Model comparison
GLM-5.3-Flash vs Yi-34B
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 27.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. GLM-5.3-Flash 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-Flash leads 58.4 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 90.2% for GLM-5.3-Flash and 14.7% for Yi-34B.
Side by side
| GLM-5.3-Flash | Yi-34B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | 01.AI |
| Noometry Index | 49.6 | 27.4 |
| Released | 2026-08-20 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.50 | — |
| Results tracked | 36 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
GLM-5.3-Flash: 53.7 (#26), Yi-34B: 31.8 (#269)
| Benchmark | GLM-5.3-Flash | Yi-34B |
|---|---|---|
| LMArena Coding | 1506 | 1112 |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| LMArena WebDev | 1614 | — |
| SciCode | 51.6% | — |
| ALE-Bench | 303.55 | — |
Agentic & Tool Use Not comparable
GLM-5.3-Flash: 34.3 (#41), Yi-34B: —
| Benchmark | GLM-5.3-Flash | Yi-34B |
|---|---|---|
| APEX-Agents | 52.8% | — |
| GDP.pdf | 14% | — |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 31.7 (#69), Yi-34B: 20.3 (#222)
| Benchmark | GLM-5.3-Flash | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1490 | 1104 |
| Epoch Capabilities Index | 151.9 | 117.28 |
| CritPt | 15.4% | — |
| Chess Puzzles | 14% | — |
| Mystery Game Puzzles | 8% | — |
| Surface Evolver Bench | 52.5% | — |
| Bench to the Future 3 | 0.15 | — |
| BIG-Bench Hard | — | 71.7% |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.1 (#38), Yi-34B: 19.8 (#277)
| Benchmark | GLM-5.3-Flash | Yi-34B |
|---|---|---|
| LMArena Math | 1499 | 1114 |
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 93.9% | — |
| ProofBench | 21% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#33), Yi-34B: 7.5 (#304)
| Benchmark | GLM-5.3-Flash | Yi-34B |
|---|---|---|
| GPQA Diamond | 90.2% | 14.7% |
| LMArena Expert | 1512 | 1061 |
| MMLU | — | 76.3% |
Multimodal Not comparable
GLM-5.3-Flash: 42.6 (#25), Yi-34B: —
| Benchmark | GLM-5.3-Flash | Yi-34B |
|---|---|---|
| LMArena Vision | 1304 | — |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.2 (#24), Yi-34B: 29.9 (#259)
| Benchmark | GLM-5.3-Flash | Yi-34B |
|---|---|---|
| LMArena Non-English | 1462 | 1079 |
| LMArena Chinese | 1529 | 1175 |
| LMArena French | 1495 | 1080 |
| LMArena German | 1457 | 1042 |
| LMArena Japanese | 1420 | 993 |
| LMArena Korean | 1443 | 959 |
| LMArena Russian | 1472 | 1050 |
| LMArena Spanish | 1471 | 1070 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.8 (#17), Yi-34B: 56.4 (#269)
| Benchmark | GLM-5.3-Flash | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1480 | 1091 |
Long Context GLM-5.3-Flash leads
GLM-5.3-Flash: 45.3 (#41), Yi-34B: 33.2 (#259)
| Benchmark | GLM-5.3-Flash | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1479 | 1094 |
Writing & Preference GLM-5.3-Flash leads
GLM-5.3-Flash: 65.4 (#49), Yi-34B: 34.3 (#268)
| Benchmark | GLM-5.3-Flash | Yi-34B |
|---|---|---|
| LMArena Text | 1471 | 1129 |
| LMArena Creative Writing | 1440 | 1108 |
| LMArena Multi-Turn | 1471 | 1113 |
Frequently asked questions
Is GLM-5.3-Flash better than Yi-34B?
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 27.4 on the Noometry Index.
Is GLM-5.3-Flash or Yi-34B better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.7 versus 31.8 in the Noometry coding category.
How many benchmarks do GLM-5.3-Flash and Yi-34B share?
19 benchmarks have published results for both models. GLM-5.3-Flash has 36 scored results on Noometry and Yi-34B has 23.