Model comparison
GLM-4.5-Air vs Grok 3
GLM-4.5-Air and Grok 3 score almost the same on the Noometry Index (38.9 vs 39.9), so choose on price, context window or the category you care about most.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. GLM-4.5-Air scores higher in 3 categories and Grok 3 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.2 to 35.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 43% for GLM-4.5-Air and 61.3% for Grok 3.
- GLM-4.5-Air has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5-Air | Grok 3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 38.9 | 39.9 |
| Released | 2025-07-20 | 2025-04-09 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.10 | — |
| Results tracked | 27 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
GLM-4.5-Air: 33.3 (#259), Grok 3: 41.9 (#115)
| Benchmark | GLM-4.5-Air | Grok 3 |
|---|---|---|
| LMArena Coding | 1397 | 1432 |
| Aider Polyglot | — | 53.3% |
| GSO | 2.9% | — |
| WeirdML | — | 37.2% |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, Grok 3: 30.5 (#76)
| Benchmark | GLM-4.5-Air | Grok 3 |
|---|---|---|
| BALROG | — | 29.5% |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 24.1 (#166), Grok 3: 13.7 (#333)
| Benchmark | GLM-4.5-Air | Grok 3 |
|---|---|---|
| Kagi LLM Benchmark | 43% | 61.3% |
| LMArena Hard Prompts | 1379 | 1434 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 36.1% |
| ARC-AGI-1 | — | 5.5% |
| Epoch Capabilities Index | — | 138.33 |
| ForecastBench | 59.2 | — |
Math Grok 3 leads
GLM-4.5-Air: 36.2 (#170), Grok 3: 38.0 (#145)
| Benchmark | GLM-4.5-Air | Grok 3 |
|---|---|---|
| Omni-MATH | 39.1% | 46.4% |
| LMArena Math | 1396 | 1391 |
| OTIS Mock AIME 2024-2025 | — | 55.6% |
| MATH Level 5 | — | 88.7% |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Grok 3 leads
GLM-4.5-Air: 35.0 (#191), Grok 3: 46.2 (#82)
| Benchmark | GLM-4.5-Air | Grok 3 |
|---|---|---|
| MMLU-Pro | 76.2% | 78.8% |
| Vectara Hallucination Rate | 9.3% | 5.8% |
| GPQA (HELM) | 59.4% | 65% |
| LMArena Expert | 1370 | 1421 |
| GPQA Diamond | — | 75.8% |
| Humanity's Last Exam | 8.1% | — |
| Confabulations | — | 14.2% |
Multilingual Grok 3 leads
GLM-4.5-Air: 49.1 (#135), Grok 3: 52.3 (#87)
| Benchmark | GLM-4.5-Air | Grok 3 |
|---|---|---|
| LMArena Non-English | 1366 | 1410 |
| LMArena Chinese | 1426 | 1448 |
| LMArena French | 1399 | 1460 |
| LMArena German | 1377 | 1431 |
| LMArena Japanese | 1348 | 1387 |
| LMArena Korean | 1308 | 1373 |
| LMArena Russian | 1373 | 1416 |
| LMArena Spanish | 1386 | 1417 |
Instruction Following Grok 3 leads
GLM-4.5-Air: 69.6 (#171), Grok 3: 75.0 (#73)
| Benchmark | GLM-4.5-Air | Grok 3 |
|---|---|---|
| IFEval | 81.2% | 88.4% |
| LMArena Instruction Following | 1354 | 1409 |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Grok 3: 38.7 (#192)
| Benchmark | GLM-4.5-Air | Grok 3 |
|---|---|---|
| LMArena Longer Query | 1366 | 1439 |
| Fiction.LiveBench | — | 58.3% |
Writing & Preference Too close to call
GLM-4.5-Air: 55.9 (#139), Grok 3: 55.8 (#141)
| Benchmark | GLM-4.5-Air | Grok 3 |
|---|---|---|
| LMArena Text | 1384 | 1426 |
| LMArena Creative Writing | 1343 | 1414 |
| WildBench | 78.9% | 84.9% |
| LMArena Multi-Turn | 1371 | 1425 |
| Short-Story Creative Writing | — | 76.4% |
| EQ-Bench Creative Writing | — | 1186 |
Frequently asked questions
Is GLM-4.5-Air better than Grok 3?
GLM-4.5-Air and Grok 3 score almost the same on the Noometry Index (38.9 vs 39.9), so choose on price, context window or the category you care about most.
Is GLM-4.5-Air or Grok 3 better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 33.3 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Grok 3 share?
24 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Grok 3 has 40.