Model comparison
GLM-5.3 vs Olmo 2 0325 32b Instruct
GLM-5.3 is the stronger model overall, scoring 54.6 to 32.2 on the Noometry Index.
Last verified . 11 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. GLM-5.3 scores higher in 8 categories and Olmo 2 0325 32b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.3 leads 58.3 to 19.2.
Side by side
| GLM-5.3 | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Allen Institute for AI (Ai2) |
| Noometry Index | 54.6 | 32.2 |
| Released | 2026-08-14 | — |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 41 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3 leads
GLM-5.3: 59.0 (#12), Olmo 2 0325 32b Instruct: 34.6 (#222)
| Benchmark | GLM-5.3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1499 | 1210 |
| DeepSWE | 69% | — |
| FrontierCode | 40.1% | — |
| LMArena WebDev | 1623 | — |
| FrontierSWE | 30.2% | — |
| SciCode | 59% | — |
| WeirdML | 75.4% | — |
| ALE-Bench | 1,317 | — |
Agentic & Tool Use Not comparable
GLM-5.3: 36.3 (#34), Olmo 2 0325 32b Instruct: —
| Benchmark | GLM-5.3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| APEX-Agents | 56.6% | — |
| Vending-Bench 2 | 8,164 | — |
Reasoning GLM-5.3 leads
GLM-5.3: 45.2 (#42), Olmo 2 0325 32b Instruct: 22.6 (#174)
| Benchmark | GLM-5.3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1491 | 1208 |
| 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 | — |
| Epoch Capabilities Index | 155.56 | — |
Math GLM-5.3 leads
GLM-5.3: 62.1 (#27), Olmo 2 0325 32b Instruct: 24.8 (#255)
| Benchmark | GLM-5.3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Math | 1493 | 1208 |
| FrontierMath (Tiers 1-3) | 68.8% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 91.1% | — |
| ProofBench | 49% | — |
| Omni-MATH | — | 16.1% |
Knowledge GLM-5.3 leads
GLM-5.3: 58.3 (#34), Olmo 2 0325 32b Instruct: 19.2 (#274)
| Benchmark | GLM-5.3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| GPQA Diamond | 90.9% | — |
| SimpleQA Verified | 41% | — |
| MMLU-Pro | — | 41.4% |
| GPQA (HELM) | — | 28.7% |
| LMArena Expert | 1512 | — |
Multilingual GLM-5.3 leads
GLM-5.3: 55.9 (#27), Olmo 2 0325 32b Instruct: 35.0 (#243)
| Benchmark | GLM-5.3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1457 | 1160 |
| LMArena Chinese | 1523 | 1192 |
| LMArena Russian | 1460 | 1187 |
| LMArena French | 1499 | — |
| LMArena German | 1505 | — |
| LMArena Japanese | 1438 | — |
| LMArena Korean | 1478 | — |
| LMArena Spanish | 1444 | — |
Instruction Following GLM-5.3 leads
GLM-5.3: 77.8 (#15), Olmo 2 0325 32b Instruct: 61.8 (#238)
| Benchmark | GLM-5.3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1481 | 1186 |
| IFEval | — | 78% |
Long Context GLM-5.3 leads
GLM-5.3: 45.5 (#32), Olmo 2 0325 32b Instruct: 36.2 (#229)
| Benchmark | GLM-5.3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1485 | 1194 |
Writing & Preference GLM-5.3 leads
GLM-5.3: 75.9 (#6), Olmo 2 0325 32b Instruct: 42.3 (#231)
| Benchmark | GLM-5.3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1473 | 1218 |
| LMArena Creative Writing | 1459 | 1199 |
| LMArena Multi-Turn | 1473 | 1221 |
| EQ-Bench Creative Writing | 2075 | — |
| WildBench | — | 73.4% |
Frequently asked questions
Is GLM-5.3 better than Olmo 2 0325 32b Instruct?
GLM-5.3 is the stronger model overall, scoring 54.6 to 32.2 on the Noometry Index.
Is GLM-5.3 or Olmo 2 0325 32b Instruct better for coding?
GLM-5.3 scores higher on coding benchmarks: 59.0 versus 34.6 in the Noometry coding category.
How many benchmarks do GLM-5.3 and Olmo 2 0325 32b Instruct share?
11 benchmarks have published results for both models. GLM-5.3 has 41 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.