Model comparison
GLM-4.6 vs Grok 4 Fast
GLM-4.6 is the stronger model overall, scoring 40.9 to 39.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. GLM-4.6 scores higher in 8 categories and Grok 4 Fast in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 Fast leads 63.2 to 43.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 47.4% for GLM-4.6 and 66.1% for Grok 4 Fast.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | Grok 4 Fast | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 40.9 | 39.0 |
| Released | 2025-09-30 | 2025-09-19 |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 29 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 39.9 (#137), Grok 4 Fast: 32.3 (#264)
| Benchmark | GLM-4.6 | Grok 4 Fast |
|---|---|---|
| LMArena WebDev | 1339 | 1160 |
| LMArena Coding | 1449 | 1429 |
| SWE-bench Verified (bash only) | 55.4% | — |
| SciCode | 38.4% | — |
| WeirdML | — | 42.9% |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.1 (#60), Grok 4 Fast: 29.3 (#80)
| Benchmark | GLM-4.6 | Grok 4 Fast |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| τ²-bench Banking | — | 15.7% |
| Cybench | — | 30% |
| LMArena Search | — | 1171 |
Reasoning Too close to call
GLM-4.6: 23.1 (#168), Grok 4 Fast: 22.5 (#179)
| Benchmark | GLM-4.6 | Grok 4 Fast |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 66.1% |
| LMArena Hard Prompts | 1440 | 1413 |
| ARC-AGI-2 | — | 5.3% |
| ARC-AGI-1 | — | 48.5% |
| CritPt | 1.1% | — |
| DTBench | — | 82.7% |
| Epoch Capabilities Index | — | 144.21 |
| ForecastBench | — | 60.5 |
Math Too close to call
GLM-4.6: 36.4 (#115), Grok 4 Fast: 36.1 (#126)
| Benchmark | GLM-4.6 | Grok 4 Fast |
|---|---|---|
| LMArena Math | 1431 | 1419 |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-4.6 leads
GLM-4.6: 39.6 (#118), Grok 4 Fast: 31.5 (#211)
| Benchmark | GLM-4.6 | Grok 4 Fast |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 19.7% |
| LMArena Expert | 1432 | 1411 |
Multilingual GLM-4.6 leads
GLM-4.6: 53.6 (#62), Grok 4 Fast: 51.5 (#106)
| Benchmark | GLM-4.6 | Grok 4 Fast |
|---|---|---|
| LMArena Non-English | 1426 | 1397 |
| LMArena Chinese | 1500 | 1458 |
| LMArena French | 1459 | 1433 |
| LMArena German | 1447 | 1383 |
| LMArena Japanese | 1394 | 1358 |
| LMArena Korean | 1401 | 1359 |
| LMArena Russian | 1418 | 1387 |
| LMArena Spanish | 1436 | 1414 |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.5 (#93), Grok 4 Fast: 73.4 (#116)
| Benchmark | GLM-4.6 | Grok 4 Fast |
|---|---|---|
| LMArena Instruction Following | 1410 | 1388 |
Long Context Grok 4 Fast leads
GLM-4.6: 43.4 (#91), Grok 4 Fast: 63.2 (#3)
| Benchmark | GLM-4.6 | Grok 4 Fast |
|---|---|---|
| LMArena Longer Query | 1423 | 1415 |
| Fiction.LiveBench | — | 94.4% |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.3 (#86), Grok 4 Fast: 60.2 (#96)
| Benchmark | GLM-4.6 | Grok 4 Fast |
|---|---|---|
| LMArena Text | 1440 | 1407 |
| LMArena Creative Writing | 1411 | 1388 |
| LMArena Multi-Turn | 1427 | 1414 |
| EQ-Bench Creative Writing | 1411 | — |
Frequently asked questions
Is GLM-4.6 better than Grok 4 Fast?
GLM-4.6 is the stronger model overall, scoring 40.9 to 39.0 on the Noometry Index.
Is GLM-4.6 or Grok 4 Fast better for coding?
GLM-4.6 scores higher on coding benchmarks: 39.9 versus 32.3 in the Noometry coding category.
How many benchmarks do GLM-4.6 and Grok 4 Fast share?
20 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Grok 4 Fast has 30.