# GPT-5.6 Luna vs Yi-34B

> GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 27.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-6-luna-vs-yi-34b
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. GPT-5.6 Luna scores higher in 8 categories and Yi-34B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 21.6.
- The biggest single-benchmark swing is GPQA Diamond: 91.6% for GPT-5.6 Luna and 14.7% for Yi-34B.
- Yi-34B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.6 Luna | Yi-34B |
|---|---|---|
| Provider | OpenAI | 01.AI |
| Noometry Index | 54.6 | 27.8 |
| Rank | 30 | 329 |
| Context | 1.05M | — |
| Input $/M | $0.20 | — |
| Output $/M | $1.20 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.6 Luna: 54.5 (#28)
- Yi-34B: 32.3 (#274)

| Benchmark | GPT-5.6 Luna | Yi-34B |
|---|---|---|
| LMArena Coding | 1466 | 1112 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| LMArena WebDev | 1519 | — |
| SciCode | 53.6% | — |
| WeirdML | 60.9% | — |
| ALE-Bench | 1,667 | — |

## Agentic & Tool Use

- GPT-5.6 Luna: 34.4 (#45)
- Yi-34B: —

| Benchmark | GPT-5.6 Luna | Yi-34B |
|---|---|---|
| APEX-Agents | 43% | — |
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |

## Reasoning

- GPT-5.6 Luna: 47.6 (#43)
- Yi-34B: 21.2 (#226)

| Benchmark | GPT-5.6 Luna | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1104 |
| Epoch Capabilities Index | 156.39 | 117.39 |
| ARC-AGI-2 | 59.5% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 49.1% | — |
| NYT Connections (extended) | 69.4% | — |
| ARC-AGI-1 | 88% | — |
| CritPt | 20.6% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 21% | — |
| DTBench | 89.1% | — |
| LMCA | 48.5% | — |
| Surface Evolver Bench | 61.9% | — |
| BIG-Bench Hard | — | 71.7% |

## Math

- GPT-5.6 Luna: 77.7 (#14)
- Yi-34B: 21.6 (#282)

| Benchmark | GPT-5.6 Luna | Yi-34B |
|---|---|---|
| LMArena Math | 1458 | 1114 |
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 60% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |

## Knowledge

- GPT-5.6 Luna: 58.5 (#34)
- Yi-34B: 7.5 (#309)

| Benchmark | GPT-5.6 Luna | Yi-34B |
|---|---|---|
| GPQA Diamond | 91.6% | 14.7% |
| LMArena Expert | 1478 | 1061 |
| SimpleQA Verified | 41% | — |
| MMLU | — | 76.3% |

## Multimodal

- GPT-5.6 Luna: 42.7 (#28)
- Yi-34B: —

| Benchmark | GPT-5.6 Luna | Yi-34B |
|---|---|---|
| LMArena Vision | 1258 | — |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |

## Multilingual

- GPT-5.6 Luna: 52.8 (#78)
- Yi-34B: 29.7 (#264)

| Benchmark | GPT-5.6 Luna | Yi-34B |
|---|---|---|
| LMArena Non-English | 1417 | 1079 |
| LMArena Chinese | 1470 | 1176 |
| LMArena French | 1456 | 1081 |
| LMArena German | 1454 | 1042 |
| LMArena Japanese | 1411 | 993 |
| LMArena Korean | 1415 | 959 |
| LMArena Russian | 1428 | 1050 |
| LMArena Spanish | 1448 | 1070 |

## Instruction Following

- GPT-5.6 Luna: 75.6 (#57)
- Yi-34B: 56.2 (#274)

| Benchmark | GPT-5.6 Luna | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1437 | 1091 |

## Long Context

- GPT-5.6 Luna: 43.9 (#82)
- Yi-34B: 33.2 (#264)

| Benchmark | GPT-5.6 Luna | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1436 | 1094 |

## Writing & Preference

- GPT-5.6 Luna: 68.0 (#29)
- Yi-34B: 34.1 (#273)

| Benchmark | GPT-5.6 Luna | Yi-34B |
|---|---|---|
| LMArena Text | 1431 | 1129 |
| LMArena Creative Writing | 1396 | 1108 |
| LMArena Multi-Turn | 1434 | 1113 |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |

## FAQ

### Is GPT-5.6 Luna better than Yi-34B?

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 27.8 on the Noometry Index.

### Is GPT-5.6 Luna or Yi-34B better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 32.3 in the Noometry coding category.

### How many benchmarks do GPT-5.6 Luna and Yi-34B share?

19 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and Yi-34B has 23.