Model comparison
GLM-5.3 vs Yi-34B
GLM-5.3 is the stronger model overall, scoring 54.8 to 27.8 on the Noometry Index.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. GLM-5.3 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-5.3 leads 58.3 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 90.9% for GLM-5.3 and 14.7% for Yi-34B.
Side by side
| GLM-5.3 | Yi-34B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | 01.AI |
| Noometry Index | 54.8 | 27.8 |
| Released | 2026-08-14 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 42 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3 leads
GLM-5.3: 59.5 (#14), Yi-34B: 32.3 (#274)
| Benchmark | GLM-5.3 | Yi-34B |
|---|---|---|
| LMArena Coding | 1496 | 1112 |
| DeepSWE | 69% | — |
| FrontierCode | 40.1% | — |
| CursorBench | 42.6% | — |
| LMArena WebDev | 1622 | — |
| FrontierSWE | 30.2% | — |
| SciCode | 59% | — |
| WeirdML | 75.4% | — |
| ALE-Bench | 1,317 | — |
Agentic & Tool Use Not comparable
GLM-5.3: 36.4 (#38), Yi-34B: —
| Benchmark | GLM-5.3 | Yi-34B |
|---|---|---|
| APEX-Agents | 56.6% | — |
| Vending-Bench 2 | 8,164 | — |
Reasoning GLM-5.3 leads
GLM-5.3: 46.1 (#46), Yi-34B: 21.2 (#226)
| Benchmark | GLM-5.3 | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1489 | 1104 |
| Epoch Capabilities Index | 155.61 | 117.39 |
| NYT Connections (extended) | 74.2% | — |
| CritPt | 19.1% | — |
| Chess Puzzles | 21% | — |
| Mystery Game Puzzles | 33% | — |
| DTBench | 87.7% | — |
| LMCA | 55.5% | — |
| Bench to the Future 3 | 0.15 | — |
| BIG-Bench Hard | — | 71.7% |
Math GLM-5.3 leads
GLM-5.3: 62.3 (#33), Yi-34B: 21.6 (#282)
| Benchmark | GLM-5.3 | Yi-34B |
|---|---|---|
| LMArena Math | 1489 | 1114 |
| FrontierMath (Tiers 1-3) | 68.8% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 91.1% | — |
| ProofBench | 49% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge GLM-5.3 leads
GLM-5.3: 58.3 (#37), Yi-34B: 7.5 (#309)
| Benchmark | GLM-5.3 | Yi-34B |
|---|---|---|
| GPQA Diamond | 90.9% | 14.7% |
| LMArena Expert | 1516 | 1061 |
| SimpleQA Verified | 41% | — |
| MMLU | — | 76.3% |
Multilingual GLM-5.3 leads
GLM-5.3: 55.7 (#28), Yi-34B: 29.7 (#264)
| Benchmark | GLM-5.3 | Yi-34B |
|---|---|---|
| LMArena Non-English | 1457 | 1079 |
| LMArena Chinese | 1528 | 1176 |
| LMArena French | 1499 | 1081 |
| LMArena German | 1499 | 1042 |
| LMArena Japanese | 1453 | 993 |
| LMArena Korean | 1472 | 959 |
| LMArena Russian | 1463 | 1050 |
| LMArena Spanish | 1460 | 1070 |
Instruction Following GLM-5.3 leads
GLM-5.3: 77.5 (#23), Yi-34B: 56.2 (#274)
| Benchmark | GLM-5.3 | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1477 | 1091 |
Long Context GLM-5.3 leads
GLM-5.3: 45.4 (#41), Yi-34B: 33.2 (#264)
| Benchmark | GLM-5.3 | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1482 | 1094 |
Writing & Preference GLM-5.3 leads
GLM-5.3: 75.7 (#6), Yi-34B: 34.1 (#273)
| Benchmark | GLM-5.3 | Yi-34B |
|---|---|---|
| LMArena Text | 1471 | 1129 |
| LMArena Creative Writing | 1457 | 1108 |
| LMArena Multi-Turn | 1472 | 1113 |
| EQ-Bench Creative Writing | 2075 | — |
Frequently asked questions
Is GLM-5.3 better than Yi-34B?
GLM-5.3 is the stronger model overall, scoring 54.8 to 27.8 on the Noometry Index.
Is GLM-5.3 or Yi-34B better for coding?
GLM-5.3 scores higher on coding benchmarks: 59.5 versus 32.3 in the Noometry coding category.
How many benchmarks do GLM-5.3 and Yi-34B share?
19 benchmarks have published results for both models. GLM-5.3 has 42 scored results on Noometry and Yi-34B has 23.