Model comparison
GLM-4.5-Air vs Olmo 3 32b Think
GLM-4.5-Air and Olmo 3 32b Think score almost the same on the Noometry Index (38.9 vs 38.7), so choose on price, context window or the category you care about most.
Last verified . 14 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. GLM-4.5-Air scores higher in 4 categories and Olmo 3 32b Think in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GLM-4.5-Air leads 49.1 to 41.2.
Side by side
| GLM-4.5-Air | Olmo 3 32b Think | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Allen Institute for AI (Ai2) |
| Noometry Index | 38.9 | 38.7 |
| Released | 2025-07-20 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.10 | — |
| Results tracked | 27 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3 32b Think leads
GLM-4.5-Air: 33.3 (#259), Olmo 3 32b Think: 38.6 (#172)
| Benchmark | GLM-4.5-Air | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1397 | 1319 |
| GSO | 2.9% | — |
Reasoning Olmo 3 32b Think leads
GLM-4.5-Air: 24.1 (#166), Olmo 3 32b Think: 25.9 (#140)
| Benchmark | GLM-4.5-Air | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1302 |
| Kagi LLM Benchmark | 43% | — |
| ForecastBench | 59.2 | — |
Math Too close to call
GLM-4.5-Air: 36.2 (#170), Olmo 3 32b Think: 36.5 (#165)
| Benchmark | GLM-4.5-Air | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1396 | 1316 |
| Omni-MATH | 39.1% | — |
Knowledge Too close to call
GLM-4.5-Air: 35.0 (#191), Olmo 3 32b Think: 35.0 (#190)
| Benchmark | GLM-4.5-Air | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1370 | 1273 |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.1 (#135), Olmo 3 32b Think: 41.2 (#210)
| Benchmark | GLM-4.5-Air | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1366 | 1255 |
| LMArena Chinese | 1426 | 1300 |
| LMArena French | 1399 | 1291 |
| LMArena German | 1377 | 1290 |
| LMArena Russian | 1373 | 1254 |
| LMArena Japanese | 1348 | — |
| LMArena Korean | 1308 | — |
| LMArena Spanish | 1386 | — |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.6 (#171), Olmo 3 32b Think: 67.2 (#198)
| Benchmark | GLM-4.5-Air | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1354 | 1275 |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Olmo 3 32b Think: 39.4 (#182)
| Benchmark | GLM-4.5-Air | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1366 | 1296 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Olmo 3 32b Think: 49.1 (#193)
| Benchmark | GLM-4.5-Air | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1384 | 1300 |
| LMArena Creative Writing | 1343 | 1256 |
| LMArena Multi-Turn | 1371 | 1290 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Olmo 3 32b Think?
GLM-4.5-Air and Olmo 3 32b Think score almost the same on the Noometry Index (38.9 vs 38.7), so choose on price, context window or the category you care about most.
Is GLM-4.5-Air or Olmo 3 32b Think better for coding?
Olmo 3 32b Think scores higher on coding benchmarks: 38.6 versus 33.3 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Olmo 3 32b Think share?
14 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Olmo 3 32b Think has 14.