Model comparison
GLM-4.5 vs Grok-3 mini
GLM-4.5 and Grok-3 mini score almost the same on the Noometry Index (41.4 vs 41.0), so choose on price, context window or the category you care about most.
Last verified . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. GLM-4.5 scores higher in 4 categories and Grok-3 mini in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.5 leads 27.7 to 13.8.
- The biggest single-benchmark swing is Fiction.LiveBench: 58.3% for GLM-4.5 and 66.7% for Grok-3 mini.
- GLM-4.5 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5 | Grok-3 mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 41.4 | 41.0 |
| Released | 2025-07-27 | 2025-04-09 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 27 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.5: 41.1 (#121), Grok-3 mini: 40.4 (#126)
| Benchmark | GLM-4.5 | Grok-3 mini |
|---|---|---|
| WeirdML | 40.6% | 42.6% |
| LMArena Coding | 1434 | 1380 |
| SWE-bench Verified (bash only) | 54.2% | — |
| Aider Polyglot | — | 49.3% |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |
Reasoning GLM-4.5 leads
GLM-4.5: 27.7 (#99), Grok-3 mini: 13.8 (#323)
| Benchmark | GLM-4.5 | Grok-3 mini |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 61.3% |
| LMArena Hard Prompts | 1430 | 1374 |
| ARC-AGI-2 | — | 0.4% |
| ARC-AGI-1 | — | 16.5% |
| Epoch Capabilities Index | — | 140.35 |
Math Grok-3 mini leads
GLM-4.5: 36.3 (#119), Grok-3 mini: 40.3 (#78)
| Benchmark | GLM-4.5 | Grok-3 mini |
|---|---|---|
| LMArena Math | 1427 | 1386 |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Grok-3 mini leads
GLM-4.5: 35.5 (#172), Grok-3 mini: 46.3 (#75)
| Benchmark | GLM-4.5 | Grok-3 mini |
|---|---|---|
| Confabulations | 11.3% | 10.8% |
| LMArena Expert | 1433 | 1395 |
| GPQA Diamond | — | 76.3% |
| Humanity's Last Exam | 8.3% | — |
| MMLU-Pro | — | 79.9% |
| GPQA (HELM) | — | 67.5% |
Multilingual GLM-4.5 leads
GLM-4.5: 53.0 (#74), Grok-3 mini: 48.3 (#141)
| Benchmark | GLM-4.5 | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1417 | 1352 |
| LMArena Chinese | 1465 | 1387 |
| LMArena French | 1423 | 1357 |
| LMArena German | 1406 | 1350 |
| LMArena Japanese | 1416 | 1343 |
| LMArena Korean | 1382 | 1336 |
| LMArena Russian | 1414 | 1352 |
| LMArena Spanish | 1454 | 1379 |
Instruction Following Grok-3 mini leads
GLM-4.5: 74.3 (#100), Grok-3 mini: 78.7 (#8)
| Benchmark | GLM-4.5 | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1405 | 1356 |
| IFEval | — | 95.1% |
Long Context Grok-3 mini leads
GLM-4.5: 38.2 (#196), Grok-3 mini: 41.0 (#142)
| Benchmark | GLM-4.5 | Grok-3 mini |
|---|---|---|
| Fiction.LiveBench | 58.3% | 66.7% |
| LMArena Longer Query | 1413 | 1372 |
Writing & Preference GLM-4.5 leads
GLM-4.5: 57.7 (#121), Grok-3 mini: 52.7 (#163)
| Benchmark | GLM-4.5 | Grok-3 mini |
|---|---|---|
| LMArena Text | 1430 | 1370 |
| LMArena Creative Writing | 1395 | 1342 |
| Short-Story Creative Writing | 73.4% | 73.5% |
| LMArena Multi-Turn | 1415 | 1355 |
| EQ-Bench Creative Writing | 1343 | — |
| WildBench | — | 65.1% |
Frequently asked questions
Is GLM-4.5 better than Grok-3 mini?
GLM-4.5 and Grok-3 mini score almost the same on the Noometry Index (41.4 vs 41.0), so choose on price, context window or the category you care about most.
Is GLM-4.5 or Grok-3 mini better for coding?
They score almost the same on coding (41.1 vs 40.4); test both on your own repository before choosing.
How many benchmarks do GLM-4.5 and Grok-3 mini share?
22 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Grok-3 mini has 35.