# GPT-5.6 Terra vs Yi-Lightning

> GPT-5.6 Terra is the stronger model overall, scoring 59.1 to 36.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-6-terra-vs-yi-lightning
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GPT-5.6 Terra scores higher in 8 categories and Yi-Lightning in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Terra leads 81.5 to 33.5.

## Snapshot

| | GPT-5.6 Terra | Yi-Lightning |
|---|---|---|
| Provider | OpenAI | 01.AI |
| Noometry Index | 59.1 | 36.5 |
| Rank | 15 | 206 |
| Context | 1.05M | — |
| Input $/M | $2 | — |
| Output $/M | $12 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.6 Terra: 57.1 (#16)
- Yi-Lightning: 27.0 (#315)

| Benchmark | GPT-5.6 Terra | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1484 | 1313 |
| DeepSWE | 69.6% | — |
| FrontierCode | 41.3% | — |
| Aider Polyglot | — | 12.9% |
| CursorBench | 41.3% | — |
| LMArena WebDev | 1520 | — |
| SciCode | 55% | — |
| WeirdML | 78.3% | — |
| ALE-Bench | 1,951 | — |

## Agentic & Tool Use

- GPT-5.6 Terra: 40.2 (#23)
- Yi-Lightning: —

| Benchmark | GPT-5.6 Terra | Yi-Lightning |
|---|---|---|
| APEX-Agents | 58.2% | — |
| BALROG | 53.2% | — |
| GDP.pdf | 24.7% | — |
| Vending-Bench 2 | 7,343 | — |

## Reasoning

- GPT-5.6 Terra: 60.6 (#19)
- Yi-Lightning: 24.9 (#137)

| Benchmark | GPT-5.6 Terra | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1467 | 1302 |
| ARC-AGI-2 | 83.9% | — |
| SimpleBench | 48.9% | — |
| Kagi LLM Benchmark | 51.3% | — |
| NYT Connections (extended) | 78.4% | — |
| ARC-AGI-1 | 96.5% | — |
| CritPt | 30% | — |
| Chess Puzzles | 54% | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 93.3% | — |
| LMCA | 55% | — |
| Surface Evolver Bench | 83.8% | — |
| Epoch Capabilities Index | 159.31 | — |

## Math

- GPT-5.6 Terra: 81.5 (#10)
- Yi-Lightning: 33.5 (#173)

| Benchmark | GPT-5.6 Terra | Yi-Lightning |
|---|---|---|
| LMArena Math | 1463 | 1300 |
| FrontierMath (Tiers 1-3) | 86% | — |
| FrontierMath Tier 4 | 70.7% | — |
| OTIS Mock AIME 2024-2025 | 99.7% | — |
| ProofBench | 74% | — |

## Knowledge

- GPT-5.6 Terra: 61.3 (#27)
- Yi-Lightning: 34.8 (#182)

| Benchmark | GPT-5.6 Terra | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1492 | 1286 |
| GPQA Diamond | 93.3% | — |
| SimpleQA Verified | 43.2% | — |

## Multimodal

- GPT-5.6 Terra: 47.5 (#10)
- Yi-Lightning: —

| Benchmark | GPT-5.6 Terra | Yi-Lightning |
|---|---|---|
| LMArena Vision | 1271 | — |
| Blueprint-Bench 2 | 30.8% | — |
| Furniture Assembly | 54.2% | — |
| LMArena Document | 1472 | — |

## Multilingual

- GPT-5.6 Terra: 54.5 (#42)
- Yi-Lightning: 42.4 (#191)

| Benchmark | GPT-5.6 Terra | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1439 | 1269 |
| LMArena Chinese | 1514 | 1320 |
| LMArena French | 1476 | 1304 |
| LMArena German | 1462 | 1267 |
| LMArena Japanese | 1446 | 1228 |
| LMArena Korean | 1420 | 1192 |
| LMArena Russian | 1450 | 1255 |
| LMArena Spanish | 1455 | 1315 |

## Instruction Following

- GPT-5.6 Terra: 76.6 (#38)
- Yi-Lightning: 67.6 (#191)

| Benchmark | GPT-5.6 Terra | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1453 | 1278 |

## Long Context

- GPT-5.6 Terra: 44.4 (#64)
- Yi-Lightning: 39.4 (#176)

| Benchmark | GPT-5.6 Terra | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1452 | 1297 |

## Writing & Preference

- GPT-5.6 Terra: 70.4 (#21)
- Yi-Lightning: 50.4 (#178)

| Benchmark | GPT-5.6 Terra | Yi-Lightning |
|---|---|---|
| LMArena Text | 1446 | 1302 |
| LMArena Creative Writing | 1411 | 1280 |
| LMArena Multi-Turn | 1451 | 1311 |
| EQ-Bench Creative Writing | 1855 | — |
| EQ-Bench 4 | 1234 | — |

## FAQ

### Is GPT-5.6 Terra better than Yi-Lightning?

GPT-5.6 Terra is the stronger model overall, scoring 59.1 to 36.5 on the Noometry Index.

### Is GPT-5.6 Terra or Yi-Lightning better for coding?

GPT-5.6 Terra scores higher on coding benchmarks: 57.1 versus 27.0 in the Noometry coding category.

### How many benchmarks do GPT-5.6 Terra and Yi-Lightning share?

17 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Yi-Lightning has 18.