# GLM-5.1 vs Yi-34B

> GLM-5.1 is the stronger model overall, scoring 47.6 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-yi-34b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Yi-34B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.1 leads 55.0 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 89.9% for GLM-5.1 and 14.7% for Yi-34B.

## Snapshot

| | GLM-5.1 | Yi-34B |
|---|---|---|
| Provider | Z.ai (Zhipu) | 01.AI |
| Noometry Index | 47.6 | 27.4 |
| Rank | 51 | 325 |
| Context | 200K | — |
| Input $/M | $1.40 | — |
| Output $/M | $4.40 | — |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.5 (#52)
- Yi-34B: 31.8 (#269)

| Benchmark | GLM-5.1 | Yi-34B |
|---|---|---|
| LMArena Coding | 1486 | 1112 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1509 | — |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- Yi-34B: —

| Benchmark | GLM-5.1 | Yi-34B |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- Yi-34B: 20.3 (#222)

| Benchmark | GLM-5.1 | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1472 | 1104 |
| Epoch Capabilities Index | 149.86 | 117.28 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| BIG-Bench Hard | — | 71.7% |

## Math

- GLM-5.1: 49.0 (#48)
- Yi-34B: 19.8 (#277)

| Benchmark | GLM-5.1 | Yi-34B |
|---|---|---|
| LMArena Math | 1472 | 1114 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| MATH Level 5 | — | 5.1% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
| GSM8K | — | 76% |

## Knowledge

- GLM-5.1: 55.0 (#45)
- Yi-34B: 7.5 (#304)

| Benchmark | GLM-5.1 | Yi-34B |
|---|---|---|
| GPQA Diamond | 89.9% | 14.7% |
| LMArena Expert | 1477 | 1061 |
| SimpleQA Verified | 34% | — |
| MMLU | — | 76.3% |

## Multilingual

- GLM-5.1: 55.2 (#34)
- Yi-34B: 29.9 (#259)

| Benchmark | GLM-5.1 | Yi-34B |
|---|---|---|
| LMArena Non-English | 1448 | 1079 |
| LMArena Chinese | 1516 | 1175 |
| LMArena French | 1478 | 1080 |
| LMArena German | 1466 | 1042 |
| LMArena Japanese | 1436 | 993 |
| LMArena Korean | 1423 | 959 |
| LMArena Russian | 1453 | 1050 |
| LMArena Spanish | 1467 | 1070 |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- Yi-34B: 56.4 (#269)

| Benchmark | GLM-5.1 | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1451 | 1091 |

## Long Context

- GLM-5.1: 44.9 (#51)
- Yi-34B: 33.2 (#259)

| Benchmark | GLM-5.1 | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1467 | 1094 |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- Yi-34B: 34.3 (#268)

| Benchmark | GLM-5.1 | Yi-34B |
|---|---|---|
| LMArena Text | 1462 | 1129 |
| LMArena Creative Writing | 1454 | 1108 |
| LMArena Multi-Turn | 1473 | 1113 |
| EQ-Bench Creative Writing | 1592 | — |

## FAQ

### Is GLM-5.1 better than Yi-34B?

GLM-5.1 is the stronger model overall, scoring 47.6 to 27.4 on the Noometry Index.

### Is GLM-5.1 or Yi-34B better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.5 versus 31.8 in the Noometry coding category.

### How many benchmarks do GLM-5.1 and Yi-34B share?

19 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Yi-34B has 23.