
| LMArena Japanese | 1375 | 1228 |
| LMArena Korean | 1369 | 1192 |
| LMArena Russian | 1417 | 1255 |
| LMArena Spanish | 1403 | 1315 |

## Instruction Following

- GPT-5.4 mini: 74.3 (#99)
- Yi-Lightning: 67.6 (#191)

| Benchmark | GPT-5.4 mini | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1405 | 1278 |

## Long Context

- GPT-5.4 mini: 42.9 (#107)
- Yi-Lightning: 39.4 (#176)

| Benchmark | GPT-5.4 mini | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1407 | 1297 |

## Writing & Preference

- GPT-5.4 mini: 64.2 (#56)
- Yi-Lightning: 50.4 (#178)

| Benchmark | GPT-5.4 mini | Yi-Lightning |
|---|---|---|
| LMArena Text | 1411 | 1302 |
| LMArena Creative Writing | 1370 | 1280 |
| LMArena Multi-Turn | 1429 | 1311 |
| EQ-Bench Creative Writing | 1665 | — |

## FAQ

### Is GPT-5.4 mini better than Yi-Lightning?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 36.5 on the Noometry Index.

### Is GPT-5.4 mini or Yi-Lightning better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 27.0 in the Noometry coding category.

### How many benchmarks do GPT-5.4 mini and Yi-Lightning share?

17 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Yi-Lightning has 18.